{"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/end-to-end-temporal-action-detection-with-1b","title":"End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames","arxiv_id":"2311.17241","date":"2023-11-28","proceeding":"CVPR 2024 1","authors":["Shuming Liu","Chen-Lin Zhang","Chen Zhao","Bernard Ghanem"],"abstract":"Recently, temporal action detection (TAD) has seen significant performance improvement with end-to-end training. However, due to the memory bottleneck, only models with limited scales and limited data volumes can afford end-to-end training, which inevitably restricts TAD performance. In this paper, we reduce the memory consumption for end-to-end training, and manage to scale up the TAD backbone to 1 billion parameters and the input video to 1,536 frames, leading to significant detection performance. The key to our approach lies in our proposed temporal-informative adapter (TIA), which is a novel lightweight module that reduces training memory. Using TIA, we free the humongous backbone from learning to adapt to the TAD task by only updating the parameters in TIA. TIA also leads to better TAD representation by temporally aggregating context from adjacent frames throughout the backbone. We evaluate our model across four representative datasets. Owing to our efficient design, we are able to train end-to-end on VideoMAEv2-giant and achieve 75.4% mAP on THUMOS14, being the first end-to-end model to outperform the best feature-based methods. Code is available at https://github.com/sming256/AdaTAD.","url_abs":"https://arxiv.org/abs/2311.17241v2","url_pdf":"https://arxiv.org/pdf/2311.17241v2.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":"end-to-end-temporal-action-detection-with-1b","repo_url":"https://github.com/sming256/OpenTAD","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"end-to-end-temporal-action-detection-with-1b","repo_url":"https://github.com/sming256/AdaTAD","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"action-detection","task_name":"Action Detection"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/temporal-action-localization-on-activitynet","task":"Temporal Action Localization","dataset":"ActivityNet-1.3","model":"AdaTAD (VideoMAEv2-giant)","rank_in_archive_order":4,"of":33,"metrics":{"mAP":"41.93","mAP IOU@0.5":"61.72","mAP IOU@0.75":"43.35","mAP IOU@0.95":"10.85"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-action-localization-on-epic-kitchens","task":"Temporal Action Localization","dataset":"EPIC-KITCHENS-100","model":"AdaTAD (verb, VideoMAE-L)","rank_in_archive_order":1,"of":6,"metrics":{"Avg mAP (0.1-0.5)":"29.3","mAP IOU@0.1":"33.1","mAP IOU@0.2":"32.2","mAP IOU@0.3":"30.4","mAP IOU@0.4":"27.5","mAP IOU@0.5":"23.1"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-action-localization-on-thumos14","task":"Temporal Action Localization","dataset":"THUMOS’14","model":"AdaTAD (VideoMAEv2-giant)","rank_in_archive_order":1,"of":42,"metrics":{"Avg mAP (0.3:0.7)":"76.9","mAP IOU@0.3":"89.7","mAP IOU@0.4":"86.7","mAP IOU@0.5":"80.9","mAP IOU@0.6":"71.0","mAP IOU@0.7":"56.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.17241","atlas_url":"https://app.syntology.ai/?focus=2311.17241","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":"2311.17241"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2311.17241\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2311.17241"},"call":"get_concepts_for_paper(arxiv_id=\"2311.17241\")"}],"by_repo":[{"repo":"sming256/OpenTAD","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sming256/AdaTAD","kind":"named_in_paper","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":"fe45ceca774fd2e7115864eb6ef76c7094cd9e0db1728a4c88bad4e442dff976","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}