{"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/language-repository-for-long-video","title":"Language Repository for Long Video Understanding","arxiv_id":"2403.14622","date":"2024-03-21","proceeding":null,"authors":["Kumara Kahatapitiya","Kanchana Ranasinghe","Jongwoo Park","Michael S. Ryoo"],"abstract":"Language has become a prominent modality in computer vision with the rise of LLMs. Despite supporting long context-lengths, their effectiveness in handling long-term information gradually declines with input length. This becomes critical, especially in applications such as long-form video understanding. In this paper, we introduce a Language Repository (LangRepo) for LLMs, that maintains concise and structured information as an interpretable (i.e., all-textual) representation. Our repository is updated iteratively based on multi-scale video chunks. We introduce write and read operations that focus on pruning redundancies in text, and extracting information at various temporal scales. The proposed framework is evaluated on zero-shot visual question-answering benchmarks including EgoSchema, NExT-QA, IntentQA and NExT-GQA, showing state-of-the-art performance at its scale. Our code is available at https://github.com/kkahatapitiya/LangRepo.","url_abs":"https://arxiv.org/abs/2403.14622v2","url_pdf":"https://arxiv.org/pdf/2403.14622v2.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":"language-repository-for-long-video","repo_url":"https://github.com/kkahatapitiya/langrepo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":null,"task_name":"EgoSchema"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"zeroshot-video-question-answer","task_name":"Zero-Shot Video Question Answer"}],"methods":[{"method_slug":"focus","method_name":"Focus"},{"method_slug":"pruning","method_name":"Pruning"}],"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":"LangRepo (12B)","rank_in_archive_order":20,"of":29,"metrics":{"Accuracy":"41.2"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-egoschema","task":"Zero-Shot Video Question Answer","dataset":"EgoSchema (subset)","model":"LangRepo (12B)","rank_in_archive_order":3,"of":14,"metrics":{"Accuracy":"66.2"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-intentqa","task":"Zero-Shot Video Question Answer","dataset":"IntentQA","model":"LangRepo (12B)","rank_in_archive_order":10,"of":13,"metrics":{"Accuracy":"59.1"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-next-gqa","task":"Zero-Shot Video Question Answer","dataset":"NExT-GQA","model":"LangRepo (12B)","rank_in_archive_order":7,"of":9,"metrics":{"Acc@GQA":"17.1"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-next-qa","task":"Zero-Shot Video Question Answer","dataset":"NExT-QA","model":"LangRepo (12B)","rank_in_archive_order":22,"of":27,"metrics":{"Accuracy":"60.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.14622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14622"}},"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/kkahatapitiya/langrepo","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":9,"ran":9,"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":"d3cd8c8e5b09319c","entry":"clean_text","repo":"kkahatapitiya/langrepo","repo_kind":"official","path":"util.py","file_url":"https://github.com/kkahatapitiya/langrepo/blob/HEAD/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d3cd8c8e5b09319c"}},{"code_sha256_prefix":"bd041cf95d856b5d","entry":"do_nothing","repo":"kkahatapitiya/langrepo","repo_kind":"official","path":"merge.py","file_url":"https://github.com/kkahatapitiya/langrepo/blob/HEAD/merge.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":"bd041cf95d856b5d"}},{"code_sha256_prefix":"7beee5e0aa97c0e8","entry":"first_char_after_anchor","repo":"kkahatapitiya/langrepo","repo_kind":"official","path":"prompts.py","file_url":"https://github.com/kkahatapitiya/langrepo/blob/HEAD/prompts.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7beee5e0aa97c0e8"}},{"code_sha256_prefix":"ef77f23d65b9a1cf","entry":"first_char_as_answer","repo":"kkahatapitiya/langrepo","repo_kind":"official","path":"prompts.py","file_url":"https://github.com/kkahatapitiya/langrepo/blob/HEAD/prompts.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ef77f23d65b9a1cf"}},{"code_sha256_prefix":"036725c05a3d96f8","entry":"identity","repo":"kkahatapitiya/langrepo","repo_kind":"official","path":"prompts.py","file_url":"https://github.com/kkahatapitiya/langrepo/blob/HEAD/prompts.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"036725c05a3d96f8"}},{"code_sha256_prefix":"c66afae7b5227098","entry":"init_generator","repo":"kkahatapitiya/langrepo","repo_kind":"official","path":"merge.py","file_url":"https://github.com/kkahatapitiya/langrepo/blob/HEAD/merge.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c66afae7b5227098"}},{"code_sha256_prefix":"658682feda4928a2","entry":"load_json","repo":"kkahatapitiya/langrepo","repo_kind":"official","path":"util.py","file_url":"https://github.com/kkahatapitiya/langrepo/blob/HEAD/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"658682feda4928a2"}},{"code_sha256_prefix":"8080055de6293a6b","entry":"load_pkl","repo":"kkahatapitiya/langrepo","repo_kind":"official","path":"util.py","file_url":"https://github.com/kkahatapitiya/langrepo/blob/HEAD/util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8080055de6293a6b"}},{"code_sha256_prefix":"16eb26a585c085e1","entry":"mps_gather_workaround","repo":"kkahatapitiya/langrepo","repo_kind":"official","path":"merge.py","file_url":"https://github.com/kkahatapitiya/langrepo/blob/HEAD/merge.py","link_basis":"plan_row","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":"16eb26a585c085e1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}