{"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/boundary-denoising-for-video-activity","title":"Boundary-Denoising for Video Activity Localization","arxiv_id":"2304.02934","date":"2023-04-06","proceeding":null,"authors":["Mengmeng Xu","Mattia Soldan","Jialin Gao","Shuming Liu","Juan-Manuel Pérez-Rúa","Bernard Ghanem"],"abstract":"Video activity localization aims at understanding the semantic content in long untrimmed videos and retrieving actions of interest. The retrieved action with its start and end locations can be used for highlight generation, temporal action detection, etc. Unfortunately, learning the exact boundary location of activities is highly challenging because temporal activities are continuous in time, and there are often no clear-cut transitions between actions. Moreover, the definition of the start and end of events is subjective, which may confuse the model. To alleviate the boundary ambiguity, we propose to study the video activity localization problem from a denoising perspective. Specifically, we propose an encoder-decoder model named DenoiseLoc. During training, a set of action spans is randomly generated from the ground truth with a controlled noise scale. Then we attempt to reverse this process by boundary denoising, allowing the localizer to predict activities with precise boundaries and resulting in faster convergence speed. Experiments show that DenoiseLoc advances %in several video activity understanding tasks. For example, we observe a gain of +12.36% average mAP on QV-Highlights dataset and +1.64% mAP@0.5 on THUMOS'14 dataset over the baseline. Moreover, DenoiseLoc achieves state-of-the-art performance on TACoS and MAD datasets, but with much fewer predictions compared to other current methods.","url_abs":"https://arxiv.org/abs/2304.02934v1","url_pdf":"https://arxiv.org/pdf/2304.02934v1.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":"boundary-denoising-for-video-activity","repo_url":"https://github.com/frostinassiky/denoiseloc","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-detection","task_name":"Action Detection"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"moment-retrieval","task_name":"Moment Retrieval"},{"task_slug":"video-grounding","task_name":"Video Grounding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/moment-retrieval-on-qvhighlights","task":"Moment Retrieval","dataset":"QVHighlights","model":"DenoiseLoc","rank_in_archive_order":32,"of":32,"metrics":{"R@1 IoU=0.5":"59.27","R@1 IoU=0.7":"45.07"},"uses_additional_data":false},{"leaderboard":"/sota/video-grounding-on-mad","task":"Video Grounding","dataset":"MAD","model":"DenoiseLoc","rank_in_archive_order":2,"of":2,"metrics":{"R@1,IoU=0.1":"11.59","R@10,IoU=0.1":"41.44","R@100,IoU=0.1":"73.62","R@5,IoU=0.1":"30.35","R@50,IoU=0.1":"66.07"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.02934","atlas_url":"https://app.syntology.ai/?focus=2304.02934","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":"2304.02934"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2304.02934\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2304.02934"},"call":"get_concepts_for_paper(arxiv_id=\"2304.02934\")"}],"by_repo":[{"repo":"frostinassiky/denoiseloc","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":"09543169b9dd12fe767de456289dbe4a817a6c2b29a54d07e6b99a03790ded51","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}