Initial snapshot: hand motion pipeline (Dyn-HaMR + dex-retargeting + SPIDER)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-09-15 14:13:49 +08:00
commit 7e4ef6f98b
7002 changed files with 1452249 additions and 0 deletions
@@ -0,0 +1,30 @@
+# Associative embedding: End-to-end learning for joint detection and grouping (AE)
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://arxiv.org/abs/1611.05424">Associative Embedding (NIPS'2017)</a></summary>
+
+```bibtex
+@inproceedings{newell2017associative,
+  title={Associative embedding: End-to-end learning for joint detection and grouping},
+  author={Newell, Alejandro and Huang, Zhiao and Deng, Jia},
+  booktitle={Advances in neural information processing systems},
+  pages={2277--2287},
+  year={2017}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+We introduce associative embedding, a novel method for supervising convolutional neural networks for the task of detection and grouping. A number of computer vision problems can be framed in this manner including multi-person pose estimation, instance segmentation, and multi-object tracking. Usually the grouping of detections is achieved with multi-stage pipelines, instead we propose an approach that teaches a network to simultaneously output detections and group assignments. This technique can be easily integrated into any state-of-the-art network architecture that produces pixel-wise predictions. We show how to apply this method to both multi-person pose estimation and instance segmentation and report state-of-the-art performance for multi-person pose on the MPII and MS-COCO datasets.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146514181-84f22623-6b73-4656-89b8-9e7f551e9cc0.png">
+</div>
@@ -0,0 +1,31 @@
+# Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://arxiv.org/pdf/1904.07399.pdf">AdaptiveWingloss (ICCV'2019)</a></summary>
+
+```bibtex
+@inproceedings{wang2019adaptive,
+  title={Adaptive wing loss for robust face alignment via heatmap regression},
+  author={Wang, Xinyao and Bo, Liefeng and Fuxin, Li},
+  booktitle={Proceedings of the IEEE/CVF international conference on computer vision},
+  pages={6971--6981},
+  year={2019}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Heatmap regression with a deep network has become one of the mainstream approaches to localize facial landmarks. However, the loss function for heatmap regression is rarely studied. In this paper, we analyze the ideal loss function properties for heatmap regression in face alignment problems. Then we propose a novel loss function, named Adaptive Wing loss, that is able to adapt its shape to different types of ground truth heatmap pixels. This adaptability penalizes loss more on foreground pixels while less on background pixels. To address the imbalance between foreground and background pixels, we also propose Weighted Loss Map, which assigns high weights on foreground and difficult background pixels to help training process focus more on pixels that are crucial to landmark localization. To further improve face alignment accuracy, we introduce boundary prediction and CoordConv with boundary coordinates. Extensive experiments on different benchmarks, including COFW, 300W and WFLW, show our approach outperforms the state-of-the-art by a significant margin on
+various evaluation metrics. Besides, the Adaptive Wing loss also helps other heatmap regression tasks.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/148007960-a06a34d8-8090-49e1-80db-6bbe4a7e7e8d.png">
+</div>
@@ -0,0 +1,30 @@
+# Convolutional pose machines
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_cvpr_2016/html/Wei_Convolutional_Pose_Machines_CVPR_2016_paper.html">CPM (CVPR'2016)</a></summary>
+
+```bibtex
+@inproceedings{wei2016convolutional,
+  title={Convolutional pose machines},
+  author={Wei, Shih-En and Ramakrishna, Varun and Kanade, Takeo and Sheikh, Yaser},
+  booktitle={Proceedings of the IEEE conference on Computer Vision and Pattern Recognition},
+  pages={4724--4732},
+  year={2016}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+We introduce associative embedding, a novel method for supervising convolutional neural networks for the task of detection and grouping. A number of computer vision problems can be framed in this manner including multi-person pose estimation, instance segmentation, and multi-object tracking. Usually the grouping of detections is achieved with multi-stage pipelines, instead we propose an approach that teaches a network to simultaneously output detections and group assignments. This technique can be easily integrated into any state-of-the-art network architecture that produces pixel-wise predictions. We show how to apply this method to both multi-person pose estimation and instance segmentation and report state-of-the-art performance for multi-person pose on the MPII and MS-COCO datasets.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146514331-a599580b-69a5-4ee4-9aaf-4a72f9c25c9a.png">
+</div>
@@ -0,0 +1,30 @@
+# Distribution-aware coordinate representation for human pose estimation
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_CVPR_2020/html/Zhang_Distribution-Aware_Coordinate_Representation_for_Human_Pose_Estimation_CVPR_2020_paper.html">DarkPose (CVPR'2020)</a></summary>
+
+```bibtex
+@inproceedings{zhang2020distribution,
+  title={Distribution-aware coordinate representation for human pose estimation},
+  author={Zhang, Feng and Zhu, Xiatian and Dai, Hanbin and Ye, Mao and Zhu, Ce},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
+  pages={7093--7102},
+  year={2020}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+While being the de facto standard coordinate representation for human pose estimation, heatmap has not been investigated in-depth. This work fills this gap. For the first time, we find that the process of decoding the predicted heatmaps into the final joint coordinates in the original image space is surprisingly significant for the performance. We further probe the design limitations of the standard coordinate decoding method, and propose a more principled distributionaware decoding method. Also, we improve the standard coordinate encoding process (i.e. transforming ground-truth coordinates to heatmaps) by generating unbiased/accurate heatmaps. Taking the two together, we formulate a novel Distribution-Aware coordinate Representation of Keypoints (DARK) method. Serving as a model-agnostic plug-in, DARK brings about significant performance boost to existing human pose estimation models. Extensive experiments show that DARK yields the best results on two common benchmarks, MPII and COCO. Besides, DARK achieves the 2nd place entry in the ICCV 2019 COCO Keypoints Challenge. The code is available online.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146514732-1d53614b-e5b7-4a1c-a39f-6fc726217d81.png">
+</div>
@@ -0,0 +1,30 @@
+# DeepPose: Human pose estimation via deep neural networks
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_cvpr_2014/html/Toshev_DeepPose_Human_Pose_2014_CVPR_paper.html">DeepPose (CVPR'2014)</a></summary>
+
+```bibtex
+@inproceedings{toshev2014deeppose,
+  title={Deeppose: Human pose estimation via deep neural networks},
+  author={Toshev, Alexander and Szegedy, Christian},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={1653--1660},
+  year={2014}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+We propose a method for human pose estimation based on Deep Neural Networks (DNNs). The pose estimation is formulated as a DNN-based regression problem towards body joints. We present a cascade of such DNN regressors which results in high precision pose estimates. The approach has the advantage of reasoning about pose in a holistic fashion and has a simple but yet powerful formulation which capitalizes on recent advances in Deep Learning. We present a detailed empirical analysis with state-of-art or better performance on four academic benchmarks of diverse real-world images.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146515040-a82a8a29-d6bc-42f1-a2ab-7dfa610ce363.png">
+</div>
@@ -0,0 +1,30 @@
+# HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_CVPR_2020/html/Cheng_HigherHRNet_Scale-Aware_Representation_Learning_for_Bottom-Up_Human_Pose_Estimation_CVPR_2020_paper.html">HigherHRNet (CVPR'2020)</a></summary>
+
+```bibtex
+@inproceedings{cheng2020higherhrnet,
+  title={HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation},
+  author={Cheng, Bowen and Xiao, Bin and Wang, Jingdong and Shi, Honghui and Huang, Thomas S and Zhang, Lei},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
+  pages={5386--5395},
+  year={2020}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Bottom-up human pose estimation methods have difficulties in predicting the correct pose for small persons due to challenges in scale variation. In this paper, we present HigherHRNet: a novel bottom-up human pose estimation method for learning scale-aware representations using high-resolution feature pyramids. Equipped with multi-resolution supervision for training and multi-resolution aggregation for inference, the proposed approach is able to solve the scale variation challenge in bottom-up multi-person pose estimation and localize keypoints more precisely, especially for small person. The feature pyramid in HigherHRNet consists of feature map outputs from HRNet and upsampled higher-resolution outputs through a transposed convolution. HigherHRNet outperforms the previous best bottom-up method by 2.5% AP for medium person on COCO test-dev, showing its effectiveness in handling scale variation. Furthermore, HigherHRNet achieves new state-of-the-art result on COCO test-dev (70.5% AP) without using refinement or other post-processing techniques, surpassing all existing bottom-up methods. HigherHRNet even surpasses all top-down methods on CrowdPose test (67.6% AP), suggesting its robustness in crowded scene.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146515482-975050d6-57da-469a-8dda-201675a404e7.png">
+</div>
@@ -0,0 +1,32 @@
+# End-to-end Recovery of Human Shape and Pose
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_cvpr_2018/html/Kanazawa_End-to-End_Recovery_of_CVPR_2018_paper.html">HMR (CVPR'2018)</a></summary>
+
+```bibtex
+@inProceedings{kanazawaHMR18,
+  title={End-to-end Recovery of Human Shape and Pose},
+  author = {Angjoo Kanazawa
+  and Michael J. Black
+  and David W. Jacobs
+  and Jitendra Malik},
+  booktitle={Computer Vision and Pattern Recognition (CVPR)},
+  year={2018}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+We describe Human Mesh Recovery (HMR), an end-to-end framework for reconstructing a full 3D mesh of a human body from a single RGB image. In contrast to most current methods that compute 2D or 3D joint locations, we produce a richer and more useful mesh representation that is parameterized by shape and 3D joint angles. The main objective is to minimize the reprojection loss of keypoints, which allows our model to be trained using in-the-wild images that only have ground truth 2D annotations. However, the reprojection loss alone is highly underconstrained. In this work we address this problem by introducing an adversary trained to tell whether human body shape and pose are real or not using a large database of 3D human meshes. We show that HMR can be trained with and without using any paired 2D-to-3D supervision. We do not rely on intermediate 2D keypoint detections and infer 3D pose and shape parameters directly from image pixels. Our model runs in real-time given a bounding box containing the person. We demonstrate our approach on various images in-the-wild and out-perform previous optimization-based methods that output 3D meshes and show competitive results on tasks such as 3D joint location estimation and part segmentation.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146515822-a271ec4d-4045-4456-a7cb-740018317053.png">
+</div>
@@ -0,0 +1,31 @@
+# Stacked hourglass networks for human pose estimation
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://link.springer.com/chapter/10.1007/978-3-319-46484-8_29">Hourglass (ECCV'2016)</a></summary>
+
+```bibtex
+@inproceedings{newell2016stacked,
+  title={Stacked hourglass networks for human pose estimation},
+  author={Newell, Alejandro and Yang, Kaiyu and Deng, Jia},
+  booktitle={European conference on computer vision},
+  pages={483--499},
+  year={2016},
+  organization={Springer}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+This work introduces a novel convolutional network architecture for the task of human pose estimation. Features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body. We show how repeated bottom-up, top-down processing used in conjunction with intermediate supervision is critical to improving the performance of the network. We refer to the architecture as a “stacked hourglass” network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions. State-of-the-art results are achieved on the FLIC and MPII benchmarks outcompeting all recent methods.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146516901-cee086aa-6b7c-4f79-82bd-1168f03ea63b.png">
+</div>
@@ -0,0 +1,32 @@
+# Deep high-resolution representation learning for human pose estimation
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_CVPR_2019/html/Sun_Deep_High-Resolution_Representation_Learning_for_Human_Pose_Estimation_CVPR_2019_paper.html">HRNet (CVPR'2019)</a></summary>
