2018/08/05 by Lipeng Ke, Ke, Lipeng, Ming-Ching Chang +6
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Hand Gesture Recognition Systems #Human Pose and Action Recognition #Video Surveillance and Tracking Methods #cs.CV
paper · pdf · doi:10.48550/arxiv.1808.01623
Accepted by ICIP2018. arXiv admin note: text overlap with arXiv:1803.09894
arxiv created 2018/08/05 · openalex publication_date 2018/08/05 · arxiv updated 2018/08/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Human pose estimation is an important topic in computer vision with many applications including gesture and activity recognition. However, pose estimation from image is challenging due to appearance variations, occlusions, clutter background, and complex activities. To alleviate these problems, we develop a robust pose estimation method based on the recent deep conv-deconv modules with two improvements: (1) multi-scale supervision of body keypoints, and (2) a global regression to improve structural consistency of keypoints. We refine keypoint detection heatmaps using layer-wise multi-scale supervision to better capture local contexts. Pose inference via keypoint association is optimized globally using a regression network at the end. Our method can effectively disambiguate keypoint matches in close proximity including the mismatch of left-right body parts, and better infer occluded parts. Experimental results show that our method achieves competitive performance among state-of-the-art methods on the MPII and FLIC datasets.