{"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/tsp-temporally-sensitive-pretraining-of-video","title":"TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks","arxiv_id":"2011.11479","date":"2020-11-23","proceeding":null,"authors":["Humam Alwassel","Silvio Giancola","Bernard Ghanem"],"abstract":"Due to the large memory footprint of untrimmed videos, current state-of-the-art video localization methods operate atop precomputed video clip features. These features are extracted from video encoders typically trained for trimmed action classification tasks, making such features not necessarily suitable for temporal localization. In this work, we propose a novel supervised pretraining paradigm for clip features that not only trains to classify activities but also considers background clips and global video information to improve temporal sensitivity. Extensive experiments show that using features trained with our novel pretraining strategy significantly improves the performance of recent state-of-the-art methods on three tasks: Temporal Action Localization, Action Proposal Generation, and Dense Video Captioning. We also show that our pretraining approach is effective across three encoder architectures and two pretraining datasets. We believe video feature encoding is an important building block for localization algorithms, and extracting temporally-sensitive features should be of paramount importance in building more accurate models. The code and pretrained models are available on our project website.","url_abs":"https://arxiv.org/abs/2011.11479v3","url_pdf":"https://arxiv.org/pdf/2011.11479v3.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":"tsp-temporally-sensitive-pretraining-of-video","repo_url":"https://github.com/HumamAlwassel/TSP","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-localization","task_name":"Action Localization"},{"task_slug":"dense-video-captioning","task_name":"Dense Video Captioning"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"temporal-action-proposal-generation","task_name":"Temporal Action Proposal Generation"},{"task_slug":"temporal-localization","task_name":"Temporal Localization"},{"task_slug":"video-captioning","task_name":"Video Captioning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dense-video-captioning-on-activitynet","task":"Dense Video Captioning","dataset":"ActivityNet Captions","model":"TSP","rank_in_archive_order":7,"of":12,"metrics":{"BLEU-3":"4.16","BLEU-4":"2.02","METEOR":"8.75"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-action-localization-on-activitynet","task":"Temporal Action Localization","dataset":"ActivityNet-1.3","model":"TSP","rank_in_archive_order":18,"of":33,"metrics":{"mAP":"35.81","mAP IOU@0.5":"51.26","mAP IOU@0.75":"37.12","mAP IOU@0.95":"9.29"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-action-localization-on-thumos14","task":"Temporal Action Localization","dataset":"THUMOS’14","model":"TSP","rank_in_archive_order":25,"of":42,"metrics":{"Avg mAP (0.3:0.7)":"50.46","mAP IOU@0.1":"74.02","mAP IOU@0.2":"72.29","mAP IOU@0.3":"69.1","mAP IOU@0.4":"63.3","mAP IOU@0.5":"53.5","mAP IOU@0.6":"40.4","mAP IOU@0.7":"26"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-action-proposal-generation-on","task":"Temporal Action Proposal Generation","dataset":"ActivityNet-1.3","model":"TSP","rank_in_archive_order":5,"of":11,"metrics":{"AR@100":"76.63","AUC (val)":"69.04"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2011.11479","atlas_url":"https://app.syntology.ai/?focus=2011.11479","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":"2011.11479"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2011.11479\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2011.11479"},"call":"get_concepts_for_paper(arxiv_id=\"2011.11479\")"}],"by_repo":[{"repo":"HumamAlwassel/TSP","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":"c2c72d17eacfc908607c7600b344f9db902c216aafde6a3b8ee13ea9e58029f8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}