{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/view-invariant-probabilistic-embedding-for","title":"View-Invariant Probabilistic Embedding for Human Pose","arxiv_id":"1912.01001","date":"2019-12-02","proceeding":"ECCV 2020 8","authors":["Jennifer J. Sun","Jiaping Zhao","Liang-Chieh Chen","Florian Schroff","Hartwig Adam","Ting Liu"],"abstract":"Depictions of similar human body configurations can vary with changing viewpoints. Using only 2D information, we would like to enable vision algorithms to recognize similarity in human body poses across multiple views. This ability is useful for analyzing body movements and human behaviors in images and videos. In this paper, we propose an approach for learning a compact view-invariant embedding space from 2D joint keypoints alone, without explicitly predicting 3D poses. Since 2D poses are projected from 3D space, they have an inherent ambiguity, which is difficult to represent through a deterministic mapping. Hence, we use probabilistic embeddings to model this input uncertainty. Experimental results show that our embedding model achieves higher accuracy when retrieving similar poses across different camera views, in comparison with 2D-to-3D pose lifting models. We also demonstrate the effectiveness of applying our embeddings to view-invariant action recognition and video alignment. Our code is available at https://github.com/google-research/google-research/tree/master/poem.","url_abs":"https://arxiv.org/abs/1912.01001v4","url_pdf":"https://arxiv.org/pdf/1912.01001v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"view-invariant-probabilistic-embedding-for","repo_url":"https://github.com/google-research/google-research","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"view-invariant-probabilistic-embedding-for","repo_url":"https://github.com/google-research/google-research/tree/master/poem","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"pose-retrieval","task_name":"Pose Retrieval"},{"task_slug":"skeleton-based-action-recognition","task_name":"Skeleton Based Action Recognition"},{"task_slug":"video-alignment","task_name":"Video Alignment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/pose-retrieval-on-human3-6m","task":"Pose Retrieval","dataset":"Human3.6M","model":"Pr-VIPE","rank_in_archive_order":1,"of":1,"metrics":{"Hit@1":"76.2","Hit@10":"95.6"},"uses_additional_data":false},{"leaderboard":"/sota/pose-retrieval-on-mpi-inf-3dhp","task":"Pose Retrieval","dataset":"MPI-INF-3DHP","model":"Pr-VIPE","rank_in_archive_order":1,"of":1,"metrics":{"Hit@1":"26.4","Hit@10":"58.6"},"uses_additional_data":false},{"leaderboard":"/sota/skeleton-based-action-recognition-on-upenn","task":"Skeleton Based Action Recognition","dataset":"UPenn Action","model":"Pr-VIPE","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy":"97.5"},"uses_additional_data":false},{"leaderboard":"/sota/video-alignment-on-upenn-action","task":"Video Alignment","dataset":"UPenn Action","model":"Pr-VIPE","rank_in_archive_order":2,"of":4,"metrics":{"Kendall's Tau":"0.7476"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1912.01001","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}