{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/tube-convolutional-neural-network-t-cnn-for","title":"Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos","arxiv_id":"1703.10664","date":"2017-03-30","proceeding":"ICCV 2017 10","authors":["Rui Hou","Chen Chen","Mubarak Shah"],"abstract":"Deep learning has been demonstrated to achieve excellent results for image\nclassification and object detection. However, the impact of deep learning on\nvideo analysis (e.g. action detection and recognition) has been limited due to\ncomplexity of video data and lack of annotations. Previous convolutional neural\nnetworks (CNN) based video action detection approaches usually consist of two\nmajor steps: frame-level action proposal detection and association of proposals\nacross frames. Also, these methods employ two-stream CNN framework to handle\nspatial and temporal feature separately. In this paper, we propose an\nend-to-end deep network called Tube Convolutional Neural Network (T-CNN) for\naction detection in videos. The proposed architecture is a unified network that\nis able to recognize and localize action based on 3D convolution features. A\nvideo is first divided into equal length clips and for each clip a set of tube\nproposals are generated next based on 3D Convolutional Network (ConvNet)\nfeatures. Finally, the tube proposals of different clips are linked together\nemploying network flow and spatio-temporal action detection is performed using\nthese linked video proposals. Extensive experiments on several video datasets\ndemonstrate the superior performance of T-CNN for classifying and localizing\nactions in both trimmed and untrimmed videos compared to state-of-the-arts.","url_abs":"http://arxiv.org/abs/1703.10664v3","url_pdf":"http://arxiv.org/pdf/1703.10664v3.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":"tube-convolutional-neural-network-t-cnn-for","repo_url":"https://github.com/cyberpunk317/Action_detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-detection","task_name":"Action Detection"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"video-action-detection","task_name":"Video Action Detection"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"3d-convolution","method_name":"3D Convolution"},{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-detection-on-j-hmdb","task":"Action Detection","dataset":"J-HMDB","model":"T-CNN","rank_in_archive_order":9,"of":18,"metrics":{"Frame-mAP 0.5":"61.3","Video-mAP 0.2":"78.4","Video-mAP 0.5":"76.9"},"uses_additional_data":false},{"leaderboard":"/sota/action-detection-on-ucf-sports","task":"Action Detection","dataset":"UCF Sports","model":"T-CNN","rank_in_archive_order":1,"of":7,"metrics":{"Frame-mAP 0.5":"86.7"},"uses_additional_data":false},{"leaderboard":"/sota/action-detection-on-ucf101-24","task":"Action Detection","dataset":"UCF101-24","model":"T-CNN","rank_in_archive_order":13,"of":19,"metrics":{"Frame-mAP 0.5":"41.37","Video-mAP 0.1":"51.3","Video-mAP 0.2":"47.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1703.10664","atlas_url":"https://app.syntology.ai/?focus=1703.10664","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1703.10664"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1703.10664\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1703.10664"},"call":"get_concepts_for_paper(arxiv_id=\"1703.10664\")"}],"by_repo":[{"repo":"cyberpunk317/Action_detection","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"954aa20778f868f9f7bf8cd4c650253263c14fa6e747eb86ea62e3b29de7b158","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}