{"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/temporalmaxer-maximize-temporal-context-with","title":"TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization","arxiv_id":"2303.09055","date":"2023-03-16","proceeding":null,"authors":["Tuan N. Tang","Kwonyoung Kim","Kwanghoon Sohn"],"abstract":"Temporal Action Localization (TAL) is a challenging task in video understanding that aims to identify and localize actions within a video sequence. Recent studies have emphasized the importance of applying long-term temporal context modeling (TCM) blocks to the extracted video clip features such as employing complex self-attention mechanisms. In this paper, we present the simplest method ever to address this task and argue that the extracted video clip features are already informative to achieve outstanding performance without sophisticated architectures. To this end, we introduce TemporalMaxer, which minimizes long-term temporal context modeling while maximizing information from the extracted video clip features with a basic, parameter-free, and local region operating max-pooling block. Picking out only the most critical information for adjacent and local clip embeddings, this block results in a more efficient TAL model. We demonstrate that TemporalMaxer outperforms other state-of-the-art methods that utilize long-term TCM such as self-attention on various TAL datasets while requiring significantly fewer parameters and computational resources. The code for our approach is publicly available at https://github.com/TuanTNG/TemporalMaxer","url_abs":"https://arxiv.org/abs/2303.09055v1","url_pdf":"https://arxiv.org/pdf/2303.09055v1.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":"temporalmaxer-maximize-temporal-context-with","repo_url":"https://github.com/tuantng/temporalmaxer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-localization","task_name":"Action Localization"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/temporal-action-localization-on-epic-kitchens","task":"Temporal Action Localization","dataset":"EPIC-KITCHENS-100","model":"TemporalMaxer (verb)","rank_in_archive_order":3,"of":6,"metrics":{"Avg mAP (0.1-0.5)":"24.5","mAP IOU@0.1":"27.8","mAP IOU@0.2":"26.6","mAP IOU@0.3":"25.3","mAP IOU@0.4":"23.1","mAP IOU@0.5":"19.9"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-action-localization-on-muses","task":"Temporal Action Localization","dataset":"MUSES","model":"TemporalMaxer","rank_in_archive_order":1,"of":2,"metrics":{"mAP":"27.2","mAP@0.3":"36.7","mAP@0.4":"33.2","mAP@0.5":"27.8 ","mAP@0.6":"21.9","mAP@0.7":"16.2"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-action-localization-on-multithumos-1","task":"Temporal Action Localization","dataset":"MultiTHUMOS","model":"TemporalMaxer","rank_in_archive_order":4,"of":8,"metrics":{"Average mAP":"29.9","mAP IOU@0.1":"49.1","mAP IOU@0.2":"47.5","mAP IOU@0.3":"44.3","mAP IOU@0.4":"39.4","mAP IOU@0.5":"33.4","mAP IOU@0.6":"26.5","mAP IOU@0.7":"17.4","mAP IOU@0.8":"9.1","mAP IOU@0.9":"2.24"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-action-localization-on-thumos14","task":"Temporal Action Localization","dataset":"THUMOS’14","model":"TemporalMaxer (I3D features)","rank_in_archive_order":11,"of":42,"metrics":{"Avg mAP (0.3:0.7)":"67.7","mAP IOU@0.3":"82.8","mAP IOU@0.4":"78.9","mAP IOU@0.5":"71.8","mAP IOU@0.6":"60.5","mAP IOU@0.7":"44.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.09055","atlas_url":"https://app.syntology.ai/?focus=2303.09055","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":"2303.09055"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2303.09055\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2303.09055"},"call":"get_concepts_for_paper(arxiv_id=\"2303.09055\")"}],"by_repo":[{"repo":"tuantng/temporalmaxer","kind":"official","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":"6e4da252c8dc5069c952177dd0fcc567db58888edd627b10529e8a3901f3885a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}