{"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/15-keypoints-is-all-you-need","title":"15 Keypoints Is All You Need","arxiv_id":"1912.02323","date":"2019-12-05","proceeding":"CVPR 2020 6","authors":["Michael Snower","Asim Kadav","Farley Lai","Hans Peter Graf"],"abstract":"Pose tracking is an important problem that requires identifying unique human pose-instances and matching them temporally across different frames of a video. However, existing pose tracking methods are unable to accurately model temporal relationships and require significant computation, often computing the tracks offline. We present an efficient Multi-person Pose Tracking method, KeyTrack, that only relies on keypoint information without using any RGB or optical flow information to track human keypoints in real-time. Keypoints are tracked using our Pose Entailment method, in which, first, a pair of pose estimates is sampled from different frames in a video and tokenized. Then, a Transformer-based network makes a binary classification as to whether one pose temporally follows another. Furthermore, we improve our top-down pose estimation method with a novel, parameter-free, keypoint refinement technique that improves the keypoint estimates used during the Pose Entailment step. We achieve state-of-the-art results on the PoseTrack'17 and the PoseTrack'18 benchmarks while using only a fraction of the computation required by most other methods for computing the tracking information.","url_abs":"https://arxiv.org/abs/1912.02323v2","url_pdf":"https://arxiv.org/pdf/1912.02323v2.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":[],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"pose-tracking","task_name":"Pose Tracking"}],"methods":[{"method_slug":null,"method_name":null}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/pose-tracking-on-posetrack2017","task":"Pose Tracking","dataset":"PoseTrack2017","model":"KeyTrack","rank_in_archive_order":2,"of":10,"metrics":{"MOTA":"61.15","mAP":"74.04"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1912.02323","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}