+
+```bibtex
+@inproceedings{sun2019deep,
+  title={Deep high-resolution representation learning for human pose estimation},
+  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={5693--5703},
+  year={2019}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+In this paper, we are interested in the human pose estimation problem with a focus on learning reliable highresolution representations. Most existing methods recover high-resolution representations from low-resolution representations produced by a high-to-low resolution network. Instead, our proposed network maintains high-resolution representations through the whole process. We start from a high-resolution subnetwork as the first stage, gradually add high-to-low resolution subnetworks one by one to form more stages, and connect the mutliresolution subnetworks in parallel. We conduct repeated multi-scale fusions such that each of the high-to-low resolution representations receives information from other parallel representations over and over, leading to rich highresolution representations. As a result, the predicted keypoint heatmap is potentially more accurate and spatially more precise. We empirically demonstrate the effectiveness
+of our network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection
+dataset and the MPII Human Pose dataset. In addition, we show the superiority of our network in pose tracking on the PoseTrack dataset.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146518010-9c1d6078-dd9c-4610-94a9-cbcb60aa87c0.png">
+</div>
@@ -0,0 +1,31 @@
+# Deep high-resolution representation learning for visual recognition
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://ieeexplore.ieee.org/abstract/document/9052469/">HRNetv2 (TPAMI'2019)</a></summary>
+
+```bibtex
+@article{WangSCJDZLMTWLX19,
+  title={Deep High-Resolution Representation Learning for Visual Recognition},
+  author={Jingdong Wang and Ke Sun and Tianheng Cheng and
+          Borui Jiang and Chaorui Deng and Yang Zhao and Dong Liu and Yadong Mu and
+          Mingkui Tan and Xinggang Wang and Wenyu Liu and Bin Xiao},
+  journal={TPAMI},
+  year={2019}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions in series (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representations through the whole process. There are two key characteristics: (i) Connect the high-to-low resolution convolution streams in parallel and (ii) repeatedly exchange the information across resolutions. The benefit is that the resulting representation is semantically richer and spatially more precise. We show the superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, suggesting that the HRNet is a stronger backbone for computer vision problems.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146519239-b3416e9a-0f3a-493a-9cc5-2d257b7fae01.png">
+</div>
@@ -0,0 +1,29 @@
+# InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://link.springer.com/content/pdf/10.1007/978-3-030-58565-5_33.pdf">InterNet (ECCV'2020)</a></summary>
+
+```bibtex
+@InProceedings{Moon_2020_ECCV_InterHand2.6M,
+author = {Moon, Gyeongsik and Yu, Shoou-I and Wen, He and Shiratori, Takaaki and Lee, Kyoung Mu},
+title = {InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image},
+booktitle = {European Conference on Computer Vision (ECCV)},
+year = {2020}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Analysis of hand-hand interactions is a crucial step towards better understanding human behavior. However, most researches in 3D hand pose estimation have focused on the isolated single hand case. Therefore, we firstly propose (1) a large-scale dataset, InterHand2.6M, and (2) a baseline network, InterNet, for 3D interacting hand pose estimation from a single RGB image. The proposed InterHand2.6M consists of 2.6 M labeled single and interacting hand frames under various poses from multiple subjects. Our InterNet simultaneously performs 3D single and interacting hand pose estimation. In our experiments, we demonstrate big gains in 3D interacting hand pose estimation accuracy when leveraging the interacting hand data in InterHand2.6M. We also report the accuracy of InterNet on InterHand2.6M, which serves as a strong baseline for this new dataset. Finally, we show 3D interacting hand pose estimation results from general images.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146519040-dfd5662d-a769-4e63-bff8-cd70877e1acb.png">
+</div>
@@ -0,0 +1,30 @@
+# Lite-HRNet: A Lightweight High-Resolution Network
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://arxiv.org/abs/2104.06403">LiteHRNet (CVPR'2021)</a></summary>
+
+```bibtex
+@inproceedings{Yulitehrnet21,
+  title={Lite-HRNet: A Lightweight High-Resolution Network},
+  author={Yu, Changqian and Xiao, Bin and Gao, Changxin and Yuan, Lu and Zhang, Lei and Sang, Nong and Wang, Jingdong},
+  booktitle={CVPR},
+  year={2021}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+We present an efficient high-resolution network, Lite-HRNet, for human pose estimation. We start by simply applying the efficient shuffle block in ShuffleNet to HRNet (high-resolution network), yielding stronger performance over popular lightweight networks, such as MobileNet, ShuffleNet, and Small HRNet.
+We find that the heavily-used pointwise (1x1) convolutions in shuffle blocks become the computational bottleneck. We introduce a lightweight unit, conditional channel weighting, to replace costly pointwise (1x1) convolutions in shuffle blocks. The complexity of channel weighting is linear w.r.t the number of channels and lower than the quadratic time complexity for pointwise convolutions. Our solution learns the weights from all the channels and over multiple resolutions that are readily available in the parallel branches in HRNet. It uses the weights as the bridge to exchange information across channels and resolutions, compensating the role played by the pointwise (1x1) convolution. Lite-HRNet demonstrates superior results on human pose estimation over popular lightweight networks. Moreover, Lite-HRNet can be easily applied to semantic segmentation task in the same lightweight manner.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146520579-3e86e3af-a8b2-4071-94da-916e0ce90464.png">
+</div>
@@ -0,0 +1,29 @@
+# Rethinking on multi-stage networks for human pose estimation
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://arxiv.org/abs/1901.00148">MSPN (ArXiv'2019)</a></summary>
+
+```bibtex
+@article{li2019rethinking,
+  title={Rethinking on Multi-Stage Networks for Human Pose Estimation},
+  author={Li, Wenbo and Wang, Zhicheng and Yin, Binyi and Peng, Qixiang and Du, Yuming and Xiao, Tianzi and Yu, Gang and Lu, Hongtao and Wei, Yichen and Sun, Jian},
+  journal={arXiv preprint arXiv:1901.00148},
+  year={2019}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Existing pose estimation approaches fall into two categories: single-stage and multi-stage methods. While multi-stage methods are seemingly more suited for the task, their performance in current practice is not as good as single-stage methods. This work studies this issue. We argue that the current multi-stage methods' unsatisfactory performance comes from the insufficiency in various design choices. We propose several improvements, including the single-stage module design, cross stage feature aggregation, and coarse-to-fine supervision. The resulting method establishes the new state-of-the-art on both MS COCO and MPII Human Pose dataset, justifying the effectiveness of a multi-stage architecture. The source code is publicly available for further research.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146520722-74c1ef85-9fa3-4b96-8cbf-4a2c86a80adc.png">
+</div>
@@ -0,0 +1,29 @@
+# Learning Temporal Pose Estimation from Sparsely-Labeled Videos
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://arxiv.org/abs/1906.04016">PoseWarper (NeurIPS'2019)</a></summary>
+
+```bibtex
+@inproceedings{NIPS2019_gberta,
+title = {Learning Temporal Pose Estimation from Sparsely Labeled Videos},
+author = {Bertasius, Gedas and Feichtenhofer, Christoph, and Tran, Du and Shi, Jianbo, and Torresani, Lorenzo},
+booktitle = {Advances in Neural Information Processing Systems 33},
+year = {2019},
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Modern approaches for multi-person pose estimation in video require large amounts of dense annotations. However, labeling every frame in a video is costly and labor intensive. To reduce the need for dense annotations, we propose a PoseWarper network that leverages training videos with sparse annotations (every k frames) to learn to perform dense temporal pose propagation and estimation. Given a pair of video frames---a labeled Frame A and an unlabeled Frame B---we train our model to predict human pose in Frame A using the features from Frame B by means of deformable convolutions to implicitly learn the pose warping between A and B. We demonstrate that we can leverage our trained PoseWarper for several applications. First, at inference time we can reverse the application direction of our network in order to propagate pose information from manually annotated frames to unlabeled frames. This makes it possible to generate pose annotations for the entire video given only a few manually-labeled frames. Compared to modern label propagation methods based on optical flow, our warping mechanism is much more compact (6M vs 39M parameters), and also more accurate (88.7% mAP vs 83.8% mAP). We also show that we can improve the accuracy of a pose estimator by training it on an augmented dataset obtained by adding our propagated poses to the original manual labels. Lastly, we can use our PoseWarper to aggregate temporal pose information from neighboring frames during inference. This allows our system to achieve state-of-the-art pose detection results on the PoseTrack2017 and PoseTrack2018 datasets.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146521380-97f7c23c-4960-454c-bd93-426a9cca175c.png">
+</div>
@@ -0,0 +1,31 @@
+# Learning delicate local representations for multi-person pose estimation
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://link.springer.com/chapter/10.1007/978-3-030-58580-8_27">RSN (ECCV'2020)</a></summary>
+
+```bibtex
+@misc{cai2020learning,
+    title={Learning Delicate Local Representations for Multi-Person Pose Estimation},
+    author={Yuanhao Cai and Zhicheng Wang and Zhengxiong Luo and Binyi Yin and Angang Du and Haoqian Wang and Xinyu Zhou and Erjin Zhou and Xiangyu Zhang and Jian Sun},
+    year={2020},
+    eprint={2003.04030},
+    archivePrefix={arXiv},
+    primaryClass={cs.CV}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+In this paper, we propose a novel method called Residual Steps Network (RSN). RSN aggregates features with the same spatial size (Intra-level features) efficiently to obtain delicate local representations, which retain rich low-level spatial information and result in precise keypoint localization. Additionally, we observe the output features contribute differently to final performance. To tackle this problem, we propose an efficient attention mechanism - Pose Refine Machine (PRM) to make a trade-off between local and global representations in output features and further refine the keypoint locations. Our approach won the 1st place of COCO Keypoint Challenge 2019 and achieves state-of-the-art results on both COCO and MPII benchmarks, without using extra training data and pretrained model. Our single model achieves 78.6 on COCO test-dev, 93.0 on MPII test dataset. Ensembled models achieve 79.2 on COCO test-dev, 77.1 on COCO test-challenge dataset.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146522226-5041d16e-41cb-4d31-ae53-dbe21314a697.png">
+</div>
@@ -0,0 +1,30 @@
+# Improving Convolutional Networks with Self-Calibrated Convolutions
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_CVPR_2020/html/Liu_Improving_Convolutional_Networks_With_Self-Calibrated_Convolutions_CVPR_2020_paper.html">SCNet (CVPR'2020)</a></summary>
+
+```bibtex
+@inproceedings{liu2020improving,
+  title={Improving Convolutional Networks with Self-Calibrated Convolutions},
+  author={Liu, Jiang-Jiang and Hou, Qibin and Cheng, Ming-Ming and Wang, Changhu and Feng, Jiashi},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
+  pages={10096--10105},
+  year={2020}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Recent advances on CNNs are mostly devoted to designing more complex architectures to enhance their representation learning capacity. In this paper, we consider how to improve the basic convolutional feature transformation process of CNNs without tuning the model architectures. To this end, we present a novel self-calibrated convolutions that explicitly expand fields-of-view of each convolutional layers through internal communications and hence enrich the output features. In particular, unlike the standard convolutions that fuse spatial and channel-wise information using small kernels (e.g., 3x3), self-calibrated convolutions adaptively build long-range spatial and inter-channel dependencies around each spatial location through a novel self-calibration operation. Thus, it can help CNNs generate more discriminative representations by explicitly incorporating richer information. Our self-calibrated convolution design is simple and generic, and can be easily applied to augment standard convolutional layers without introducing extra parameters and complexity. Extensive experiments demonstrate that when applying self-calibrated convolutions into different backbones, our networks can significantly improve the baseline models in a variety of vision tasks, including image recognition, object detection, instance segmentation, and keypoint detection, with no need to change the network architectures. We hope this work could provide a promising way for future research in designing novel convolutional feature transformations for improving convolutional networks. Code is available on the project page.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146522623-fdc88996-1a8f-4b0a-bdee-fc284dfd7348.png">
