{"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/vlg-net-video-language-graph-matching-network","title":"VLG-Net: Video-Language Graph Matching Network for Video Grounding","arxiv_id":"2011.10132","date":"2020-11-19","proceeding":null,"authors":["Mattia Soldan","Mengmeng Xu","Sisi Qu","Jesper Tegner","Bernard Ghanem"],"abstract":"Grounding language queries in videos aims at identifying the time interval (or moment) semantically relevant to a language query. The solution to this challenging task demands understanding videos' and queries' semantic content and the fine-grained reasoning about their multi-modal interactions. Our key idea is to recast this challenge into an algorithmic graph matching problem. Fueled by recent advances in Graph Neural Networks, we propose to leverage Graph Convolutional Networks to model video and textual information as well as their semantic alignment. To enable the mutual exchange of information across the modalities, we design a novel Video-Language Graph Matching Network (VLG-Net) to match video and query graphs. Core ingredients include representation graphs built atop video snippets and query tokens separately and used to model intra-modality relationships. A Graph Matching layer is adopted for cross-modal context modeling and multi-modal fusion. Finally, moment candidates are created using masked moment attention pooling by fusing the moment's enriched snippet features. We demonstrate superior performance over state-of-the-art grounding methods on three widely used datasets for temporal localization of moments in videos with language queries: ActivityNet-Captions, TACoS, and DiDeMo.","url_abs":"https://arxiv.org/abs/2011.10132v2","url_pdf":"https://arxiv.org/pdf/2011.10132v2.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":"vlg-net-video-language-graph-matching-network","repo_url":"https://github.com/Soldelli/VLG-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-matching","task_name":"Graph Matching"},{"task_slug":"moment-retrieval","task_name":"Moment Retrieval"},{"task_slug":"natural-language-moment-retrieval","task_name":"Natural Language Moment Retrieval"},{"task_slug":"temporal-localization","task_name":"Temporal Localization"},{"task_slug":"video-grounding","task_name":"Video Grounding"}],"methods":[{"method_slug":"graph-convolutional-networks","method_name":"Graph Convolutional Networks"},{"method_slug":"vlg-net","method_name":"VLG-Net"}],"datasets_introduced":[],"methods_introduced":[{"slug":"vlg-net","name":"VLG-Net","full_name":"Video Language Graph Matching Network"}],"results":[{"leaderboard":"/sota/natural-language-moment-retrieval-on","task":"Natural Language Moment Retrieval","dataset":"ActivityNet Captions","model":"VLG-Net","rank_in_archive_order":6,"of":8,"metrics":{"R@1,IoU=0.5":"46.32","R@1,IoU=0.7":"29.82","R@5,IoU=0.5":"77.15","R@5,IoU=0.7":"63.33"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-moment-retrieval-on-didemo","task":"Natural Language Moment Retrieval","dataset":"DiDeMo","model":"VLG-Net","rank_in_archive_order":1,"of":1,"metrics":{"R@1,IoU=0.5":"33.35","R@1,IoU=0.7":"25.57","R@1,IoU=1.0":"25.57","R@5,IoU=0.5":"88.86","R@5,IoU=0.7":"71.72","R@5,IoU=1.0":"71.65"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-moment-retrieval-on-tacos","task":"Natural Language Moment Retrieval","dataset":"TACoS","model":"VLG-Net","rank_in_archive_order":12,"of":13,"metrics":{"R@1,IoU=0.3":"45.46","R@1,IoU=0.5":"34.19","R@5,IoU=0.1":"81.80","R@5,IoU=0.3":"70.38","R@5,IoU=0.5":"56.56"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2011.10132","atlas_url":"https://app.syntology.ai/?focus=2011.10132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.10132"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Soldelli/VLG-Net","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"7a734d85428d248e","entry":"load_pretrained_graph_weights","repo":"Soldelli/VLG-Net","repo_kind":"listed","path":"train_net.py","file_url":"https://github.com/Soldelli/VLG-Net/blob/HEAD/train_net.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7a734d85428d248e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}