{"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/background-modeling-via-uncertainty","title":"Weakly-supervised Temporal Action Localization by Uncertainty Modeling","arxiv_id":"2006.07006","date":"2020-06-12","proceeding":null,"authors":["Pilhyeon Lee","Jinglu Wang","Yan Lu","Hyeran Byun"],"abstract":"Weakly-supervised temporal action localization aims to learn detecting temporal intervals of action classes with only video-level labels. To this end, it is crucial to separate frames of action classes from the background frames (i.e., frames not belonging to any action classes). In this paper, we present a new perspective on background frames where they are modeled as out-of-distribution samples regarding their inconsistency. Then, background frames can be detected by estimating the probability of each frame being out-of-distribution, known as uncertainty, but it is infeasible to directly learn uncertainty without frame-level labels. To realize the uncertainty learning in the weakly-supervised setting, we leverage the multiple instance learning formulation. Moreover, we further introduce a background entropy loss to better discriminate background frames by encouraging their in-distribution (action) probabilities to be uniformly distributed over all action classes. Experimental results show that our uncertainty modeling is effective at alleviating the interference of background frames and brings a large performance gain without bells and whistles. We demonstrate that our model significantly outperforms state-of-the-art methods on the benchmarks, THUMOS'14 and ActivityNet (1.2 & 1.3). Our code is available at https://github.com/Pilhyeon/WTAL-Uncertainty-Modeling.","url_abs":"https://arxiv.org/abs/2006.07006v3","url_pdf":"https://arxiv.org/pdf/2006.07006v3.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":"background-modeling-via-uncertainty","repo_url":"https://github.com/Pilhyeon/WTAL-Uncertainty-Modeling","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"background-modeling-via-uncertainty","repo_url":"https://github.com/Pilhyeon/Learning-Action-Completeness-from-Points","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"action-localization","task_name":"Action Localization"},{"task_slug":"multiple-instance-learning","task_name":"Multiple Instance Learning"},{"task_slug":"out-of-distribution-detection","task_name":"Out-of-Distribution Detection"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"},{"task_slug":"weakly-supervised-action-localization","task_name":"Weakly Supervised Action Localization"},{"task_slug":"weakly-supervised-temporal-action","task_name":"Weakly-supervised Temporal Action Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-action-localization-on-2","task":"Weakly Supervised Action Localization","dataset":"ActivityNet-1.2","model":"Lee et al.","rank_in_archive_order":9,"of":19,"metrics":{"Mean mAP":"25.9","mAP@0.5":"41.2"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on-1","task":"Weakly Supervised Action Localization","dataset":"ActivityNet-1.3","model":"Lee et al.","rank_in_archive_order":11,"of":17,"metrics":{"mAP@0.5":"37","mAP@0.5:0.95":"23.7"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on","task":"Weakly Supervised Action Localization","dataset":"THUMOS 2014","model":"Lee et al.","rank_in_archive_order":14,"of":30,"metrics":{"mAP@0.1:0.5":"51.6","mAP@0.1:0.7":"41.9","mAP@0.5":"33.7"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on-5","task":"Weakly Supervised Action Localization","dataset":"THUMOS14","model":"Lee et al.","rank_in_archive_order":6,"of":12,"metrics":{"avg-mAP (0.1-0.5)":"51.6","avg-mAP (0.1:0.7)":"41.9","avg-mAP (0.3-0.7)":"32.9"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on-4","task":"Weakly Supervised Action Localization","dataset":"THUMOS’14","model":"Lee et al.","rank_in_archive_order":7,"of":13,"metrics":{"mAP@0.5":"33.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.07006","atlas_url":"https://app.syntology.ai/?focus=2006.07006","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":"2006.07006"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2006.07006\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2006.07006"},"call":"get_concepts_for_paper(arxiv_id=\"2006.07006\")"}],"by_repo":[{"repo":"Pilhyeon/WTAL-Uncertainty-Modeling","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["aaai_16280"],"harvested_for_calls":[]},{"repo":"Pilhyeon/Learning-Action-Completeness-from-Points","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"1b95979f2694144364f9ab89693094054024018b4797218b5cd0e18b36f2b8e0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}