+</div>
@@ -0,0 +1,31 @@
+# Simple baselines for human pose estimation and tracking
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_ECCV_2018/html/Bin_Xiao_Simple_Baselines_for_ECCV_2018_paper.html">SimpleBaseline2D (ECCV'2018)</a></summary>
+
+```bibtex
+@inproceedings{xiao2018simple,
+  title={Simple baselines for human pose estimation and tracking},
+  author={Xiao, Bin and Wu, Haiping and Wei, Yichen},
+  booktitle={Proceedings of the European conference on computer vision (ECCV)},
+  pages={466--481},
+  year={2018}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+There has been significant progress on pose estimation and increasing interests on pose tracking in recent years. At the same time, the overall algorithm and system complexity increases as well, making the algorithm analysis and comparison more difficult. This work provides simple and effective baseline methods. They are helpful for inspiring and
+evaluating new ideas for the field. State-of-the-art results are achieved on challenging benchmarks.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146522977-5f355832-e9c1-442f-a34f-9d24fb0aefa8.png">
+</div>
@@ -0,0 +1,29 @@
+# A simple yet effective baseline for 3d human pose estimation
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_iccv_2017/html/Martinez_A_Simple_yet_ICCV_2017_paper.html">SimpleBaseline3D (ICCV'2017)</a></summary>
+
+```bibtex
+@inproceedings{martinez_2017_3dbaseline,
+  title={A simple yet effective baseline for 3d human pose estimation},
+  author={Martinez, Julieta and Hossain, Rayat and Romero, Javier and Little, James J.},
+  booktitle={ICCV},
+  year={2017}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Following the success of deep convolutional networks, state-of-the-art methods for 3d human pose estimation have focused on deep end-to-end systems that predict 3d joint locations given raw image pixels. Despite their excellent performance, it is often not easy to understand whether their remaining error stems from a limited 2d pose (visual) understanding, or from a failure to map 2d poses into 3-dimensional positions. With the goal of understanding these sources of error, we set out to build a system that given 2d joint locations predicts 3d positions. Much to our surprise, we have found that, with current technology, "lifting" ground truth 2d joint locations to 3d space is a task that can be solved with a remarkably low error rate: a relatively simple deep feed-forward network outperforms the best reported result by about 30% on Human3.6M, the largest publicly available 3d pose estimation benchmark. Furthermore, training our system on the output of an off-the-shelf state-of-the-art 2d detector (i.e., using images as input) yields state of the art results -- this includes an array of systems that have been trained end-to-end specifically for this task. Our results indicate that a large portion of the error of modern deep 3d pose estimation systems stems from their visual analysis, and suggests directions to further advance the state of the art in 3d human pose estimation.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146523402-1b2a6c14-a5f4-4266-b2b4-19c0738cd434.png">
+</div>
@@ -0,0 +1,30 @@
+# Structure-Coherent Deep Feature Learning for Robust Face Alignment
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://ieeexplore.ieee.org/document/9442331/">SoftWingloss (TIP'2021)</a></summary>
+
+```bibtex
+@article{lin2021structure,
+  title={Structure-Coherent Deep Feature Learning for Robust Face Alignment},
+  author={Lin, Chunze and Zhu, Beier and Wang, Quan and Liao, Renjie and Qian, Chen and Lu, Jiwen and Zhou, Jie},
+  journal={IEEE Transactions on Image Processing},
+  year={2021},
+  publisher={IEEE}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+In this paper, we propose a structure-coherent deep feature learning method for face alignment. Unlike most existing face alignment methods which overlook the facial structure cues, we explicitly exploit the relation among facial landmarks to make the detector robust to hard cases such as occlusion and large pose. Specifically, we leverage a landmark-graph relational network to enforce the structural relationships among landmarks. We consider the facial landmarks as structural graph nodes and carefully design the neighborhood to passing features among the most related nodes. Our method dynamically adapts the weights of node neighborhood to eliminate distracted information from noisy nodes, such as occluded landmark point. Moreover, different from most previous works which only tend to penalize the landmarks absolute position during the training, we propose a relative location loss to enhance the information of relative location of landmarks. This relative location supervision further regularizes the facial structure. Our approach considers the interactions among facial landmarks and can be easily implemented on top of any convolutional backbone to boost the performance. Extensive experiments on three popular benchmarks, including WFLW, COFW and 300W, demonstrate the effectiveness of the proposed method. In particular, due to explicit structure modeling, our approach is especially robust to challenging cases resulting in impressive low failure rate on COFW and WFLW datasets.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/148036579-b128fb21-3a2d-4894-bb54-4223a4cdf856.png">
+</div>
@@ -0,0 +1,30 @@
+# The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_CVPR_2020/html/Huang_The_Devil_Is_in_the_Details_Delving_Into_Unbiased_Data_CVPR_2020_paper.html">UDP (CVPR'2020)</a></summary>
+
+```bibtex
+@InProceedings{Huang_2020_CVPR,
+  author = {Huang, Junjie and Zhu, Zheng and Guo, Feng and Huang, Guan},
+  title = {The Devil Is in the Details: Delving Into Unbiased Data Processing for Human Pose Estimation},
+  booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+  month = {June},
+  year = {2020}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Recently, the leading performance of human pose estimation is dominated by top-down methods. Being a fundamental component in training and inference, data processing has not been systematically considered in pose estimation community, to the best of our knowledge. In this paper, we focus on this problem and find that the devil of top-down pose estimator is in the biased data processing. Specifically, by investigating the standard data processing in state-of-the-art approaches mainly including data transformation and encoding-decoding, we find that the results obtained by common flipping strategy are unaligned with the original ones in inference. Moreover, there is statistical error in standard encoding-decoding during both training and inference. Two problems couple together and significantly degrade the pose estimation performance. Based on quantitative analyses, we then formulate a principled way to tackle this dilemma. Data is processed in continuous space based on unit length (the intervals between pixels) instead of in discrete space with pixel, and a combined classification and regression approach is adopted to perform encoding-decoding. The Unbiased Data Processing (UDP) for human pose estimation can be achieved by combining the two together. UDP not only boosts the performance of existing methods by a large margin but also plays a important role in result reproducing and future exploration. As a model-agnostic approach, UDP promotes SimpleBaseline-ResNet50-256x192 by 1.5 AP (70.2 to 71.7) and HRNet-W32-256x192 by 1.7 AP (73.5 to 75.2) on COCO test-dev set. The HRNet-W48-384x288 equipped with UDP achieves 76.5 AP and sets a new state-of-the-art for human pose estimation. The source code is publicly available for further research.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146524686-ddfe1356-77bd-46a0-a6cd-7ff418f65675.png">
+</div>
@@ -0,0 +1,30 @@
+# 3D human pose estimation in video with temporal convolutions and semi-supervised training
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_CVPR_2019/html/Pavllo_3D_Human_Pose_Estimation_in_Video_With_Temporal_Convolutions_and_CVPR_2019_paper.html">VideoPose3D (CVPR'2019)</a></summary>
+
+```bibtex
+@inproceedings{pavllo20193d,
+  title={3d human pose estimation in video with temporal convolutions and semi-supervised training},
+  author={Pavllo, Dario and Feichtenhofer, Christoph and Grangier, David and Auli, Michael},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
+  pages={7753--7762},
+  year={2019}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+In this work, we demonstrate that 3D poses in video can be effectively estimated with a fully convolutional model based on dilated temporal convolutions over 2D keypoints. We also introduce back-projection, a simple and effective semi-supervised training method that leverages unlabeled video data. We start with predicted 2D keypoints for unlabeled video, then estimate 3D poses and finally back-project to the input 2D keypoints. In the supervised setting, our fully-convolutional model outperforms the previous best result from the literature by 6 mm mean per-joint position error on Human3.6M, corresponding to an error reduction of 11%, and the model also shows significant improvements on HumanEva-I. Moreover, experiments with back-projection show that it comfortably outperforms previous state-of-the-art results in semi-supervised settings where labeled data is scarce.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146525184-34a14153-5cab-4fe0-8500-018c99a5f647.png">
+</div>
@@ -0,0 +1,29 @@
+# ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://arxiv.org/abs/2105.10154">ViPNAS (CVPR'2021)</a></summary>
+
+```bibtex
+@article{xu2021vipnas,
+  title={ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search},
+  author={Xu, Lumin and Guan, Yingda and Jin, Sheng and Liu, Wentao and Qian, Chen and Luo, Ping and Ouyang, Wanli and Wang, Xiaogang},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  year={2021}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Human pose estimation has achieved significant progress in recent years. However, most of the recent methods focus on improving accuracy using complicated models and ignoring real-time efficiency. To achieve a better trade-off between accuracy and efficiency, we propose a novel neural architecture search (NAS) method, termed ViPNAS, to search networks in both spatial and temporal levels for fast online video pose estimation. In the spatial level, we carefully design the search space with five different dimensions including network depth, width, kernel size, group number, and attentions. In the temporal level, we search from a series of temporal feature fusions to optimize the total accuracy and speed across multiple video frames. To the best of our knowledge, we are the first to search for the temporal feature fusion and automatic computation allocation in videos. Extensive experiments demonstrate the effectiveness of our approach on the challenging COCO2017 and PoseTrack2018 datasets. Our discovered model family, S-ViPNAS and T-ViPNAS, achieve significantly higher inference speed (CPU real-time) without sacrificing the accuracy compared to the previous state-of-the-art methods.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146527709-b8e55e40-426c-4958-8a35-b8d259e69efa.png">
+</div>
@@ -0,0 +1,29 @@
+# VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123460188.pdf">VoxelPose (ECCV'2020)</a></summary>
+
+```bibtex
+@inproceedings{tumultipose,
+  title={VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment},
+  author={Tu, Hanyue and Wang, Chunyu and Zeng, Wenjun},
+  booktitle={ECCV},
+  year={2020}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+We present VoxelPose to estimate 3D poses of multiple people from multiple camera views. In contrast to the previous efforts which require to establish cross-view correspondence based on noisy and incomplete 2D pose estimates, VoxelPose directly operates in the 3D space therefore avoids making incorrect decisions in each camera view. To achieve this goal, features in all camera views are aggregated in the 3D voxel space and fed into Cuboid Proposal Network (CPN) to localize all people. Then we propose Pose Regression Network (PRN) to estimate a detailed 3D pose for each proposal. The approach is robust to occlusion which occurs frequently in practice. Without bells and whistles, it outperforms the previous methods on several public datasets.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/148036780-b73a878c-7244-480b-b56e-ac739396856b.png">
