{"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/multi-modal-transformer-for-video-retrieval","title":"Multi-modal Transformer for Video Retrieval","arxiv_id":"2007.10639","date":"2020-07-21","proceeding":"ECCV 2020 8","authors":["Valentin Gabeur","Chen Sun","Karteek Alahari","Cordelia Schmid"],"abstract":"The task of retrieving video content relevant to natural language queries plays a critical role in effectively handling internet-scale datasets. Most of the existing methods for this caption-to-video retrieval problem do not fully exploit cross-modal cues present in video. Furthermore, they aggregate per-frame visual features with limited or no temporal information. In this paper, we present a multi-modal transformer to jointly encode the different modalities in video, which allows each of them to attend to the others. The transformer architecture is also leveraged to encode and model the temporal information. On the natural language side, we investigate the best practices to jointly optimize the language embedding together with the multi-modal transformer. This novel framework allows us to establish state-of-the-art results for video retrieval on three datasets. More details are available at http://thoth.inrialpes.fr/research/MMT.","url_abs":"https://arxiv.org/abs/2007.10639v1","url_pdf":"https://arxiv.org/pdf/2007.10639v1.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":"multi-modal-transformer-for-video-retrieval","repo_url":"https://github.com/gabeur/mmt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"natural-language-queries","task_name":"Natural Language Queries"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"},{"task_slug":"zero-shot-video-retrieval","task_name":"Zero-Shot Video Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-retrieval-on-activitynet","task":"Video Retrieval","dataset":"ActivityNet","model":"MMT-Pretrained","rank_in_archive_order":27,"of":31,"metrics":{"text-to-video Mean Rank":"16","text-to-video Median Rank":"3.3","text-to-video R@1":"28.7","text-to-video R@5":"61.4","text-to-video R@50":"94.5"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-activitynet","task":"Video Retrieval","dataset":"ActivityNet","model":"MMT","rank_in_archive_order":30,"of":31,"metrics":{"text-to-video Mean Rank":"20.8","text-to-video Median Rank":"5","text-to-video R@1":"22.7","text-to-video R@5":"54.2","text-to-video R@50":"93.2"},"uses_additional_data":false},{"leaderboard":"/sota/video-retrieval-on-lsmdc","task":"Video Retrieval","dataset":"LSMDC","model":"MMT-Pretrained","rank_in_archive_order":29,"of":38,"metrics":{"text-to-video Median Rank":"19.3","text-to-video R@1":"13.5","text-to-video R@10":"40.1","text-to-video R@5":"29.9"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-lsmdc","task":"Video Retrieval","dataset":"LSMDC","model":"MMT","rank_in_archive_order":30,"of":38,"metrics":{"text-to-video Median Rank":"21","text-to-video R@1":"13.2","text-to-video R@10":"38.8","text-to-video R@5":"29.2"},"uses_additional_data":false},{"leaderboard":"/sota/video-retrieval-on-msr-vtt-1ka","task":"Video Retrieval","dataset":"MSR-VTT-1kA","model":"MMT-Pretrained","rank_in_archive_order":53,"of":63,"metrics":{"text-to-video Mean Rank":"24.0","text-to-video Median Rank":"4","text-to-video R@1":"26.6","text-to-video R@10":"69.6","text-to-video R@5":"57.1"},"uses_additional_data":true},{"leaderboard":"/sota/video-retrieval-on-msr-vtt-1ka","task":"Video Retrieval","dataset":"MSR-VTT-1kA","model":"MMT","rank_in_archive_order":55,"of":63,"metrics":{"text-to-video Mean Rank":"26.7","text-to-video Median Rank":"4","text-to-video R@1":"24.6","text-to-video R@10":"67.1","text-to-video R@5":"54.0"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-retrieval-on-msr-vtt","task":"Zero-Shot Video Retrieval","dataset":"MSR-VTT","model":"MMT","rank_in_archive_order":40,"of":41,"metrics":{"text-to-video Mean Rank":"148.1","text-to-video Median Rank":"66","text-to-video R@5":"14.4"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2007.10639","atlas_url":"https://app.syntology.ai/?focus=2007.10639","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.10639"}},"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/gabeur/mmt","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"ran":6},"by_repo_kind":{"listed":{"samples":7,"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":0,"samples":[{"code_sha256_prefix":"0f786c407fb1ee4c","entry":"swish","repo":"gabeur/mmt","repo_kind":"listed","path":"model/bert.py","file_url":"https://github.com/gabeur/mmt/blob/HEAD/model/bert.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0f786c407fb1ee4c"}},{"code_sha256_prefix":"bd78c55f13b78ce3","entry":"cols2metrics","repo":"gabeur/mmt","repo_kind":"listed","path":"model/metric.py","file_url":"https://github.com/gabeur/mmt/blob/HEAD/model/metric.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd78c55f13b78ce3"}},{"code_sha256_prefix":"2fd42cf688d23870","entry":"gelu","repo":"gabeur/mmt","repo_kind":"listed","path":"model/bert.py","file_url":"https://github.com/gabeur/mmt/blob/HEAD/model/bert.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2fd42cf688d23870"}},{"code_sha256_prefix":"3910f45c24ea70d4","entry":"get_clean_word","repo":"gabeur/mmt","repo_kind":"listed","path":"base/base_dataset.py","file_url":"https://github.com/gabeur/mmt/blob/HEAD/base/base_dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3910f45c24ea70d4"}},{"code_sha256_prefix":"1f25d43573a02940","entry":"is_end_of_sentence","repo":"gabeur/mmt","repo_kind":"listed","path":"base/base_dataset.py","file_url":"https://github.com/gabeur/mmt/blob/HEAD/base/base_dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1f25d43573a02940"}},{"code_sha256_prefix":"d7cd977eb21d3ff8","entry":"sharded_cross_view_inner_product","repo":"gabeur/mmt","repo_kind":"listed","path":"model/model.py","file_url":"https://github.com/gabeur/mmt/blob/HEAD/model/model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d7cd977eb21d3ff8"}},{"code_sha256_prefix":"79bc20d6b4080f0b","entry":"v2t_metrics","repo":"gabeur/mmt","repo_kind":"listed","path":"model/metric.py","file_url":"https://github.com/gabeur/mmt/blob/HEAD/model/metric.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"79bc20d6b4080f0b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}