{"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/understanding-long-videos-in-one-multimodal","title":"Understanding Long Videos with Multimodal Language Models","arxiv_id":"2403.16998","date":"2024-03-25","proceeding":null,"authors":["Kanchana Ranasinghe","Xiang Li","Kumara Kahatapitiya","Michael S. Ryoo"],"abstract":"Large Language Models (LLMs) have allowed recent LLM-based approaches to achieve excellent performance on long-video understanding benchmarks. We investigate how extensive world knowledge and strong reasoning skills of underlying LLMs influence this strong performance. Surprisingly, we discover that LLM-based approaches can yield surprisingly good accuracy on long-video tasks with limited video information, sometimes even with no video specific information. Building on this, we exploring injecting video-specific information into an LLM-based framework. We utilize off-the-shelf vision tools to extract three object-centric information modalities from videos and then leverage natural language as a medium for fusing this information. Our resulting Multimodal Video Understanding (MVU) framework demonstrates state-of-the-art performance across multiple video understanding benchmarks. Strong performance also on robotics domain tasks establish its strong generality. Our code will be released publicly.","url_abs":"https://arxiv.org/abs/2403.16998v2","url_pdf":"https://arxiv.org/pdf/2403.16998v2.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":"understanding-long-videos-in-one-multimodal","repo_url":"https://github.com/kahnchana/mvu","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"fine-grained-action-recognition","task_name":"Fine-grained Action Recognition"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"multiple-choice","task_name":"Multiple-choice"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"world-knowledge","task_name":"World Knowledge"},{"task_slug":"zeroshot-video-question-answer","task_name":"Zero-Shot Video Question Answer"},{"task_slug":"zero-shot-long-video-question-answering","task_name":"zero-shot long video question answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/zero-shot-video-question-answer-on-egoschema-1","task":"Zero-Shot Video Question Answer","dataset":"EgoSchema (fullset)","model":"MVU (13B)","rank_in_archive_order":21,"of":29,"metrics":{"Accuracy":"37.6"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-egoschema","task":"Zero-Shot Video Question Answer","dataset":"EgoSchema (subset)","model":"MVU (13B)","rank_in_archive_order":8,"of":14,"metrics":{"Accuracy":"60.3","Inference Speed (s)":"2.42"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-next-qa","task":"Zero-Shot Video Question Answer","dataset":"NExT-QA","model":"MVU (13B)","rank_in_archive_order":24,"of":27,"metrics":{"Accuracy":"55.2"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2403.16998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16998"}},"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":"deterministic:regex_extraction","url":"https://github.com/kahnchana/mvu","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/jongwoopark7978/LVNet","reach":null}],"summary":{"ran_draft_wrong":4},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":1,"samples":[{"code_sha256_prefix":"1557cab53f91c06c","entry":"SortSimilarity","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"1557cab53f91c06c"}},{"code_sha256_prefix":"7717ae3b63a23685","entry":"calc_loglikelihood","repo":"kahnchana/mvu","repo_kind":"official","path":"src/model_frame_selection.py","file_url":"https://github.com/kahnchana/mvu/blob/HEAD/src/model_frame_selection.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7717ae3b63a23685"}},{"code_sha256_prefix":"42a46570620cd9fa","entry":"get_chunk","repo":"kahnchana/mvu","repo_kind":"official","path":"src/model_frame_selection.py","file_url":"https://github.com/kahnchana/mvu/blob/HEAD/src/model_frame_selection.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"42a46570620cd9fa"}},{"code_sha256_prefix":"076c252c52cbb161","entry":"split_list","repo":"kahnchana/mvu","repo_kind":"official","path":"src/model_frame_selection.py","file_url":"https://github.com/kahnchana/mvu/blob/HEAD/src/model_frame_selection.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"076c252c52cbb161"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}