{"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/viewpoints-and-keypoints","title":"Viewpoints and Keypoints","arxiv_id":"1411.6067","date":"2014-11-22","proceeding":"CVPR 2015 6","authors":["Shubham Tulsiani","Jitendra Malik"],"abstract":"We characterize the problem of pose estimation for rigid objects in terms of\ndetermining viewpoint to explain coarse pose and keypoint prediction to capture\nthe finer details. We address both these tasks in two different settings - the\nconstrained setting with known bounding boxes and the more challenging\ndetection setting where the aim is to simultaneously detect and correctly\nestimate pose of objects. We present Convolutional Neural Network based\narchitectures for these and demonstrate that leveraging viewpoint estimates can\nsubstantially improve local appearance based keypoint predictions. In addition\nto achieving significant improvements over state-of-the-art in the above tasks,\nwe analyze the error modes and effect of object characteristics on performance\nto guide future efforts towards this goal.","url_abs":"http://arxiv.org/abs/1411.6067v2","url_pdf":"http://arxiv.org/pdf/1411.6067v2.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":"keypoint-detection","task_name":"Keypoint Detection"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/keypoint-detection-on-pascal3d","task":"Keypoint Detection","dataset":"Pascal3D+","model":"CNN + viewpoint estimates","rank_in_archive_order":3,"of":4,"metrics":{"Mean PCK":"68.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1411.6067","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}