+</div>
@@ -0,0 +1,31 @@
+# Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_cvpr_2018/html/Feng_Wing_Loss_for_CVPR_2018_paper.html">Wingloss (CVPR'2018)</a></summary>
+
+```bibtex
+@inproceedings{feng2018wing,
+  title={Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks},
+  author={Feng, Zhen-Hua and Kittler, Josef and Awais, Muhammad and Huber, Patrik and Wu, Xiao-Jun},
+  booktitle={Computer Vision and Pattern Recognition (CVPR), 2018 IEEE Conference on},
+  year={2018},
+  pages ={2235-2245},
+  organization={IEEE}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+We present a new loss function, namely Wing loss, for robust facial landmark localisation with Convolutional Neural Networks (CNNs). We first compare and analyse different loss functions including L2, L1 and smooth L1. The analysis of these loss functions suggests that, for the training of a CNN-based localisation model, more attention should be paid to small and medium range errors. To this end, we design a piece-wise loss function. The new loss amplifies the impact of errors from the interval (-w, w) by switching from L1 loss to a modified logarithm function. To address the problem of under-representation of samples with large out-of-plane head rotations in the training set, we propose a simple but effective boosting strategy, referred to as pose-based data balancing. In particular, we deal with the data imbalance problem by duplicating the minority training samples and perturbing them by injecting random image rotation, bounding box translation and other data augmentation approaches. Last, the proposed approach is extended to create a two-stage framework for robust facial landmark localisation. The experimental results obtained on AFLW and 300W demonstrate the merits of the Wing loss function, and prove the superiority of the proposed method over the state-of-the-art approaches.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146528473-f3228f69-b60e-4807-9c4b-b45997fbc530.png">
+</div>
@@ -0,0 +1,30 @@
+# Imagenet classification with deep convolutional neural networks
+
+<!-- [BACKBONE] -->
+
+<details>
+<summary align="right"><a href="https://proceedings.neurips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf">AlexNet (NeurIPS'2012)</a></summary>
+
+```bibtex
+@inproceedings{krizhevsky2012imagenet,
+  title={Imagenet classification with deep convolutional neural networks},
+  author={Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E},
+  booktitle={Advances in neural information processing systems},
+  pages={1097--1105},
+  year={2012}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overfitting in the fully-connected layers we employed a recently-developed regularization method called “dropout” that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146537150-39cd128e-185e-48eb-9d6b-7e9a187d2ae5.png">
+</div>
@@ -0,0 +1,30 @@
+# Convolutional pose machines
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_cvpr_2016/html/Wei_Convolutional_Pose_Machines_CVPR_2016_paper.html">CPM (CVPR'2016)</a></summary>
+
+```bibtex
+@inproceedings{wei2016convolutional,
+  title={Convolutional pose machines},
+  author={Wei, Shih-En and Ramakrishna, Varun and Kanade, Takeo and Sheikh, Yaser},
+  booktitle={Proceedings of the IEEE conference on Computer Vision and Pattern Recognition},
+  pages={4724--4732},
+  year={2016}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+We introduce associative embedding, a novel method for supervising convolutional neural networks for the task of detection and grouping. A number of computer vision problems can be framed in this manner including multi-person pose estimation, instance segmentation, and multi-object tracking. Usually the grouping of detections is achieved with multi-stage pipelines, instead we propose an approach that teaches a network to simultaneously output detections and group assignments. This technique can be easily integrated into any state-of-the-art network architecture that produces pixel-wise predictions. We show how to apply this method to both multi-person pose estimation and instance segmentation and report state-of-the-art performance for multi-person pose on the MPII and MS-COCO datasets.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146514331-a599580b-69a5-4ee4-9aaf-4a72f9c25c9a.png">
+</div>
@@ -0,0 +1,30 @@
+# HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_CVPR_2020/html/Cheng_HigherHRNet_Scale-Aware_Representation_Learning_for_Bottom-Up_Human_Pose_Estimation_CVPR_2020_paper.html">HigherHRNet (CVPR'2020)</a></summary>
+
+```bibtex
+@inproceedings{cheng2020higherhrnet,
+  title={HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation},
+  author={Cheng, Bowen and Xiao, Bin and Wang, Jingdong and Shi, Honghui and Huang, Thomas S and Zhang, Lei},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
+  pages={5386--5395},
+  year={2020}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Bottom-up human pose estimation methods have difficulties in predicting the correct pose for small persons due to challenges in scale variation. In this paper, we present HigherHRNet: a novel bottom-up human pose estimation method for learning scale-aware representations using high-resolution feature pyramids. Equipped with multi-resolution supervision for training and multi-resolution aggregation for inference, the proposed approach is able to solve the scale variation challenge in bottom-up multi-person pose estimation and localize keypoints more precisely, especially for small person. The feature pyramid in HigherHRNet consists of feature map outputs from HRNet and upsampled higher-resolution outputs through a transposed convolution. HigherHRNet outperforms the previous best bottom-up method by 2.5% AP for medium person on COCO test-dev, showing its effectiveness in handling scale variation. Furthermore, HigherHRNet achieves new state-of-the-art result on COCO test-dev (70.5% AP) without using refinement or other post-processing techniques, surpassing all existing bottom-up methods. HigherHRNet even surpasses all top-down methods on CrowdPose test (67.6% AP), suggesting its robustness in crowded scene.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146515482-975050d6-57da-469a-8dda-201675a404e7.png">
+</div>
@@ -0,0 +1,31 @@
+# Stacked hourglass networks for human pose estimation
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://link.springer.com/chapter/10.1007/978-3-319-46484-8_29">Hourglass (ECCV'2016)</a></summary>
+
+```bibtex
+@inproceedings{newell2016stacked,
+  title={Stacked hourglass networks for human pose estimation},
+  author={Newell, Alejandro and Yang, Kaiyu and Deng, Jia},
+  booktitle={European conference on computer vision},
+  pages={483--499},
+  year={2016},
+  organization={Springer}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+This work introduces a novel convolutional network architecture for the task of human pose estimation. Features are processed across all scales and consolidated to best capture the various spatial relationships associated with the body. We show how repeated bottom-up, top-down processing used in conjunction with intermediate supervision is critical to improving the performance of the network. We refer to the architecture as a “stacked hourglass” network based on the successive steps of pooling and upsampling that are done to produce a final set of predictions. State-of-the-art results are achieved on the FLIC and MPII benchmarks outcompeting all recent methods.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146516901-cee086aa-6b7c-4f79-82bd-1168f03ea63b.png">
+</div>
@@ -0,0 +1,39 @@
+# HRFormer: High-Resolution Vision Transformer for Dense Predict
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://proceedings.neurips.cc/paper/2021/hash/3bbfdde8842a5c44a0323518eec97cbe-Abstract.html">HRFormer (NIPS'2021)</a></summary>
+
+```bibtex
+@article{yuan2021hrformer,
+  title={HRFormer: High-Resolution Vision Transformer for Dense Predict},
+  author={Yuan, Yuhui and Fu, Rao and Huang, Lang and Lin, Weihong and Zhang, Chao and Chen, Xilin and Wang, Jingdong},
+  journal={Advances in Neural Information Processing Systems},
+  volume={34},
+  year={2021}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+We present a High-Resolution Transformer (HRFormer) that learns high-resolution representations for dense
+prediction tasks, in contrast to the original Vision Transformer that produces low-resolution representations
+and has high memory and computational cost. We take advantage of the multi-resolution parallel design
+introduced in high-resolution convolutional networks (HRNet), along with local-window self-attention
+that performs self-attention over small non-overlapping image windows, for improving the memory and
+computation efficiency. In addition, we introduce a convolution into the FFN to exchange information
+across the disconnected image windows. We demonstrate the effectiveness of the HighResolution Transformer
+on both human pose estimation and semantic segmentation tasks, e.g., HRFormer outperforms Swin
+transformer by 1.3 AP on COCO pose estimation with 50% fewer parameters and 30% fewer FLOPs.
+Code is available at: https://github.com/HRNet/HRFormer
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/28900607/155838218-a6aa12b5-5855-45ed-922e-1cfe74f63027.png">
+</div>
@@ -0,0 +1,32 @@
+# Deep high-resolution representation learning for human pose estimation
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_CVPR_2019/html/Sun_Deep_High-Resolution_Representation_Learning_for_Human_Pose_Estimation_CVPR_2019_paper.html">HRNet (CVPR'2019)</a></summary>
+
+```bibtex
+@inproceedings{sun2019deep,
+  title={Deep high-resolution representation learning for human pose estimation},
+  author={Sun, Ke and Xiao, Bin and Liu, Dong and Wang, Jingdong},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={5693--5703},
+  year={2019}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+In this paper, we are interested in the human pose estimation problem with a focus on learning reliable highresolution representations. Most existing methods recover high-resolution representations from low-resolution representations produced by a high-to-low resolution network. Instead, our proposed network maintains high-resolution representations through the whole process. We start from a high-resolution subnetwork as the first stage, gradually add high-to-low resolution subnetworks one by one to form more stages, and connect the mutliresolution subnetworks in parallel. We conduct repeated multi-scale fusions such that each of the high-to-low resolution representations receives information from other parallel representations over and over, leading to rich highresolution representations. As a result, the predicted keypoint heatmap is potentially more accurate and spatially more precise. We empirically demonstrate the effectiveness
+of our network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection
+dataset and the MPII Human Pose dataset. In addition, we show the superiority of our network in pose tracking on the PoseTrack dataset.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146518010-9c1d6078-dd9c-4610-94a9-cbcb60aa87c0.png">
+</div>
@@ -0,0 +1,31 @@
+# Deep high-resolution representation learning for visual recognition
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://ieeexplore.ieee.org/abstract/document/9052469/">HRNetv2 (TPAMI'2019)</a></summary>
+
+```bibtex
+@article{WangSCJDZLMTWLX19,
+  title={Deep High-Resolution Representation Learning for Visual Recognition},
+  author={Jingdong Wang and Ke Sun and Tianheng Cheng and
+          Borui Jiang and Chaorui Deng and Yang Zhao and Dong Liu and Yadong Mu and
+          Mingkui Tan and Xinggang Wang and Wenyu Liu and Bin Xiao},
+  journal={TPAMI},
+  year={2019}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions in series (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representations through the whole process. There are two key characteristics: (i) Connect the high-to-low resolution convolution streams in parallel and (ii) repeatedly exchange the information across resolutions. The benefit is that the resulting representation is semantically richer and spatially more precise. We show the superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, suggesting that the HRNet is a stronger backbone for computer vision problems.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146519239-b3416e9a-0f3a-493a-9cc5-2d257b7fae01.png">
+</div>
@@ -0,0 +1,30 @@
+# Lite-HRNet: A Lightweight High-Resolution Network
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://arxiv.org/abs/2104.06403">LiteHRNet (CVPR'2021)</a></summary>
+
+```bibtex
+@inproceedings{Yulitehrnet21,
+  title={Lite-HRNet: A Lightweight High-Resolution Network},
+  author={Yu, Changqian and Xiao, Bin and Gao, Changxin and Yuan, Lu and Zhang, Lei and Sang, Nong and Wang, Jingdong},
+  booktitle={CVPR},
+  year={2021}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+We present an efficient high-resolution network, Lite-HRNet, for human pose estimation. We start by simply applying the efficient shuffle block in ShuffleNet to HRNet (high-resolution network), yielding stronger performance over popular lightweight networks, such as MobileNet, ShuffleNet, and Small HRNet.
