{"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/mtvr-multilingual-moment-retrieval-in-videos","title":"MTVR: Multilingual Moment Retrieval in Videos","arxiv_id":"2108.00061","date":"2021-07-30","proceeding":"ACL 2021 5","authors":["Jie Lei","Tamara L. Berg","Mohit Bansal"],"abstract":"We introduce mTVR, a large-scale multilingual video moment retrieval dataset, containing 218K English and Chinese queries from 21.8K TV show video clips. The dataset is collected by extending the popular TVR dataset (in English) with paired Chinese queries and subtitles. Compared to existing moment retrieval datasets, mTVR is multilingual, larger, and comes with diverse annotations. We further propose mXML, a multilingual moment retrieval model that learns and operates on data from both languages, via encoder parameter sharing and language neighborhood constraints. We demonstrate the effectiveness of mXML on the newly collected MTVR dataset, where mXML outperforms strong monolingual baselines while using fewer parameters. In addition, we also provide detailed dataset analyses and model ablations. Data and code are publicly available at https://github.com/jayleicn/mTVRetrieval","url_abs":"https://arxiv.org/abs/2108.00061v1","url_pdf":"https://arxiv.org/pdf/2108.00061v1.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":"mtvr-multilingual-moment-retrieval-in-videos","repo_url":"https://github.com/jayleicn/mTVRetrieval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"moment-retrieval","task_name":"Moment Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[{"slug":"mtvr","name":"mTVR","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2108.00061","atlas_url":"https://app.syntology.ai/?focus=2108.00061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.00061"}},"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/jayleicn/mTVRetrieval","reach":null}],"summary":{"ran":6,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":10,"ran":7,"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":10,"samples":[{"code_sha256_prefix":"d7fb7167ff474aeb","entry":"BertAttention","repo":"jayleicn/mTVRetrieval","repo_kind":"official","path":"baselines/mxml/model_xml_shared.py","file_url":"https://github.com/jayleicn/mTVRetrieval/blob/HEAD/baselines/mxml/model_xml_shared.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d7fb7167ff474aeb"}},{"code_sha256_prefix":"a35f293effa83702","entry":"BertSelfOutput","repo":"jayleicn/mTVRetrieval","repo_kind":"official","path":"baselines/mxml/model_xml_shared.py","file_url":"https://github.com/jayleicn/mTVRetrieval/blob/HEAD/baselines/mxml/model_xml_shared.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a35f293effa83702"}},{"code_sha256_prefix":"38a1280d3a5d384f","entry":"ConvEncoder","repo":"jayleicn/mTVRetrieval","repo_kind":"official","path":"baselines/mxml/model_xml_shared.py","file_url":"https://github.com/jayleicn/mTVRetrieval/blob/HEAD/baselines/mxml/model_xml_shared.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"38a1280d3a5d384f"}},{"code_sha256_prefix":"106a951f0c6e3d8b","entry":"DepthwiseSeparableConv","repo":"jayleicn/mTVRetrieval","repo_kind":"official","path":"baselines/mxml/model_xml_shared.py","file_url":"https://github.com/jayleicn/mTVRetrieval/blob/HEAD/baselines/mxml/model_xml_shared.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"106a951f0c6e3d8b"}},{"code_sha256_prefix":"df7b9d7001cc5e80","entry":"RNNEncoder","repo":"jayleicn/mTVRetrieval","repo_kind":"official","path":"baselines/mxml/model_xml_shared.py","file_url":"https://github.com/jayleicn/mTVRetrieval/blob/HEAD/baselines/mxml/model_xml_shared.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"df7b9d7001cc5e80"}},{"code_sha256_prefix":"4c7b7aecba17d832","entry":"TrainablePositionalEncoding","repo":"jayleicn/mTVRetrieval","repo_kind":"official","path":"baselines/mxml/model_xml_shared.py","file_url":"https://github.com/jayleicn/mTVRetrieval/blob/HEAD/baselines/mxml/model_xml_shared.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4c7b7aecba17d832"}},{"code_sha256_prefix":"1a5542dee1f0295c","entry":"mask_logits","repo":"jayleicn/mTVRetrieval","repo_kind":"official","path":"baselines/mxml/model_xml_shared.py","file_url":"https://github.com/jayleicn/mTVRetrieval/blob/HEAD/baselines/mxml/model_xml_shared.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1a5542dee1f0295c"}},{"code_sha256_prefix":"f68c67bac0562ca9","entry":"BertSelfAttention","repo":"jayleicn/mTVRetrieval","repo_kind":"official","path":"baselines/mxml/model_xml_shared.py","file_url":"https://github.com/jayleicn/mTVRetrieval/blob/HEAD/baselines/mxml/model_xml_shared.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f68c67bac0562ca9"}},{"code_sha256_prefix":"35e7bd100103d64b","entry":"XML","repo":"jayleicn/mTVRetrieval","repo_kind":"official","path":"baselines/mxml/model_xml_shared.py","file_url":"https://github.com/jayleicn/mTVRetrieval/blob/HEAD/baselines/mxml/model_xml_shared.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"35e7bd100103d64b"}},{"code_sha256_prefix":"f92c658edfb11489","entry":"XMLShared","repo":"jayleicn/mTVRetrieval","repo_kind":"official","path":"baselines/mxml/model_xml_shared.py","file_url":"https://github.com/jayleicn/mTVRetrieval/blob/HEAD/baselines/mxml/model_xml_shared.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f92c658edfb11489"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}