{"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/multilevel-language-and-vision-integration","title":"Multilevel Language and Vision Integration for Text-to-Clip Retrieval","arxiv_id":"1804.05113","date":"2018-04-13","proceeding":null,"authors":["Huijuan Xu","Kun He","Bryan A. Plummer","Leonid Sigal","Stan Sclaroff","Kate Saenko"],"abstract":"We address the problem of text-based activity retrieval in video. Given a\nsentence describing an activity, our task is to retrieve matching clips from an\nuntrimmed video. To capture the inherent structures present in both text and\nvideo, we introduce a multilevel model that integrates vision and language\nfeatures earlier and more tightly than prior work. First, we inject text\nfeatures early on when generating clip proposals, to help eliminate unlikely\nclips and thus speed up processing and boost performance. Second, to learn a\nfine-grained similarity metric for retrieval, we use visual features to\nmodulate the processing of query sentences at the word level in a recurrent\nneural network. A multi-task loss is also employed by adding query\nre-generation as an auxiliary task. Our approach significantly outperforms\nprior work on two challenging benchmarks: Charades-STA and ActivityNet\nCaptions.","url_abs":"http://arxiv.org/abs/1804.05113v3","url_pdf":"http://arxiv.org/pdf/1804.05113v3.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":"multilevel-language-and-vision-integration","repo_url":"https://github.com/VisionLearningGroup/Text-to-Clip_Retrieval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.05113","atlas_url":"https://app.syntology.ai/?focus=1804.05113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.05113"}},"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/VisionLearningGroup/Text-to-Clip_Retrieval","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":"81aab88321de62c2","entry":"interpolated_prec_rec","repo":"VisionLearningGroup/Text-to-Clip_Retrieval","repo_kind":"official","path":"experiments/Text_to_Clip/test_fast/utils.py","file_url":"https://github.com/VisionLearningGroup/Text-to-Clip_Retrieval/blob/HEAD/experiments/Text_to_Clip/test_fast/utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"81aab88321de62c2"}},{"code_sha256_prefix":"d0744a2fe3151508","entry":"segment_iou","repo":"VisionLearningGroup/Text-to-Clip_Retrieval","repo_kind":"official","path":"experiments/Text_to_Clip/test_fast/utils.py","file_url":"https://github.com/VisionLearningGroup/Text-to-Clip_Retrieval/blob/HEAD/experiments/Text_to_Clip/test_fast/utils.py","link_basis":"harvester_set","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":"d0744a2fe3151508"}},{"code_sha256_prefix":"0087afa9a6463790","entry":"py_cpu_nms","repo":"VisionLearningGroup/Text-to-Clip_Retrieval","repo_kind":"official","path":"lib/nms/py_cpu_nms.py","file_url":"https://github.com/VisionLearningGroup/Text-to-Clip_Retrieval/blob/HEAD/lib/nms/py_cpu_nms.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":"0087afa9a6463790"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}