+We find that the heavily-used pointwise (1x1) convolutions in shuffle blocks become the computational bottleneck. We introduce a lightweight unit, conditional channel weighting, to replace costly pointwise (1x1) convolutions in shuffle blocks. The complexity of channel weighting is linear w.r.t the number of channels and lower than the quadratic time complexity for pointwise convolutions. Our solution learns the weights from all the channels and over multiple resolutions that are readily available in the parallel branches in HRNet. It uses the weights as the bridge to exchange information across channels and resolutions, compensating the role played by the pointwise (1x1) convolution. Lite-HRNet demonstrates superior results on human pose estimation over popular lightweight networks. Moreover, Lite-HRNet can be easily applied to semantic segmentation task in the same lightweight manner.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146520579-3e86e3af-a8b2-4071-94da-916e0ce90464.png">
+</div>
@@ -0,0 +1,30 @@
+# Mobilenetv2: Inverted residuals and linear bottlenecks
+
+<!-- [BACKBONE] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_cvpr_2018/html/Sandler_MobileNetV2_Inverted_Residuals_CVPR_2018_paper.html">MobilenetV2 (CVPR'2018)</a></summary>
+
+```bibtex
+@inproceedings{sandler2018mobilenetv2,
+  title={Mobilenetv2: Inverted residuals and linear bottlenecks},
+  author={Sandler, Mark and Howard, Andrew and Zhu, Menglong and Zhmoginov, Andrey and Chen, Liang-Chieh},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={4510--4520},
+  year={2018}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+In this paper we describe a new mobile architecture, mbox{MobileNetV2}, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes. We also describe efficient ways of applying these mobile models to object detection in a novel framework we call mbox{SSDLite}. Additionally, we demonstrate how to build mobile semantic segmentation models through a reduced form of mbox{DeepLabv3} which we call Mobile mbox{DeepLabv3}. is based on an inverted residual structure where the shortcut connections are between the thin bottleneck layers. The intermediate expansion layer uses lightweight depthwise convolutions to filter features as a source of non-linearity. Additionally, we find that it is important to remove non-linearities in the narrow layers in order to maintain representational power. We demonstrate that this improves performance and provide an intuition that led to this design. Finally, our approach allows decoupling of the input/output domains from the expressiveness of the transformation, which provides a convenient framework for further analysis. We measure our performance on mbox{ImageNet}~cite{Russakovsky:2015:ILS:2846547.2846559} classification, COCO object detection cite{COCO}, VOC image segmentation cite{PASCAL}. We evaluate the trade-offs between accuracy, and number of operations measured by multiply-adds (MAdd), as well as actual latency, and the number of parameters.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146537871-75c22a93-72ef-4a24-9ce9-0c2823381961.png">
+</div>
@@ -0,0 +1,29 @@
+# Rethinking on multi-stage networks for human pose estimation
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://arxiv.org/abs/1901.00148">MSPN (ArXiv'2019)</a></summary>
+
+```bibtex
+@article{li2019rethinking,
+  title={Rethinking on Multi-Stage Networks for Human Pose Estimation},
+  author={Li, Wenbo and Wang, Zhicheng and Yin, Binyi and Peng, Qixiang and Du, Yuming and Xiao, Tianzi and Yu, Gang and Lu, Hongtao and Wei, Yichen and Sun, Jian},
+  journal={arXiv preprint arXiv:1901.00148},
+  year={2019}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Existing pose estimation approaches fall into two categories: single-stage and multi-stage methods. While multi-stage methods are seemingly more suited for the task, their performance in current practice is not as good as single-stage methods. This work studies this issue. We argue that the current multi-stage methods' unsatisfactory performance comes from the insufficiency in various design choices. We propose several improvements, including the single-stage module design, cross stage feature aggregation, and coarse-to-fine supervision. The resulting method establishes the new state-of-the-art on both MS COCO and MPII Human Pose dataset, justifying the effectiveness of a multi-stage architecture. The source code is publicly available for further research.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146520722-74c1ef85-9fa3-4b96-8cbf-4a2c86a80adc.png">
+</div>
@@ -0,0 +1,29 @@
+# ResNeSt: Split-Attention Networks
+
+<!-- [BACKBONE] -->
+
+<details>
+<summary align="right"><a href="https://arxiv.org/abs/2004.08955">ResNeSt (ArXiv'2020)</a></summary>
+
+```bibtex
+@article{zhang2020resnest,
+  title={ResNeSt: Split-Attention Networks},
+  author={Zhang, Hang and Wu, Chongruo and Zhang, Zhongyue and Zhu, Yi and Zhang, Zhi and Lin, Haibin and Sun, Yue and He, Tong and Muller, Jonas and Manmatha, R. and Li, Mu and Smola, Alexander},
+  journal={arXiv preprint arXiv:2004.08955},
+  year={2020}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+It is well known that featuremap attention and multi-path representation are important for visual recognition. In this paper, we present a modularized architecture, which applies the channel-wise attention on different network branches to leverage their success in capturing cross-feature interactions and learning diverse representations. Our design results in a simple and unified computation block, which can be parameterized using only a few variables. Our model, named ResNeSt, outperforms EfficientNet in accuracy and latency trade-off on image classification. In addition, ResNeSt has achieved superior transfer learning results on several public benchmarks serving as the backbone, and has been adopted by the winning entries of COCO-LVIS challenge. The source code for complete system and pretrained models are publicly available.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146538001-387b40dc-886c-48c5-8621-1dc287fa2ae3.png">
+</div>
@@ -0,0 +1,32 @@
+# Deep residual learning for image recognition
+
+<!-- [BACKBONE] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_cvpr_2016/html/He_Deep_Residual_Learning_CVPR_2016_paper.html">ResNet (CVPR'2016)</a></summary>
+
+```bibtex
+@inproceedings{he2016deep,
+  title={Deep residual learning for image recognition},
+  author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={770--778},
+  year={2016}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from
+considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC
+& COCO 2015 competitions1 , where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146538539-d635ee57-200c-40f5-93cf-a34a5b416feb.png">
+</div>
@@ -0,0 +1,31 @@
+# Bag of tricks for image classification with convolutional neural networks
+
+<!-- [BACKBONE] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_CVPR_2019/html/He_Bag_of_Tricks_for_Image_Classification_with_Convolutional_Neural_Networks_CVPR_2019_paper.html">ResNetV1D (CVPR'2019)</a></summary>
+
+```bibtex
+@inproceedings{he2019bag,
+  title={Bag of tricks for image classification with convolutional neural networks},
+  author={He, Tong and Zhang, Zhi and Zhang, Hang and Zhang, Zhongyue and Xie, Junyuan and Li, Mu},
+  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
+  pages={558--567},
+  year={2019}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Much of the recent progress made in image classification research can be credited to training procedure refinements, such as changes in data augmentations and optimization methods. In the literature, however, most refinements are either briefly mentioned as implementation details or only visible in source code. In this paper, we will examine a collection of such refinements and empirically evaluate their impact on the final model accuracy through ablation study. We will show that, by combining these refinements together, we are able to improve various CNN models significantly. For example, we raise ResNet-50’s top-1 validation accuracy from 75.3% to 79.29% on ImageNet. We will also demonstrate that improvement on image classification accuracy leads to better transfer learning performance in other application domains such as object detection and semantic
+segmentation.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146539869-6deeea09-8f28-4b19-8737-2d9b0d080189.png">
+</div>
@@ -0,0 +1,30 @@
+# Aggregated residual transformations for deep neural networks
+
+<!-- [BACKBONE] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_cvpr_2017/html/Xie_Aggregated_Residual_Transformations_CVPR_2017_paper.html">ResNext (CVPR'2017)</a></summary>
+
+```bibtex
+@inproceedings{xie2017aggregated,
+  title={Aggregated residual transformations for deep neural networks},
+  author={Xie, Saining and Girshick, Ross and Doll{\'a}r, Piotr and Tu, Zhuowen and He, Kaiming},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={1492--1500},
+  year={2017}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+We present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transformations with the same topology. Our simple design results in a homogeneous, multi-branch architecture that has only a few hyper-parameters to set. This strategy exposes a new dimension, which we call "cardinality" (the size of the set of transformations), as an essential factor in addition to the dimensions of depth and width. On the ImageNet-1K dataset, we empirically show that even under the restricted condition of maintaining complexity, increasing cardinality is able to improve classification accuracy. Moreover, increasing cardinality is more effective than going deeper or wider when we increase the capacity. Our models, named ResNeXt, are the foundations of our entry to the ILSVRC 2016 classification task in which we secured 2nd place. We further investigate ResNeXt on an ImageNet-5K set and the COCO detection set, also showing better results than its ResNet counterpart. The code and models are publicly available online.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146540039-cd3950dd-a6d2-4836-9af2-f7f990e98f77.png">
+</div>
@@ -0,0 +1,31 @@
+# Learning delicate local representations for multi-person pose estimation
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://link.springer.com/chapter/10.1007/978-3-030-58580-8_27">RSN (ECCV'2020)</a></summary>
+
+```bibtex
+@misc{cai2020learning,
+    title={Learning Delicate Local Representations for Multi-Person Pose Estimation},
+    author={Yuanhao Cai and Zhicheng Wang and Zhengxiong Luo and Binyi Yin and Angang Du and Haoqian Wang and Xinyu Zhou and Erjin Zhou and Xiangyu Zhang and Jian Sun},
+    year={2020},
+    eprint={2003.04030},
+    archivePrefix={arXiv},
+    primaryClass={cs.CV}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+In this paper, we propose a novel method called Residual Steps Network (RSN). RSN aggregates features with the same spatial size (Intra-level features) efficiently to obtain delicate local representations, which retain rich low-level spatial information and result in precise keypoint localization. Additionally, we observe the output features contribute differently to final performance. To tackle this problem, we propose an efficient attention mechanism - Pose Refine Machine (PRM) to make a trade-off between local and global representations in output features and further refine the keypoint locations. Our approach won the 1st place of COCO Keypoint Challenge 2019 and achieves state-of-the-art results on both COCO and MPII benchmarks, without using extra training data and pretrained model. Our single model achieves 78.6 on COCO test-dev, 93.0 on MPII test dataset. Ensembled models achieve 79.2 on COCO test-dev, 77.1 on COCO test-challenge dataset.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146522226-5041d16e-41cb-4d31-ae53-dbe21314a697.png">
+</div>
@@ -0,0 +1,30 @@
+# Improving Convolutional Networks with Self-Calibrated Convolutions
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_CVPR_2020/html/Liu_Improving_Convolutional_Networks_With_Self-Calibrated_Convolutions_CVPR_2020_paper.html">SCNet (CVPR'2020)</a></summary>
+
+```bibtex
+@inproceedings{liu2020improving,
+  title={Improving Convolutional Networks with Self-Calibrated Convolutions},
+  author={Liu, Jiang-Jiang and Hou, Qibin and Cheng, Ming-Ming and Wang, Changhu and Feng, Jiashi},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
+  pages={10096--10105},
