{"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/svbench-a-benchmark-with-temporal-multi-turn","title":"SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding","arxiv_id":"2502.10810","date":"2025-02-15","proceeding":null,"authors":["Zhenyu Yang","Yuhang Hu","Zemin Du","Dizhan Xue","Shengsheng Qian","JiaHong Wu","Fan Yang","WeiMing Dong","Changsheng Xu"],"abstract":"Despite the significant advancements of Large Vision-Language Models (LVLMs) on established benchmarks, there remains a notable gap in suitable evaluation regarding their applicability in the emerging domain of long-context streaming video understanding. Current benchmarks for video understanding typically emphasize isolated single-instance text inputs and fail to evaluate the capacity to sustain temporal reasoning throughout the entire duration of video streams. To address these limitations, we introduce SVBench, a pioneering benchmark with temporal multi-turn question-answering chains specifically designed to thoroughly assess the capabilities of streaming video understanding of current LVLMs. We design a semi-automated annotation pipeline to obtain 49,979 Question-Answer (QA) pairs of 1,353 streaming videos, which includes generating QA chains that represent a series of consecutive multi-turn dialogues over video segments and constructing temporal linkages between successive QA chains. Our experimental results, obtained from 14 models in dialogue and streaming evaluations, reveal that while the closed-source GPT-4o outperforms others, most open-source LVLMs struggle with long-context streaming video understanding. We also construct a StreamingChat model, which significantly outperforms open-source LVLMs on our SVBench and achieves comparable performance on diverse vision-language benchmarks. We expect SVBench to advance the research of streaming video understanding by providing a comprehensive and in-depth analysis of current LVLMs. Our benchmark and model can be accessed at https://yzy-bupt.github.io/SVBench.","url_abs":"https://arxiv.org/abs/2502.10810v1","url_pdf":"https://arxiv.org/pdf/2502.10810v1.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":"svbench-a-benchmark-with-temporal-multi-turn","repo_url":"https://github.com/yzy-bupt/SVBench","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"streaming-video-understanding","task_name":"Streaming video understanding"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[{"method_slug":"streaming-module","method_name":"Streaming Module"}],"datasets_introduced":[{"slug":"svbench","name":"SVBench","full_name":"Streaming Video Understanding Benchmark"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.10810","atlas_url":"https://app.syntology.ai/?focus=2502.10810","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.10810"}},"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":"deterministic:regex_extraction","url":"https://github.com/sotayang/SVBench","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/yzy-bupt/SVBench","reach":{"status":"ok"}}],"summary":{"ran_violates":1,"ran":1,"unverified":1},"by_repo_kind":{"found_in_text":{"samples":3,"ran":2,"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":"5f3bdd5f3304a0e0","entry":"version_cmp","repo":"sotayang/svbench","repo_kind":"found_in_text","path":"StreamingChat/streamingchat/model/internvl_chat/modeling_internvl_chat.py","file_url":"https://github.com/sotayang/svbench/blob/HEAD/StreamingChat/streamingchat/model/internvl_chat/modeling_internvl_chat.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5f3bdd5f3304a0e0"}},{"code_sha256_prefix":"0ffff8689a554ffd","entry":"Conversation","repo":"sotayang/SVBench","repo_kind":"found_in_text","path":"StreamingChat/streamingchat/conversation.py","file_url":"https://github.com/sotayang/SVBench/blob/HEAD/StreamingChat/streamingchat/conversation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0ffff8689a554ffd"}},{"code_sha256_prefix":"a9d852824f085e6f","entry":"SeparatorStyle","repo":"sotayang/SVBench","repo_kind":"found_in_text","path":"StreamingChat/streamingchat/conversation.py","file_url":"https://github.com/sotayang/SVBench/blob/HEAD/StreamingChat/streamingchat/conversation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a9d852824f085e6f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}