{"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/too-many-frames-not-all-useful-efficient","title":"Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA","arxiv_id":"2406.09396","date":"2024-06-13","proceeding":null,"authors":["Jongwoo Park","Kanchana Ranasinghe","Kumara Kahatapitiya","Wonjeong Ryoo","Donghyun Kim","Michael S. Ryoo"],"abstract":"Long-form videos that span across wide temporal intervals are highly information redundant and contain multiple distinct events or entities that are often loosely related. Therefore, when performing long-form video question answering (LVQA), all information necessary to generate a correct response can often be contained within a small subset of frames. Recent literature explore the use of large language models (LLMs) in LVQA benchmarks, achieving exceptional performance, while relying on vision language models (VLMs) to convert all visual content within videos into natural language. Such VLMs often independently caption a large number of frames uniformly sampled from long videos, which is not efficient and can mostly be redundant. Questioning these decision choices, we explore optimal strategies for key-frame selection that can significantly reduce these redundancies, namely Hierarchical Keyframe Selector. Our proposed framework, LVNet, achieves state-of-the-art performance at a comparable caption scale across three benchmark LVQA datasets: EgoSchema, NExT-QA, IntentQA. The code can be found at https://github.com/jongwoopark7978/LVNet","url_abs":"https://arxiv.org/abs/2406.09396v4","url_pdf":"https://arxiv.org/pdf/2406.09396v4.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":"too-many-frames-not-all-useful-efficient","repo_url":"https://github.com/jongwoopark7978/LVNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":null,"task_name":"EgoSchema"},{"task_slug":"form","task_name":"Form"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"zeroshot-video-question-answer","task_name":"Zero-Shot Video Question Answer"}],"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":"LVNet","rank_in_archive_order":8,"of":29,"metrics":{"Accuracy":"61.1"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-egoschema","task":"Zero-Shot Video Question Answer","dataset":"EgoSchema (subset)","model":"LVNet","rank_in_archive_order":5,"of":14,"metrics":{"Accuracy":"66.0"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-intentqa","task":"Zero-Shot Video Question Answer","dataset":"IntentQA","model":"LVNet","rank_in_archive_order":2,"of":13,"metrics":{"Accuracy":"71.1"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-video-question-answer-on-next-qa","task":"Zero-Shot Video Question Answer","dataset":"NExT-QA","model":"LVNet(GPT-4o)","rank_in_archive_order":7,"of":27,"metrics":{"Accuracy":"72.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.09396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09396"}},"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/jongwoopark7978/LVNet","reach":null}],"summary":{"ran_draft_wrong":3},"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":3,"samples":[{"code_sha256_prefix":"1557cab53f91c06c","entry":"SortSimilarity","repo":"jongwoopark7978/LVNet","repo_kind":"official","path":"coarseKeyframeDetector.py","file_url":"https://github.com/jongwoopark7978/LVNet/blob/HEAD/coarseKeyframeDetector.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1557cab53f91c06c"}},{"code_sha256_prefix":"3069205356329c82","entry":"create_question","repo":"jongwoopark7978/LVNet","repo_kind":"official","path":"fineKeyframeDetector.py","file_url":"https://github.com/jongwoopark7978/LVNet/blob/HEAD/fineKeyframeDetector.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3069205356329c82"}},{"code_sha256_prefix":"f41cb1a19b154297","entry":"encode_image","repo":"jongwoopark7978/LVNet","repo_kind":"official","path":"fineKeyframeDetector.py","file_url":"https://github.com/jongwoopark7978/LVNet/blob/HEAD/fineKeyframeDetector.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f41cb1a19b154297"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}