{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/negative-sample-matters-a-renaissance-of","title":"Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding","arxiv_id":"2109.04872","date":"2021-09-10","proceeding":null,"authors":["Zhenzhi Wang","LiMin Wang","Tao Wu","TianHao Li","Gangshan Wu"],"abstract":"Temporal grounding aims to localize a video moment which is semantically aligned with a given natural language query. Existing methods typically apply a detection or regression pipeline on the fused representation with the research focus on designing complicated prediction heads or fusion strategies. Instead, from a perspective on temporal grounding as a metric-learning problem, we present a Mutual Matching Network (MMN), to directly model the similarity between language queries and video moments in a joint embedding space. This new metric-learning framework enables fully exploiting negative samples from two new aspects: constructing negative cross-modal pairs in a mutual matching scheme and mining negative pairs across different videos. These new negative samples could enhance the joint representation learning of two modalities via cross-modal mutual matching to maximize their mutual information. Experiments show that our MMN achieves highly competitive performance compared with the state-of-the-art methods on four video grounding benchmarks. Based on MMN, we present a winner solution for the HC-STVG challenge of the 3rd PIC workshop. This suggests that metric learning is still a promising method for temporal grounding via capturing the essential cross-modal correlation in a joint embedding space. Code is available at https://github.com/MCG-NJU/MMN.","url_abs":"https://arxiv.org/abs/2109.04872v2","url_pdf":"https://arxiv.org/pdf/2109.04872v2.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":"negative-sample-matters-a-renaissance-of","repo_url":"https://github.com/mcg-nju/mmn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"negative-sample-matters-a-renaissance-of","repo_url":"https://github.com/aim3-ruc/youmakeup_challenge2022","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"temporal-sentence-grounding","task_name":"Temporal Sentence Grounding"},{"task_slug":"video-grounding","task_name":"Video Grounding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/temporal-sentence-grounding-on-charades-sta","task":"Temporal Sentence Grounding","dataset":"Charades-STA","model":"MMN (Full, MViT-K400-Pretrain-feature, evaluated by AdaFocus)","rank_in_archive_order":4,"of":13,"metrics":{"R1@0.5":"55.2","R1@0.7":"32.2","R5@0.5":"88.3","R5@0.7":"62.7"},"uses_additional_data":false},{"leaderboard":"/sota/temporal-sentence-grounding-on-charades-sta","task":"Temporal Sentence Grounding","dataset":"Charades-STA","model":"MMN (Full, I3D-K400-Pretrain-feature, evaluated by AdaFocus)","rank_in_archive_order":5,"of":13,"metrics":{"R1@0.5":"49.4","R1@0.7":"29.8","R5@0.5":"85.8","R5@0.7":"60.5"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2109.04872","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}