{"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/timechat-a-time-sensitive-multimodal-large","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","arxiv_id":"2312.02051","date":"2023-12-04","proceeding":"CVPR 2024 1","authors":["Shuhuai Ren","Linli Yao","Shicheng Li","Xu sun","Lu Hou"],"abstract":"This work proposes TimeChat, a time-sensitive multimodal large language model specifically designed for long video understanding. Our model incorporates two key architectural contributions: (1) a timestamp-aware frame encoder that binds visual content with the timestamp of each frame, and (2) a sliding video Q-Former that produces a video token sequence of varying lengths to accommodate videos of various durations. Additionally, we construct an instruction-tuning dataset, encompassing 6 tasks and a total of 125K instances, to further enhance TimeChat's instruction-following performance. Experiment results across various video understanding tasks, such as dense captioning, temporal grounding, and highlight detection, demonstrate TimeChat's strong zero-shot temporal localization and reasoning capabilities. For example, it achieves +9.2 F1 score and +2.8 CIDEr on YouCook2, +5.8 HIT@1 on QVHighlights, and +27.5 R@1 (IoU=0.5) on Charades-STA, compared to state-of-the-art video large language models, holding the potential to serve as a versatile video assistant for long-form video comprehension tasks and satisfy realistic user requirements.","url_abs":"https://arxiv.org/abs/2312.02051v2","url_pdf":"https://arxiv.org/pdf/2312.02051v2.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":"timechat-a-time-sensitive-multimodal-large","repo_url":"https://github.com/renshuhuai-andy/timechat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"timechat-a-time-sensitive-multimodal-large","repo_url":"https://github.com/lntzm/cvpr24track-longvideo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"dense-captioning","task_name":"Dense Captioning"},{"task_slug":"highlight-detection","task_name":"Highlight Detection"},{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"multimodal-large-language-model","task_name":"Multimodal Large Language Model"},{"task_slug":"temporal-localization","task_name":"Temporal Localization"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"video-text-retrieval","task_name":"Video-Text Retrieval"},{"task_slug":"zeroshot-video-question-answer","task_name":"Zero-Shot Video Question Answer"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-question-answering-on-mvbench","task":"Video Question Answering","dataset":"MVBench","model":"TimeChat","rank_in_archive_order":16,"of":22,"metrics":{"Avg.":"38.5"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-ovbench","task":"Video Question Answering","dataset":"OVBench","model":"TimeChat (7B)","rank_in_archive_order":15,"of":16,"metrics":{"AVG":"12.8"},"uses_additional_data":false},{"leaderboard":"/sota/video-text-retrieval-on-test-of-time","task":"Video-Text Retrieval","dataset":"Test-of-Time","model":"Time-Chat","rank_in_archive_order":2,"of":4,"metrics":{"2-Class Accuracy":"76.67"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-video-question-answer-on-egoschema-1","task":"Zero-Shot Video Question Answer","dataset":"EgoSchema (fullset)","model":"TimeChat (7B)","rank_in_archive_order":24,"of":29,"metrics":{"Accuracy":"33.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.02051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02051"}},"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/renshuhuai-andy/timechat","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lntzm/cvpr24track-longvideo","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran_fixture":1,"ran_violates":1,"ran":4,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"listed":{"samples":11,"ran":7,"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":"d61c483a3c2b3156","entry":"apply_rotary_pos_emb","repo":"lntzm/cvpr24track-longvideo","repo_kind":"listed","path":"timechat/models/modeling_llama.py","file_url":"https://github.com/lntzm/cvpr24track-longvideo/blob/HEAD/timechat/models/modeling_llama.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d61c483a3c2b3156"}},{"code_sha256_prefix":"4cb732f513d69dfd","entry":"disabled_train","repo":"lntzm/cvpr24track-longvideo","repo_kind":"listed","path":"timechat/models/blip2.py","file_url":"https://github.com/lntzm/cvpr24track-longvideo/blob/HEAD/timechat/models/blip2.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"4cb732f513d69dfd"}},{"code_sha256_prefix":"741e5b0b3aa32a32","entry":"load_data","repo":"lntzm/cvpr24track-longvideo","repo_kind":"listed","path":"evaluate.py","file_url":"https://github.com/lntzm/cvpr24track-longvideo/blob/HEAD/evaluate.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"741e5b0b3aa32a32"}},{"code_sha256_prefix":"d650b26a59df9e29","entry":"merge_seg_caps","repo":"lntzm/cvpr24track-longvideo","repo_kind":"listed","path":"evaluate.py","file_url":"https://github.com/lntzm/cvpr24track-longvideo/blob/HEAD/evaluate.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"d650b26a59df9e29"}},{"code_sha256_prefix":"e49f0cf401af904b","entry":"read_txt","repo":"lntzm/cvpr24track-longvideo","repo_kind":"listed","path":"evaluate.py","file_url":"https://github.com/lntzm/cvpr24track-longvideo/blob/HEAD/evaluate.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e49f0cf401af904b"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"lntzm/cvpr24track-longvideo","repo_kind":"listed","path":"timechat/models/modeling_llama.py","file_url":"https://github.com/lntzm/cvpr24track-longvideo/blob/HEAD/timechat/models/modeling_llama.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b99eea6376d1e212"}},{"code_sha256_prefix":"cb33571427334815","entry":"tile","repo":"lntzm/cvpr24track-longvideo","repo_kind":"listed","path":"timechat/models/base_model.py","file_url":"https://github.com/lntzm/cvpr24track-longvideo/blob/HEAD/timechat/models/base_model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"cb33571427334815"}},{"code_sha256_prefix":"0ec9fc2025c16f65","entry":"all_gather_with_grad","repo":"lntzm/cvpr24track-longvideo","repo_kind":"listed","path":"timechat/models/base_model.py","file_url":"https://github.com/lntzm/cvpr24track-longvideo/blob/HEAD/timechat/models/base_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"0ec9fc2025c16f65"}},{"code_sha256_prefix":"f9970c764c5e259d","entry":"check_ans","repo":"lntzm/cvpr24track-longvideo","repo_kind":"listed","path":"benchmark/evaluate_mvbench.py","file_url":"https://github.com/lntzm/cvpr24track-longvideo/blob/HEAD/benchmark/evaluate_mvbench.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"f9970c764c5e259d"}},{"code_sha256_prefix":"8c3317746d989d00","entry":"extract_answer","repo":"lntzm/cvpr24track-longvideo","repo_kind":"listed","path":"benchmark/evaluate_egoschema.py","file_url":"https://github.com/lntzm/cvpr24track-longvideo/blob/HEAD/benchmark/evaluate_egoschema.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"8c3317746d989d00"}},{"code_sha256_prefix":"71a5b262cd33e2d0","entry":"prepare_input_output_pairs","repo":"lntzm/cvpr24track-longvideo","repo_kind":"listed","path":"utils/compress_video_data.py","file_url":"https://github.com/lntzm/cvpr24track-longvideo/blob/HEAD/utils/compress_video_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"71a5b262cd33e2d0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}