{"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/does-your-vision-language-model-get-lost-in","title":"Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?","arxiv_id":"2503.12496","date":"2025-03-16","proceeding":null,"authors":["Tianyuan Qu","Longxiang Tang","Bohao Peng","Senqiao Yang","Bei Yu","Jiaya Jia"],"abstract":"The rise of Large Vision-Language Models (LVLMs) has significantly advanced video understanding. However, efficiently processing long videos remains a challenge due to the ``Sampling Dilemma'': low-density sampling risks missing critical information, while high-density sampling introduces redundancy. To address this issue, we introduce LSDBench, the first benchmark designed to evaluate LVLMs on long-video tasks by constructing high Necessary Sampling Density (NSD) questions, where NSD represents the minimum sampling density required to accurately answer a given question. LSDBench focuses on dense, short-duration actions to rigorously assess the sampling strategies employed by LVLMs. To tackle the challenges posed by high-NSD questions, we propose a novel Reasoning-Driven Hierarchical Sampling (RHS) framework, which combines global localization of question-relevant cues with local dense sampling for precise inference. Additionally, we develop a lightweight Semantic-Guided Frame Selector to prioritize informative frames, enabling RHS to achieve comparable or superior performance with significantly fewer sampled frames. Together, our LSDBench and RHS framework address the unique challenges of high-NSD long-video tasks, setting a new standard for evaluating and improving LVLMs in this domain. Our benchmark and evaluation codes has been released at: https://github.com/dvlab-research/LSDBench","url_abs":"https://arxiv.org/abs/2503.12496v2","url_pdf":"https://arxiv.org/pdf/2503.12496v2.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":"does-your-vision-language-model-get-lost-in","repo_url":"https://github.com/dvlab-research/LSDBench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[{"slug":"lsdbench","name":"LSDBench","full_name":"Long-video Sampling Dilemma Benchmark"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.12496","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.12496"}},"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/dvlab-research/LSDBench","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/dvlabresearch/LSDBench","reach":{"status":"gone","observed_at":"2026-09-16","how":"tree_404+repo_404"}}],"summary":{"ran_honours":3,"unverified":6},"by_repo_kind":{"official":{"samples":9,"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":0,"samples":[{"code_sha256_prefix":"6e45201fa27cb24a","entry":"ceil_by_factor","repo":"dvlab-research/LSDBench","repo_kind":"official","path":"evaluation/models/vison_process.py","file_url":"https://github.com/dvlab-research/LSDBench/blob/HEAD/evaluation/models/vison_process.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6e45201fa27cb24a"}},{"code_sha256_prefix":"8155263d7ff19bb3","entry":"floor_by_factor","repo":"dvlab-research/LSDBench","repo_kind":"official","path":"evaluation/models/vison_process.py","file_url":"https://github.com/dvlab-research/LSDBench/blob/HEAD/evaluation/models/vison_process.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8155263d7ff19bb3"}},{"code_sha256_prefix":"e252767324188623","entry":"round_by_factor","repo":"dvlab-research/LSDBench","repo_kind":"official","path":"evaluation/models/vison_process.py","file_url":"https://github.com/dvlab-research/LSDBench/blob/HEAD/evaluation/models/vison_process.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e252767324188623"}},{"code_sha256_prefix":"f9f821b532a13010","entry":"extract_characters_regex","repo":"dvlab-research/LSDBench","repo_kind":"official","path":"evaluation/utils.py","file_url":"https://github.com/dvlab-research/LSDBench/blob/HEAD/evaluation/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f9f821b532a13010"}},{"code_sha256_prefix":"af2cd70eceedd1fe","entry":"get_new_height_width","repo":"dvlab-research/LSDBench","repo_kind":"official","path":"lsdbench/preprocess_videos.py","file_url":"https://github.com/dvlab-research/LSDBench/blob/HEAD/lsdbench/preprocess_videos.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"af2cd70eceedd1fe"}},{"code_sha256_prefix":"3215d04bb0514c81","entry":"handle_arg_string","repo":"dvlab-research/LSDBench","repo_kind":"official","path":"evaluation/utils.py","file_url":"https://github.com/dvlab-research/LSDBench/blob/HEAD/evaluation/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3215d04bb0514c81"}},{"code_sha256_prefix":"7ff50bed9f532d98","entry":"normalize_time_segment","repo":"dvlab-research/LSDBench","repo_kind":"official","path":"evaluation/models/model_qwen_rhs.py","file_url":"https://github.com/dvlab-research/LSDBench/blob/HEAD/evaluation/models/model_qwen_rhs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7ff50bed9f532d98"}},{"code_sha256_prefix":"5a0b9c814c13cc10","entry":"simple_parse_args_string","repo":"dvlab-research/LSDBench","repo_kind":"official","path":"evaluation/utils.py","file_url":"https://github.com/dvlab-research/LSDBench/blob/HEAD/evaluation/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5a0b9c814c13cc10"}},{"code_sha256_prefix":"1e0fdfff9d3ab61c","entry":"time_to_seconds","repo":"dvlab-research/LSDBench","repo_kind":"official","path":"evaluation/models/model_qwen_rhs.py","file_url":"https://github.com/dvlab-research/LSDBench/blob/HEAD/evaluation/models/model_qwen_rhs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1e0fdfff9d3ab61c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}