{"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/object-detection-in-videos-with-tubelet","title":"Object Detection in Videos with Tubelet Proposal Networks","arxiv_id":"1702.06355","date":"2017-02-21","proceeding":"CVPR 2017 7","authors":["Kai Kang","Hongsheng Li","Tong Xiao","Wanli Ouyang","Junjie Yan","Xihui Liu","Xiaogang Wang"],"abstract":"Object detection in videos has drawn increasing attention recently with the\nintroduction of the large-scale ImageNet VID dataset. Different from object\ndetection in static images, temporal information in videos is vital for object\ndetection. To fully utilize temporal information, state-of-the-art methods are\nbased on spatiotemporal tubelets, which are essentially sequences of associated\nbounding boxes across time. However, the existing methods have major\nlimitations in generating tubelets in terms of quality and efficiency.\nMotion-based methods are able to obtain dense tubelets efficiently, but the\nlengths are generally only several frames, which is not optimal for\nincorporating long-term temporal information. Appearance-based methods, usually\ninvolving generic object tracking, could generate long tubelets, but are\nusually computationally expensive. In this work, we propose a framework for\nobject detection in videos, which consists of a novel tubelet proposal network\nto efficiently generate spatiotemporal proposals, and a Long Short-term Memory\n(LSTM) network that incorporates temporal information from tubelet proposals\nfor achieving high object detection accuracy in videos. Experiments on the\nlarge-scale ImageNet VID dataset demonstrate the effectiveness of the proposed\nframework for object detection in videos.","url_abs":"http://arxiv.org/abs/1702.06355v2","url_pdf":"http://arxiv.org/pdf/1702.06355v2.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":"object-detection-in-videos-with-tubelet","repo_url":"https://github.com/myfavouritekk/tpn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1702.06355","atlas_url":"https://app.syntology.ai/?focus=1702.06355","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.06355"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/myfavouritekk/tpn","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"b3695ebe0c382b05","entry":"bbox_transform_inv","repo":"myfavouritekk/tpn","repo_kind":"listed","path":"src/tpn/bidirectional_recurrent_extract_features.py","file_url":"https://github.com/myfavouritekk/tpn/blob/HEAD/src/tpn/bidirectional_recurrent_extract_features.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b3695ebe0c382b05"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}