{"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/span-based-localizing-network-for-natural","title":"Span-based Localizing Network for Natural Language Video Localization","arxiv_id":"2004.13931","date":"2020-04-29","proceeding":"ACL 2020 6","authors":["Hao Zhang","Aixin Sun","Wei Jing","Joey Tianyi Zhou"],"abstract":"Given an untrimmed video and a text query, natural language video localization (NLVL) is to locate a matching span from the video that semantically corresponds to the query. Existing solutions formulate NLVL either as a ranking task and apply multimodal matching architecture, or as a regression task to directly regress the target video span. In this work, we address NLVL task with a span-based QA approach by treating the input video as text passage. We propose a video span localizing network (VSLNet), on top of the standard span-based QA framework, to address NLVL. The proposed VSLNet tackles the differences between NLVL and span-based QA through a simple yet effective query-guided highlighting (QGH) strategy. The QGH guides VSLNet to search for matching video span within a highlighted region. Through extensive experiments on three benchmark datasets, we show that the proposed VSLNet outperforms the state-of-the-art methods; and adopting span-based QA framework is a promising direction to solve NLVL.","url_abs":"https://arxiv.org/abs/2004.13931v2","url_pdf":"https://arxiv.org/pdf/2004.13931v2.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":"span-based-localizing-network-for-natural","repo_url":"https://github.com/IsaacChanghau/VSLNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"temporal-sentence-grounding","task_name":"Temporal Sentence Grounding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/temporal-sentence-grounding-on-ego4d-goalstep","task":"Temporal Sentence Grounding","dataset":"Ego4D-Goalstep","model":"VSLNet","rank_in_archive_order":3,"of":3,"metrics":{"R@1,IoU=0.3":"11.70"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.13931","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.13931"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/IsaacChanghau/VSLNet","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"unverified":7},"by_repo_kind":{"official":{"samples":8,"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":"60df4d5a1eee1b92","entry":"mask_logits","repo":"IsaacChanghau/VSLNet","repo_kind":"official","path":"model/layers_t7.py","file_url":"https://github.com/IsaacChanghau/VSLNet/blob/HEAD/model/layers_t7.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"60df4d5a1eee1b92"}},{"code_sha256_prefix":"4e202cca8e3ea3af","entry":"count_params","repo":"IsaacChanghau/VSLNet","repo_kind":"official","path":"model/ops.py","file_url":"https://github.com/IsaacChanghau/VSLNet/blob/HEAD/model/ops.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e202cca8e3ea3af"}},{"code_sha256_prefix":"643e5c0498d8393e","entry":"crosscheck_videos","repo":"IsaacChanghau/VSLNet","repo_kind":"official","path":"prepare/download_activitynet_video.py","file_url":"https://github.com/IsaacChanghau/VSLNet/blob/HEAD/prepare/download_activitynet_video.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"643e5c0498d8393e"}},{"code_sha256_prefix":"165f82154890ed43","entry":"extract_features","repo":"IsaacChanghau/VSLNet","repo_kind":"official","path":"prepare/extract_activitynet.py","file_url":"https://github.com/IsaacChanghau/VSLNet/blob/HEAD/prepare/extract_activitynet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"165f82154890ed43"}},{"code_sha256_prefix":"9eb82fd2ed0c768d","entry":"get_shape_list","repo":"IsaacChanghau/VSLNet","repo_kind":"official","path":"model/ops.py","file_url":"https://github.com/IsaacChanghau/VSLNet/blob/HEAD/model/ops.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9eb82fd2ed0c768d"}},{"code_sha256_prefix":"2b9cf698c6fbf32b","entry":"load_images","repo":"IsaacChanghau/VSLNet","repo_kind":"official","path":"prepare/extract_activitynet.py","file_url":"https://github.com/IsaacChanghau/VSLNet/blob/HEAD/prepare/extract_activitynet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b9cf698c6fbf32b"}},{"code_sha256_prefix":"e168b7ed17766ce5","entry":"mask_logits","repo":"IsaacChanghau/VSLNet","repo_kind":"official","path":"model/ops.py","file_url":"https://github.com/IsaacChanghau/VSLNet/blob/HEAD/model/ops.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e168b7ed17766ce5"}},{"code_sha256_prefix":"6c360dafe2114a71","entry":"word_embedding_lookup","repo":"IsaacChanghau/VSLNet","repo_kind":"official","path":"model/layers.py","file_url":"https://github.com/IsaacChanghau/VSLNet/blob/HEAD/model/layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6c360dafe2114a71"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}