+  year={2020}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Recent advances on CNNs are mostly devoted to designing more complex architectures to enhance their representation learning capacity. In this paper, we consider how to improve the basic convolutional feature transformation process of CNNs without tuning the model architectures. To this end, we present a novel self-calibrated convolutions that explicitly expand fields-of-view of each convolutional layers through internal communications and hence enrich the output features. In particular, unlike the standard convolutions that fuse spatial and channel-wise information using small kernels (e.g., 3x3), self-calibrated convolutions adaptively build long-range spatial and inter-channel dependencies around each spatial location through a novel self-calibration operation. Thus, it can help CNNs generate more discriminative representations by explicitly incorporating richer information. Our self-calibrated convolution design is simple and generic, and can be easily applied to augment standard convolutional layers without introducing extra parameters and complexity. Extensive experiments demonstrate that when applying self-calibrated convolutions into different backbones, our networks can significantly improve the baseline models in a variety of vision tasks, including image recognition, object detection, instance segmentation, and keypoint detection, with no need to change the network architectures. We hope this work could provide a promising way for future research in designing novel convolutional feature transformations for improving convolutional networks. Code is available on the project page.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146522623-fdc88996-1a8f-4b0a-bdee-fc284dfd7348.png">
+</div>
@@ -0,0 +1,30 @@
+# Squeeze-and-excitation networks
+
+<!-- [BACKBONE] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_cvpr_2018/html/Hu_Squeeze-and-Excitation_Networks_CVPR_2018_paper">SEResNet (CVPR'2018)</a></summary>
+
+```bibtex
+@inproceedings{hu2018squeeze,
+  title={Squeeze-and-excitation networks},
+  author={Hu, Jie and Shen, Li and Sun, Gang},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={7132--7141},
+  year={2018}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Convolutional neural networks are built upon the convolution operation, which extracts informative features by fusing spatial and channel-wise information together within local receptive fields. In order to boost the representational power of a network, several recent approaches have shown the benefit of enhancing spatial encoding. In this work, we focus on the channel relationship and propose a novel architectural unit, which we term the “Squeeze-and-Excitation” (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels. We demonstrate that by stacking these blocks together, we can construct SENet architectures that generalise extremely well across challenging datasets. Crucially, we find that SE blocks produce significant performance improvements for existing state-of-the-art deep architectures at minimal additional computational cost. SENets formed the foundation of our ILSVRC 2017 classification submission which won first place and significantly reduced the top-5 error to 2.251%, achieving a ∼25% relative improvement over the winning entry of 2016. Code and models are available at https: //github.com/hujie-frank/SENet.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146540423-a7e8ae12-3b3e-447e-848b-682c06c1126e.png">
+</div>
@@ -0,0 +1,30 @@
+# Shufflenet: An extremely efficient convolutional neural network for mobile devices
+
+<!-- [BACKBONE] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_cvpr_2018/html/Zhang_ShuffleNet_An_Extremely_CVPR_2018_paper.html">ShufflenetV1 (CVPR'2018)</a></summary>
+
+```bibtex
+@inproceedings{zhang2018shufflenet,
+  title={Shufflenet: An extremely efficient convolutional neural network for mobile devices},
+  author={Zhang, Xiangyu and Zhou, Xinyu and Lin, Mengxiao and Sun, Jian},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={6848--6856},
+  year={2018}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs). The new architecture utilizes two new operations, pointwise group convolution and channel shuffle, to greatly reduce computation cost while maintaining accuracy. Experiments on ImageNet classification and MS COCO object detection demonstrate the superior performance of ShuffleNet over other structures, e.g. lower top-1 error (absolute 7.8%) than recent MobileNet~cite{howard2017mobilenets} on ImageNet classification task, under the computation budget of 40 MFLOPs. On an ARM-based mobile device, ShuffleNet achieves $sim$13$ imes$ actual speedup over AlexNet while maintaining comparable accuracy.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146540601-7ed2ac24-aa7d-44b1-a7e0-be03bde0e098.png">
+</div>
@@ -0,0 +1,30 @@
+# Shufflenet v2: Practical guidelines for efficient cnn architecture design
+
+<!-- [BACKBONE] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_ECCV_2018/html/Ningning_Light-weight_CNN_Architecture_ECCV_2018_paper.html">ShufflenetV2 (ECCV'2018)</a></summary>
+
+```bibtex
+@inproceedings{ma2018shufflenet,
+  title={Shufflenet v2: Practical guidelines for efficient cnn architecture design},
+  author={Ma, Ningning and Zhang, Xiangyu and Zheng, Hai-Tao and Sun, Jian},
+  booktitle={Proceedings of the European conference on computer vision (ECCV)},
+  pages={116--131},
+  year={2018}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Current network architecture design is mostly guided by the indirect metric of computation complexity, i.e., FLOPs. However, the direct metric, such as speed, also depends on the other factors such as memory access cost and platform characterics. Taking these factors into account, this work proposes practical guidelines for efficient network de- sign. Accordingly, a new architecture called ShuffleNet V2 is presented. Comprehensive experiments verify that it is the state-of-the-art in both speed and accuracy.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146540752-993df527-7ec3-475c-ba12-3791bf8b3a0c.png">
+</div>
@@ -0,0 +1,29 @@
+# Very Deep Convolutional Networks for Large-Scale Image Recognition
+
+<!-- [BACKBONE] -->
+
+<details>
+<summary align="right"><a href="https://arxiv.org/abs/1409.1556">VGG (ICLR'2015)</a></summary>
+
+```bibtex
+@article{simonyan2014very,
+  title={Very deep convolutional networks for large-scale image recognition},
+  author={Simonyan, Karen and Zisserman, Andrew},
+  journal={arXiv preprint arXiv:1409.1556},
+  year={2014}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146540877-b0fc7823-efe2-4b5c-8168-3b3a9d7e93ac.png">
+</div>
@@ -0,0 +1,29 @@
+# ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://arxiv.org/abs/2105.10154">ViPNAS (CVPR'2021)</a></summary>
+
+```bibtex
+@article{xu2021vipnas,
+  title={ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search},
+  author={Xu, Lumin and Guan, Yingda and Jin, Sheng and Liu, Wentao and Qian, Chen and Luo, Ping and Ouyang, Wanli and Wang, Xiaogang},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  year={2021}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Human pose estimation has achieved significant progress in recent years. However, most of the recent methods focus on improving accuracy using complicated models and ignoring real-time efficiency. To achieve a better trade-off between accuracy and efficiency, we propose a novel neural architecture search (NAS) method, termed ViPNAS, to search networks in both spatial and temporal levels for fast online video pose estimation. In the spatial level, we carefully design the search space with five different dimensions including network depth, width, kernel size, group number, and attentions. In the temporal level, we search from a series of temporal feature fusions to optimize the total accuracy and speed across multiple video frames. To the best of our knowledge, we are the first to search for the temporal feature fusion and automatic computation allocation in videos. Extensive experiments demonstrate the effectiveness of our approach on the challenging COCO2017 and PoseTrack2018 datasets. Our discovered model family, S-ViPNAS and T-ViPNAS, achieve significantly higher inference speed (CPU real-time) without sacrificing the accuracy compared to the previous state-of-the-art methods.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146527709-b8e55e40-426c-4958-8a35-b8d259e69efa.png">
+</div>
@@ -0,0 +1,20 @@
+# 300 faces in-the-wild challenge: Database and results
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://www.sciencedirect.com/science/article/pii/S0262885616000147">300W (IMAVIS'2016)</a></summary>
+
+```bibtex
+@article{sagonas2016300,
+  title={300 faces in-the-wild challenge: Database and results},
+  author={Sagonas, Christos and Antonakos, Epameinondas and Tzimiropoulos, Georgios and Zafeiriou, Stefanos and Pantic, Maja},
+  journal={Image and vision computing},
+  volume={47},
+  pages={3--18},
+  year={2016},
+  publisher={Elsevier}
+}
+```
+
+</details>
@@ -0,0 +1,19 @@
+# Annotated facial landmarks in the wild: A large-scale, real-world database for facial landmark localization
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://ieeexplore.ieee.org/abstract/document/6130513/">AFLW (ICCVW'2011)</a></summary>
+
+```bibtex
+@inproceedings{koestinger2011annotated,
+  title={Annotated facial landmarks in the wild: A large-scale, real-world database for facial landmark localization},
+  author={Koestinger, Martin and Wohlhart, Paul and Roth, Peter M and Bischof, Horst},
+  booktitle={2011 IEEE international conference on computer vision workshops (ICCV workshops)},
+  pages={2144--2151},
+  year={2011},
+  organization={IEEE}
+}
+```
+
+</details>
@@ -0,0 +1,17 @@
+# Ai challenger: A large-scale dataset for going deeper in image understanding
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://arxiv.org/abs/1711.06475">AI Challenger (ArXiv'2017)</a></summary>
+
+```bibtex
+@article{wu2017ai,
+  title={Ai challenger: A large-scale dataset for going deeper in image understanding},
+  author={Wu, Jiahong and Zheng, He and Zhao, Bo and Li, Yixin and Yan, Baoming and Liang, Rui and Wang, Wenjia and Zhou, Shipei and Lin, Guosen and Fu, Yanwei and others},
+  journal={arXiv preprint arXiv:1711.06475},
+  year={2017}
+}
+```
+
+</details>
@@ -0,0 +1,18 @@
+# Cross-Domain Adaptation for Animal Pose Estimation
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_ICCV_2019/html/Cao_Cross-Domain_Adaptation_for_Animal_Pose_Estimation_ICCV_2019_paper.html">Animal-Pose (ICCV'2019)</a></summary>
+
+```bibtex
+@InProceedings{Cao_2019_ICCV,
+    author = {Cao, Jinkun and Tang, Hongyang and Fang, Hao-Shu and Shen, Xiaoyong and Lu, Cewu and Tai, Yu-Wing},
+    title = {Cross-Domain Adaptation for Animal Pose Estimation},
+    booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
+    month = {October},
+    year = {2019}
+}
+```
+
+</details>
@@ -0,0 +1,19 @@
+# AP-10K: A Benchmark for Animal Pose Estimation in the Wild
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://arxiv.org/abs/2108.12617">AP-10K (NeurIPS'2021)</a></summary>
+
+```bibtex
+@misc{yu2021ap10k,
+      title={AP-10K: A Benchmark for Animal Pose Estimation in the Wild},
+      author={Hang Yu and Yufei Xu and Jing Zhang and Wei Zhao and Ziyu Guan and Dacheng Tao},
+      year={2021},
+      eprint={2108.12617},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+```
+
+</details>
@@ -0,0 +1,18 @@
+# ATRW: A Benchmark for Amur Tiger Re-identification in the Wild
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://arxiv.org/abs/1906.05586">ATRW (ACM MM'2020)</a></summary>
+
+```bibtex
+@inproceedings{li2020atrw,
+  title={ATRW: A Benchmark for Amur Tiger Re-identification in the Wild},
+  author={Li, Shuyuan and Li, Jianguo and Tang, Hanlin and Qian, Rui and Lin, Weiyao},
+  booktitle={Proceedings of the 28th ACM International Conference on Multimedia},
+  pages={2590--2598},
+  year={2020}
+}
+```
+
+</details>
@@ -0,0 +1,19 @@
+# Microsoft coco: Common objects in context
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://link.springer.com/chapter/10.1007/978-3-319-10602-1_48">COCO (ECCV'2014)</a></summary>
+
+```bibtex
+@inproceedings{lin2014microsoft,
+  title={Microsoft coco: Common objects in context},
+  author={Lin, Tsung-Yi and Maire, Michael and Belongie, Serge and Hays, James and Perona, Pietro and Ramanan, Deva and Doll{\'a}r, Piotr and Zitnick, C Lawrence},
+  booktitle={European conference on computer vision},
+  pages={740--755},
+  year={2014},
+  organization={Springer}
+}
+```
+
+</details>
@@ -0,0 +1,17 @@
+# Whole-Body Human Pose Estimation in the Wild
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://link.springer.com/chapter/10.1007/978-3-030-58545-7_12">COCO-WholeBody (ECCV'2020)</a></summary>
+
+```bibtex
+@inproceedings{jin2020whole,
+  title={Whole-Body Human Pose Estimation in the Wild},
+  author={Jin, Sheng and Xu, Lumin and Xu, Jin and Wang, Can and Liu, Wentao and Qian, Chen and Ouyang, Wanli and Luo, Ping},
+  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
+  year={2020}
+}
+```
+
+</details>
@@ -0,0 +1,17 @@
+# Whole-Body Human Pose Estimation in the Wild
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://link.springer.com/chapter/10.1007/978-3-030-58545-7_12">COCO-WholeBody-Face (ECCV'2020)</a></summary>
+
+```bibtex
+@inproceedings{jin2020whole,
+  title={Whole-Body Human Pose Estimation in the Wild},
+  author={Jin, Sheng and Xu, Lumin and Xu, Jin and Wang, Can and Liu, Wentao and Qian, Chen and Ouyang, Wanli and Luo, Ping},
+  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
+  year={2020}
+}
+```
+
+</details>
@@ -0,0 +1,17 @@
+# Whole-Body Human Pose Estimation in the Wild
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://link.springer.com/chapter/10.1007/978-3-030-58545-7_12">COCO-WholeBody-Hand (ECCV'2020)</a></summary>
+
+```bibtex
+@inproceedings{jin2020whole,
+  title={Whole-Body Human Pose Estimation in the Wild},
+  author={Jin, Sheng and Xu, Lumin and Xu, Jin and Wang, Can and Liu, Wentao and Qian, Chen and Ouyang, Wanli and Luo, Ping},
