{"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/adversarial-background-aware-loss-for-weakly","title":"Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity Localization","arxiv_id":"2007.06643","date":"2020-07-13","proceeding":"ECCV 2020 8","authors":["Kyle Min","Jason J. Corso"],"abstract":"Temporally localizing activities within untrimmed videos has been extensively studied in recent years. Despite recent advances, existing methods for weakly-supervised temporal activity localization struggle to recognize when an activity is not occurring. To address this issue, we propose a novel method named A2CL-PT. Two triplets of the feature space are considered in our approach: one triplet is used to learn discriminative features for each activity class, and the other one is used to distinguish the features where no activity occurs (i.e. background features) from activity-related features for each video. To further improve the performance, we build our network using two parallel branches which operate in an adversarial way: the first branch localizes the most salient activities of a video and the second one finds other supplementary activities from non-localized parts of the video. Extensive experiments performed on THUMOS14 and ActivityNet datasets demonstrate that our proposed method is effective. Specifically, the average mAP of IoU thresholds from 0.1 to 0.9 on the THUMOS14 dataset is significantly improved from 27.9% to 30.0%.","url_abs":"https://arxiv.org/abs/2007.06643v1","url_pdf":"https://arxiv.org/pdf/2007.06643v1.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":"adversarial-background-aware-loss-for-weakly","repo_url":"https://github.com/kylemin/A2CL-PT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":null,"task_name":"Triplet"},{"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-1","task":"Weakly Supervised Action Localization","dataset":"ActivityNet-1.3","model":"A2CL-PT","rank_in_archive_order":12,"of":17,"metrics":{"mAP@0.5":"36.8","mAP@0.5:0.95":"22.5"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on","task":"Weakly Supervised Action Localization","dataset":"THUMOS 2014","model":"A2CL-PT","rank_in_archive_order":17,"of":30,"metrics":{"mAP@0.1:0.5":"46.9","mAP@0.1:0.7":"37.8","mAP@0.5":"30.1"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on-5","task":"Weakly Supervised Action Localization","dataset":"THUMOS14","model":"A2CL-PT","rank_in_archive_order":10,"of":12,"metrics":{"avg-mAP (0.1-0.5)":"46.9","avg-mAP (0.1:0.7)":"37.8","avg-mAP (0.3-0.7)":"30.6"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-action-localization-on-4","task":"Weakly Supervised Action Localization","dataset":"THUMOS’14","model":"A2CL-PT","rank_in_archive_order":11,"of":13,"metrics":{"mAP@0.5":"30.1"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-temporal-action","task":"Weakly-supervised Temporal Action Localization","dataset":"THUMOS’14","model":"A2CL-PT","rank_in_archive_order":3,"of":4,"metrics":{"mAP IOU@0.1":"61.2","mAP IOU@0.2":"56.1","mAP IOU@0.3":"48.1","mAP IOU@0.4":"39.0","mAP IOU@0.5":"30.1","mAP IOU@0.6":"19.2","mAP IOU@0.7":"10.6","mAP IOU@0.8":"4.8","mAP IOU@0.9":"1.0","mAP@AVG(0.1:0.9)":"30.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2007.06643","atlas_url":"https://app.syntology.ai/?focus=2007.06643","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":"2007.06643"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2007.06643\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2007.06643"},"call":"get_concepts_for_paper(arxiv_id=\"2007.06643\")"}],"by_repo":[{"repo":"kylemin/A2CL-PT","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":"e991ed2016005744d4417f06c21f24262ccefdba07b1ad1316bc7bb4b60e7b8e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}