{"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/objects-do-not-disappear-video-object","title":"Objects do not disappear: Video object detection by single-frame object location anticipation","arxiv_id":"2308.04770","date":"2023-08-09","proceeding":"ICCV 2023 1","authors":["Xin Liu","Fatemeh Karimi Nejadasl","Jan C. van Gemert","Olaf Booij","Silvia L. Pintea"],"abstract":"Objects in videos are typically characterized by continuous smooth motion. We exploit continuous smooth motion in three ways. 1) Improved accuracy by using object motion as an additional source of supervision, which we obtain by anticipating object locations from a static keyframe. 2) Improved efficiency by only doing the expensive feature computations on a small subset of all frames. Because neighboring video frames are often redundant, we only compute features for a single static keyframe and predict object locations in subsequent frames. 3) Reduced annotation cost, where we only annotate the keyframe and use smooth pseudo-motion between keyframes. We demonstrate computational efficiency, annotation efficiency, and improved mean average precision compared to the state-of-the-art on four datasets: ImageNet VID, EPIC KITCHENS-55, YouTube-BoundingBoxes, and Waymo Open dataset. Our source code is available at https://github.com/L-KID/Videoobject-detection-by-location-anticipation.","url_abs":"https://arxiv.org/abs/2308.04770v1","url_pdf":"https://arxiv.org/pdf/2308.04770v1.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":"objects-do-not-disappear-video-object","repo_url":"https://github.com/l-kid/video-object-detection-by-location-anticipation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"objects-do-not-disappear-video-object","repo_url":"https://github.com/Elstuhn/Video-object-detection-by-location-anticipation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"video-object-detection","task_name":"Video Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-object-detection-on-epic-kitchens-55","task":"Video Object Detection","dataset":"EPIC-KITCHENS-55","model":"Ours (Faster RCNN)","rank_in_archive_order":1,"of":1,"metrics":{"mAP@.5":"41.7"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-detection-on-imagenet-vid","task":"Video Object Detection","dataset":"ImageNet VID","model":"Ours (Def. DETR + SwinB)","rank_in_archive_order":3,"of":33,"metrics":{"MAP ":"91.3"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-detection-on-imagenet-vid","task":"Video Object Detection","dataset":"ImageNet VID","model":"Ours (Def. DETR + R101)","rank_in_archive_order":8,"of":33,"metrics":{"MAP ":"87.9"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-detection-on-imagenet-vid","task":"Video Object Detection","dataset":"ImageNet VID","model":"Ours (Faster RCNN + R101)","rank_in_archive_order":10,"of":33,"metrics":{"MAP ":"87.2"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-detection-on-waymo-open-dataset","task":"Video Object Detection","dataset":"Waymo Open Dataset","model":"","rank_in_archive_order":1,"of":1,"metrics":{"AP":"59.28"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-detection-on-yt-bb","task":"Video Object Detection","dataset":"YT-BB","model":"","rank_in_archive_order":1,"of":1,"metrics":{"mAP":"59.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.04770","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}