+  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
+  year={2020}
+}
+```
+
+</details>
@@ -0,0 +1,18 @@
+# Robust face landmark estimation under occlusion
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_iccv_2013/html/Burgos-Artizzu_Robust_Face_Landmark_2013_ICCV_paper.html">COFW (ICCV'2013)</a></summary>
+
+```bibtex
+@inproceedings{burgos2013robust,
+  title={Robust face landmark estimation under occlusion},
+  author={Burgos-Artizzu, Xavier P and Perona, Pietro and Doll{\'a}r, Piotr},
+  booktitle={Proceedings of the IEEE international conference on computer vision},
+  pages={1513--1520},
+  year={2013}
+}
+```
+
+</details>
@@ -0,0 +1,17 @@
+# CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_CVPR_2019/html/Li_CrowdPose_Efficient_Crowded_Scenes_Pose_Estimation_and_a_New_Benchmark_CVPR_2019_paper.html">CrowdPose (CVPR'2019)</a></summary>
+
+```bibtex
+@article{li2018crowdpose,
+  title={CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark},
+  author={Li, Jiefeng and Wang, Can and Zhu, Hao and Mao, Yihuan and Fang, Hao-Shu and Lu, Cewu},
+  journal={arXiv preprint arXiv:1812.00324},
+  year={2018}
+}
+```
+
+</details>
@@ -0,0 +1,35 @@
+# DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_cvpr_2016/html/Liu_DeepFashion_Powering_Robust_CVPR_2016_paper.html">DeepFashion (CVPR'2016)</a></summary>
+
+```bibtex
+@inproceedings{liuLQWTcvpr16DeepFashion,
+ author = {Liu, Ziwei and Luo, Ping and Qiu, Shi and Wang, Xiaogang and Tang, Xiaoou},
+ title = {DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations},
+ booktitle = {Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
+ month = {June},
+ year = {2016}
+}
+```
+
+</details>
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://link.springer.com/chapter/10.1007/978-3-319-46475-6_15">DeepFashion (ECCV'2016)</a></summary>
+
+```bibtex
+@inproceedings{liuYLWTeccv16FashionLandmark,
+ author = {Liu, Ziwei and Yan, Sijie and Luo, Ping and Wang, Xiaogang and Tang, Xiaoou},
+ title = {Fashion Landmark Detection in the Wild},
+ booktitle = {European Conference on Computer Vision (ECCV)},
+ month = {October},
+ year = {2016}
+ }
+```
+
+</details>
@@ -0,0 +1,21 @@
+# Fast animal pose estimation using deep neural networks
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://www.nature.com/articles/s41592-018-0234-5">Vinegar Fly (Nature Methods'2019)</a></summary>
+
+```bibtex
+@article{pereira2019fast,
+  title={Fast animal pose estimation using deep neural networks},
+  author={Pereira, Talmo D and Aldarondo, Diego E and Willmore, Lindsay and Kislin, Mikhail and Wang, Samuel S-H and Murthy, Mala and Shaevitz, Joshua W},
+  journal={Nature methods},
+  volume={16},
+  number={1},
+  pages={117--125},
+  year={2019},
+  publisher={Nature Publishing Group}
+}
+```
+
+</details>
@@ -0,0 +1,18 @@
+# Freihand: A dataset for markerless capture of hand pose and shape from single rgb images
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_ICCV_2019/html/Zimmermann_FreiHAND_A_Dataset_for_Markerless_Capture_of_Hand_Pose_and_ICCV_2019_paper.html">FreiHand (ICCV'2019)</a></summary>
+
+```bibtex
+@inproceedings{zimmermann2019freihand,
+  title={Freihand: A dataset for markerless capture of hand pose and shape from single rgb images},
+  author={Zimmermann, Christian and Ceylan, Duygu and Yang, Jimei and Russell, Bryan and Argus, Max and Brox, Thomas},
+  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
+  pages={813--822},
+  year={2019}
+}
+```
+
+</details>
@@ -0,0 +1,22 @@
+# Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://ieeexplore.ieee.org/abstract/document/6682899/">Human3.6M (TPAMI'2014)</a></summary>
+
+```bibtex
+@article{h36m_pami,
+  author = {Ionescu, Catalin and Papava, Dragos and Olaru, Vlad and Sminchisescu,  Cristian},
+  title = {Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments},
+  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
+  publisher = {IEEE Computer Society},
+  volume = {36},
+  number = {7},
+  pages = {1325-1339},
+  month = {jul},
+  year = {2014}
+}
+```
+
+</details>
@@ -0,0 +1,17 @@
+# PaStaNet: Toward Human Activity Knowledge Engine
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://arxiv.org/abs/2004.00945">Halpe (CVPR'2020)</a></summary>
+
+```bibtex
+@inproceedings{li2020pastanet,
+  title={PaStaNet: Toward Human Activity Knowledge Engine},
+  author={Li, Yong-Lu and Xu, Liang and Liu, Xinpeng and Huang, Xijie and Xu, Yue and Wang, Shiyi and Fang, Hao-Shu and Ma, Ze and Chen, Mingyang and Lu, Cewu},
+  booktitle={CVPR},
+  year={2020}
+}
+```
+
+</details>
@@ -0,0 +1,18 @@
+# Pretraining boosts out-of-domain robustness for pose estimation
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://openaccess.thecvf.com/content/WACV2021/html/Mathis_Pretraining_Boosts_Out-of-Domain_Robustness_for_Pose_Estimation_WACV_2021_paper.html">Horse-10 (WACV'2021)</a></summary>
+
+```bibtex
+@inproceedings{mathis2021pretraining,
+  title={Pretraining boosts out-of-domain robustness for pose estimation},
+  author={Mathis, Alexander and Biasi, Thomas and Schneider, Steffen and Yuksekgonul, Mert and Rogers, Byron and Bethge, Matthias and Mathis, Mackenzie W},
+  booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
+  pages={1859--1868},
+  year={2021}
+}
+```
+
+</details>
@@ -0,0 +1,18 @@
+# InterHand2.6M: A dataset and baseline for 3D interacting hand pose estimation from a single RGB image
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://link.springer.com/content/pdf/10.1007/978-3-030-58565-5_33.pdf">InterHand2.6M (ECCV'2020)</a></summary>
+
+```bibtex
+@article{moon2020interhand2,
+  title={InterHand2.6M: A dataset and baseline for 3D interacting hand pose estimation from a single RGB image},
+  author={Moon, Gyeongsik and Yu, Shoou-I and Wen, He and Shiratori, Takaaki and Lee, Kyoung Mu},
+  journal={arXiv preprint arXiv:2008.09309},
+  year={2020},
+  publisher={Springer}
+}
+```
+
+</details>
@@ -0,0 +1,19 @@
+# Towards understanding action recognition
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://www.cv-foundation.org/openaccess/content_iccv_2013/html/Jhuang_Towards_Understanding_Action_2013_ICCV_paper.html">JHMDB (ICCV'2013)</a></summary>
+
+```bibtex
+@inproceedings{Jhuang:ICCV:2013,
+  title = {Towards understanding action recognition},
+  author = {H. Jhuang and J. Gall and S. Zuffi and C. Schmid and M. J. Black},
+  booktitle = {International Conf. on Computer Vision (ICCV)},
+  month = Dec,
+  pages = {3192-3199},
+  year = {2013}
+}
+```
+
+</details>
@@ -0,0 +1,20 @@
+# DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://elifesciences.org/articles/47994">Desert Locust (Elife'2019)</a></summary>
+
+```bibtex
+@article{graving2019deepposekit,
+  title={DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning},
+  author={Graving, Jacob M and Chae, Daniel and Naik, Hemal and Li, Liang and Koger, Benjamin and Costelloe, Blair R and Couzin, Iain D},
+  journal={Elife},
+  volume={8},
+  pages={e47994},
+  year={2019},
+  publisher={eLife Sciences Publications Limited}
+}
+```
+
+</details>
@@ -0,0 +1,18 @@
+# MacaquePose: A novel ‘in the wild’macaque monkey pose dataset for markerless motion capture
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://www.ncbi.nlm.nih.gov/pmc/articles/pmc7874091/">MacaquePose (bioRxiv'2020)</a></summary>
+
+```bibtex
+@article{labuguen2020macaquepose,
+  title={MacaquePose: A novel ‘in the wild’macaque monkey pose dataset for markerless motion capture},
+  author={Labuguen, Rollyn and Matsumoto, Jumpei and Negrete, Salvador and Nishimaru, Hiroshi and Nishijo, Hisao and Takada, Masahiko and Go, Yasuhiro and Inoue, Ken-ichi and Shibata, Tomohiro},
+  journal={bioRxiv},
+  year={2020},
+  publisher={Cold Spring Harbor Laboratory}
+}
+```
+
+</details>
@@ -0,0 +1,18 @@
+# Understanding humans in crowded scenes: Deep nested adversarial learning and a new benchmark for multi-human parsing
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://dl.acm.org/doi/abs/10.1145/3240508.3240509">MHP (ACM MM'2018)</a></summary>
+
+```bibtex
+@inproceedings{zhao2018understanding,
+  title={Understanding humans in crowded scenes: Deep nested adversarial learning and a new benchmark for multi-human parsing},
+  author={Zhao, Jian and Li, Jianshu and Cheng, Yu and Sim, Terence and Yan, Shuicheng and Feng, Jiashi},
+  booktitle={Proceedings of the 26th ACM international conference on Multimedia},
+  pages={792--800},
+  year={2018}
+}
+```
+
+</details>
@@ -0,0 +1,20 @@
+# Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://ieeexplore.ieee.org/abstract/document/8374605/">MPI-INF-3DHP (3DV'2017)</a></summary>
+
+```bibtex
+@inproceedings{mono-3dhp2017,
+  author = {Mehta, Dushyant and Rhodin, Helge and Casas, Dan and Fua, Pascal and Sotnychenko, Oleksandr and Xu, Weipeng and Theobalt, Christian},
+  title = {Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision},
+  booktitle = {3D Vision (3DV), 2017 Fifth International Conference on},
+  url = {http://gvv.mpi-inf.mpg.de/3dhp_dataset},
+  year = {2017},
+  organization={IEEE},
+  doi={10.1109/3dv.2017.00064},
+}
+```
+
+</details>
@@ -0,0 +1,18 @@
+# 2D Human Pose Estimation: New Benchmark and State of the Art Analysis
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_cvpr_2014/html/Andriluka_2D_Human_Pose_2014_CVPR_paper.html">MPII (CVPR'2014)</a></summary>
+
+```bibtex
+@inproceedings{andriluka14cvpr,
+  author = {Mykhaylo Andriluka and Leonid Pishchulin and Peter Gehler and Schiele, Bernt},
+  title = {2D Human Pose Estimation: New Benchmark and State of the Art Analysis},
+  booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
+  year = {2014},
+  month = {June}
+}
+```
+
+</details>
@@ -0,0 +1,18 @@
+# TRB: A Novel Triplet Representation for Understanding 2D Human Body
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_ICCV_2019/html/Duan_TRB_A_Novel_Triplet_Representation_for_Understanding_2D_Human_Body_ICCV_2019_paper.html">MPII-TRB (ICCV'2019)</a></summary>
+
+```bibtex
+@inproceedings{duan2019trb,
+  title={TRB: A Novel Triplet Representation for Understanding 2D Human Body},
+  author={Duan, Haodong and Lin, Kwan-Yee and Jin, Sheng and Liu, Wentao and Qian, Chen and Ouyang, Wanli},
+  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
+  pages={9479--9488},
+  year={2019}
+}
+```
+
+</details>
@@ -0,0 +1,18 @@
+# Pose2seg: Detection free human instance segmentation
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_CVPR_2019/html/Zhang_Pose2Seg_Detection_Free_Human_Instance_Segmentation_CVPR_2019_paper.html">OCHuman (CVPR'2019)</a></summary>
+
+```bibtex
+@inproceedings{zhang2019pose2seg,
+  title={Pose2seg: Detection free human instance segmentation},
+  author={Zhang, Song-Hai and Li, Ruilong and Dong, Xin and Rosin, Paul and Cai, Zixi and Han, Xi and Yang, Dingcheng and Huang, Haozhi and Hu, Shi-Min},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={889--898},
+  year={2019}
+}
+```
+
+</details>
@@ -0,0 +1,21 @@
+# Mask-pose cascaded cnn for 2d hand pose estimation from single color image
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://ieeexplore.ieee.org/abstract/document/8529221/">OneHand10K (TCSVT'2019)</a></summary>
+
+```bibtex
+@article{wang2018mask,
+  title={Mask-pose cascaded cnn for 2d hand pose estimation from single color image},
+  author={Wang, Yangang and Peng, Cong and Liu, Yebin},
+  journal={IEEE Transactions on Circuits and Systems for Video Technology},
+  volume={29},
+  number={11},
+  pages={3258--3268},
+  year={2018},
+  publisher={IEEE}
+}
+```
+
+</details>
@@ -0,0 +1,18 @@
+# Hand keypoint detection in single images using multiview bootstrapping
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_cvpr_2017/html/Simon_Hand_Keypoint_Detection_CVPR_2017_paper.html">CMU Panoptic HandDB (CVPR'2017)</a></summary>
+
+```bibtex
+@inproceedings{simon2017hand,
+  title={Hand keypoint detection in single images using multiview bootstrapping},
+  author={Simon, Tomas and Joo, Hanbyul and Matthews, Iain and Sheikh, Yaser},
+  booktitle={Proceedings of the IEEE conference on Computer Vision and Pattern Recognition},
+  pages={1145--1153},
+  year={2017}
+}
+```
+
+</details>
@@ -0,0 +1,17 @@
+# Panoptic Studio: A Massively Multiview System for Social Motion Capture
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://openaccess.thecvf.com/content_iccv_2015/html/Joo_Panoptic_Studio_A_ICCV_2015_paper.html">CMU Panoptic (ICCV'2015)</a></summary>
+
+```bibtex
+@Article = {joo_iccv_2015,
+author = {Hanbyul Joo, Hao Liu, Lei Tan, Lin Gui, Bart Nabbe, Iain Matthews, Takeo Kanade, Shohei Nobuhara, and Yaser Sheikh},
+title = {Panoptic Studio: A Massively Multiview System for Social Motion Capture},
+booktitle = {ICCV},
+year = {2015}
+}
+```
+
+</details>
@@ -0,0 +1,18 @@
+# Posetrack: A benchmark for human pose estimation and tracking
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_cvpr_2018/html/Andriluka_PoseTrack_A_Benchmark_CVPR_2018_paper.html">PoseTrack18 (CVPR'2018)</a></summary>
+
+```bibtex
+@inproceedings{andriluka2018posetrack,
+  title={Posetrack: A benchmark for human pose estimation and tracking},
+  author={Andriluka, Mykhaylo and Iqbal, Umar and Insafutdinov, Eldar and Pishchulin, Leonid and Milan, Anton and Gall, Juergen and Schiele, Bernt},
+  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
+  pages={5167--5176},
+  year={2018}
+}
+```
+
+</details>
@@ -0,0 +1,19 @@
+# Learning to Estimate 3D Hand Pose from Single RGB Images
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://lmb.informatik.uni-freiburg.de/projects/hand3d/">RHD (ICCV'2017)</a></summary>
+
+```bibtex
+@TechReport{zb2017hand,
+  author={Christian Zimmermann and Thomas Brox},
+  title={Learning to Estimate 3D Hand Pose from Single RGB Images},
+  institution={arXiv:1705.01389},
+  year={2017},
+  note="https://arxiv.org/abs/1705.01389",
+  url="https://lmb.informatik.uni-freiburg.de/projects/hand3d/"
+}
+```
+
+</details>
@@ -0,0 +1,18 @@
+# Look at boundary: A boundary-aware face alignment algorithm
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_cvpr_2018/html/Wu_Look_at_Boundary_CVPR_2018_paper.html">WFLW (CVPR'2018)</a></summary>
+
+```bibtex
+@inproceedings{wu2018look,
+  title={Look at boundary: A boundary-aware face alignment algorithm},
+  author={Wu, Wayne and Qian, Chen and Yang, Shuo and Wang, Quan and Cai, Yici and Zhou, Qiang},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={2129--2138},
+  year={2018}
+}
+```
+
+</details>
@@ -0,0 +1,20 @@
+# DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning
+
+<!-- [DATASET] -->
+
+<details>
+<summary align="right"><a href="https://elifesciences.org/articles/47994">Grévy’s Zebra (Elife'2019)</a></summary>
+
+```bibtex
+@article{graving2019deepposekit,
+  title={DeepPoseKit, a software toolkit for fast and robust animal pose estimation using deep learning},
+  author={Graving, Jacob M and Chae, Daniel and Naik, Hemal and Li, Liang and Koger, Benjamin and Costelloe, Blair R and Couzin, Iain D},
+  journal={Elife},
+  volume={8},
+  pages={e47994},
+  year={2019},
+  publisher={eLife Sciences Publications Limited}
+}
+```
+
+</details>
@@ -0,0 +1,21 @@
+# Albumentations: fast and flexible image augmentations
+
+<!-- [OTHERS] -->
+
+<details>
+<summary align="right"><a href="https://www.mdpi.com/649002">Albumentations (Information'2020)</a></summary>
+
+```bibtex
+@article{buslaev2020albumentations,
+  title={Albumentations: fast and flexible image augmentations},
+  author={Buslaev, Alexander and Iglovikov, Vladimir I and Khvedchenya, Eugene and Parinov, Alex and Druzhinin, Mikhail and Kalinin, Alexandr A},
+  journal={Information},
+  volume={11},
+  number={2},
+  pages={125},
+  year={2020},
+  publisher={Multidisciplinary Digital Publishing Institute}
+}
+```
+
+</details>
@@ -0,0 +1,31 @@
+# Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://arxiv.org/pdf/1904.07399.pdf">AdaptiveWingloss (ICCV'2019)</a></summary>
+
+```bibtex
+@inproceedings{wang2019adaptive,
+  title={Adaptive wing loss for robust face alignment via heatmap regression},
+  author={Wang, Xinyao and Bo, Liefeng and Fuxin, Li},
+  booktitle={Proceedings of the IEEE/CVF international conference on computer vision},
+  pages={6971--6981},
+  year={2019}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Heatmap regression with a deep network has become one of the mainstream approaches to localize facial landmarks. However, the loss function for heatmap regression is rarely studied. In this paper, we analyze the ideal loss function properties for heatmap regression in face alignment problems. Then we propose a novel loss function, named Adaptive Wing loss, that is able to adapt its shape to different types of ground truth heatmap pixels. This adaptability penalizes loss more on foreground pixels while less on background pixels. To address the imbalance between foreground and background pixels, we also propose Weighted Loss Map, which assigns high weights on foreground and difficult background pixels to help training process focus more on pixels that are crucial to landmark localization. To further improve face alignment accuracy, we introduce boundary prediction and CoordConv with boundary coordinates. Extensive experiments on different benchmarks, including COFW, 300W and WFLW, show our approach outperforms the state-of-the-art by a significant margin on
+various evaluation metrics. Besides, the Adaptive Wing loss also helps other heatmap regression tasks.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/148007960-a06a34d8-8090-49e1-80db-6bbe4a7e7e8d.png">
+</div>
@@ -0,0 +1,30 @@
+# Distribution-aware coordinate representation for human pose estimation
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_CVPR_2020/html/Zhang_Distribution-Aware_Coordinate_Representation_for_Human_Pose_Estimation_CVPR_2020_paper.html">DarkPose (CVPR'2020)</a></summary>
+
+```bibtex
+@inproceedings{zhang2020distribution,
+  title={Distribution-aware coordinate representation for human pose estimation},
+  author={Zhang, Feng and Zhu, Xiatian and Dai, Hanbin and Ye, Mao and Zhu, Ce},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
+  pages={7093--7102},
+  year={2020}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+While being the de facto standard coordinate representation for human pose estimation, heatmap has not been investigated in-depth. This work fills this gap. For the first time, we find that the process of decoding the predicted heatmaps into the final joint coordinates in the original image space is surprisingly significant for the performance. We further probe the design limitations of the standard coordinate decoding method, and propose a more principled distributionaware decoding method. Also, we improve the standard coordinate encoding process (i.e. transforming ground-truth coordinates to heatmaps) by generating unbiased/accurate heatmaps. Taking the two together, we formulate a novel Distribution-Aware coordinate Representation of Keypoints (DARK) method. Serving as a model-agnostic plug-in, DARK brings about significant performance boost to existing human pose estimation models. Extensive experiments show that DARK yields the best results on two common benchmarks, MPII and COCO. Besides, DARK achieves the 2nd place entry in the ICCV 2019 COCO Keypoints Challenge. The code is available online.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146514732-1d53614b-e5b7-4a1c-a39f-6fc726217d81.png">
+</div>
@@ -0,0 +1,17 @@
+# Mixed Precision Training
+
+<!-- [OTHERS] -->
+
+<details>
+<summary align="right"><a href="https://arxiv.org/abs/1710.03740">FP16 (ArXiv'2017)</a></summary>
+
+```bibtex
+@article{micikevicius2017mixed,
+  title={Mixed precision training},
+  author={Micikevicius, Paulius and Narang, Sharan and Alben, Jonah and Diamos, Gregory and Elsen, Erich and Garcia, David and Ginsburg, Boris and Houston, Michael and Kuchaiev, Oleksii and Venkatesh, Ganesh and others},
+  journal={arXiv preprint arXiv:1710.03740},
+  year={2017}
+}
+```
+
+</details>
@@ -0,0 +1,30 @@
+# Structure-Coherent Deep Feature Learning for Robust Face Alignment
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="https://ieeexplore.ieee.org/document/9442331/">SoftWingloss (TIP'2021)</a></summary>
+
+```bibtex
+@article{lin2021structure,
+  title={Structure-Coherent Deep Feature Learning for Robust Face Alignment},
+  author={Lin, Chunze and Zhu, Beier and Wang, Quan and Liao, Renjie and Qian, Chen and Lu, Jiwen and Zhou, Jie},
+  journal={IEEE Transactions on Image Processing},
+  year={2021},
+  publisher={IEEE}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+In this paper, we propose a structure-coherent deep feature learning method for face alignment. Unlike most existing face alignment methods which overlook the facial structure cues, we explicitly exploit the relation among facial landmarks to make the detector robust to hard cases such as occlusion and large pose. Specifically, we leverage a landmark-graph relational network to enforce the structural relationships among landmarks. We consider the facial landmarks as structural graph nodes and carefully design the neighborhood to passing features among the most related nodes. Our method dynamically adapts the weights of node neighborhood to eliminate distracted information from noisy nodes, such as occluded landmark point. Moreover, different from most previous works which only tend to penalize the landmarks absolute position during the training, we propose a relative location loss to enhance the information of relative location of landmarks. This relative location supervision further regularizes the facial structure. Our approach considers the interactions among facial landmarks and can be easily implemented on top of any convolutional backbone to boost the performance. Extensive experiments on three popular benchmarks, including WFLW, COFW and 300W, demonstrate the effectiveness of the proposed method. In particular, due to explicit structure modeling, our approach is especially robust to challenging cases resulting in impressive low failure rate on COFW and WFLW datasets.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/148036579-b128fb21-3a2d-4894-bb54-4223a4cdf856.png">
+</div>
@@ -0,0 +1,30 @@
+# The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_CVPR_2020/html/Huang_The_Devil_Is_in_the_Details_Delving_Into_Unbiased_Data_CVPR_2020_paper.html">UDP (CVPR'2020)</a></summary>
+
+```bibtex
+@InProceedings{Huang_2020_CVPR,
+  author = {Huang, Junjie and Zhu, Zheng and Guo, Feng and Huang, Guan},
+  title = {The Devil Is in the Details: Delving Into Unbiased Data Processing for Human Pose Estimation},
+  booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+  month = {June},
+  year = {2020}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+Recently, the leading performance of human pose estimation is dominated by top-down methods. Being a fundamental component in training and inference, data processing has not been systematically considered in pose estimation community, to the best of our knowledge. In this paper, we focus on this problem and find that the devil of top-down pose estimator is in the biased data processing. Specifically, by investigating the standard data processing in state-of-the-art approaches mainly including data transformation and encoding-decoding, we find that the results obtained by common flipping strategy are unaligned with the original ones in inference. Moreover, there is statistical error in standard encoding-decoding during both training and inference. Two problems couple together and significantly degrade the pose estimation performance. Based on quantitative analyses, we then formulate a principled way to tackle this dilemma. Data is processed in continuous space based on unit length (the intervals between pixels) instead of in discrete space with pixel, and a combined classification and regression approach is adopted to perform encoding-decoding. The Unbiased Data Processing (UDP) for human pose estimation can be achieved by combining the two together. UDP not only boosts the performance of existing methods by a large margin but also plays a important role in result reproducing and future exploration. As a model-agnostic approach, UDP promotes SimpleBaseline-ResNet50-256x192 by 1.5 AP (70.2 to 71.7) and HRNet-W32-256x192 by 1.7 AP (73.5 to 75.2) on COCO test-dev set. The HRNet-W48-384x288 equipped with UDP achieves 76.5 AP and sets a new state-of-the-art for human pose estimation. The source code is publicly available for further research.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146524686-ddfe1356-77bd-46a0-a6cd-7ff418f65675.png">
+</div>
@@ -0,0 +1,31 @@
+# Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks
+
+<!-- [ALGORITHM] -->
+
+<details>
+<summary align="right"><a href="http://openaccess.thecvf.com/content_cvpr_2018/html/Feng_Wing_Loss_for_CVPR_2018_paper.html">Wingloss (CVPR'2018)</a></summary>
+
+```bibtex
+@inproceedings{feng2018wing,
+  title={Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks},
+  author={Feng, Zhen-Hua and Kittler, Josef and Awais, Muhammad and Huber, Patrik and Wu, Xiao-Jun},
+  booktitle={Computer Vision and Pattern Recognition (CVPR), 2018 IEEE Conference on},
+  year={2018},
+  pages ={2235-2245},
+  organization={IEEE}
+}
+```
+
+</details>
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+We present a new loss function, namely Wing loss, for robust facial landmark localisation with Convolutional Neural Networks (CNNs). We first compare and analyse different loss functions including L2, L1 and smooth L1. The analysis of these loss functions suggests that, for the training of a CNN-based localisation model, more attention should be paid to small and medium range errors. To this end, we design a piece-wise loss function. The new loss amplifies the impact of errors from the interval (-w, w) by switching from L1 loss to a modified logarithm function. To address the problem of under-representation of samples with large out-of-plane head rotations in the training set, we propose a simple but effective boosting strategy, referred to as pose-based data balancing. In particular, we deal with the data imbalance problem by duplicating the minority training samples and perturbing them by injecting random image rotation, bounding box translation and other data augmentation approaches. Last, the proposed approach is extended to create a two-stage framework for robust facial landmark localisation. The experimental results obtained on AFLW and 300W demonstrate the merits of the Wing loss function, and prove the superiority of the proposed method over the state-of-the-art approaches.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/15977946/146528473-f3228f69-b60e-4807-9c4b-b45997fbc530.png">
+</div>