{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/chat-univi-unified-visual-representation","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","arxiv_id":"2311.08046","date":"2023-11-14","proceeding":"CVPR 2024 1","authors":["Peng Jin","Ryuichi Takanobu","Wancai Zhang","Xiaochun Cao","Li Yuan"],"abstract":"Large language models have demonstrated impressive universal capabilities across a wide range of open-ended tasks and have extended their utility to encompass multimodal conversations. However, existing methods encounter challenges in effectively handling both image and video understanding, particularly with limited visual tokens. In this work, we introduce Chat-UniVi, a Unified Vision-language model capable of comprehending and engaging in conversations involving images and videos through a unified visual representation. Specifically, we employ a set of dynamic visual tokens to uniformly represent images and videos. This representation framework empowers the model to efficiently utilize a limited number of visual tokens to simultaneously capture the spatial details necessary for images and the comprehensive temporal relationship required for videos. Moreover, we leverage a multi-scale representation, enabling the model to perceive both high-level semantic concepts and low-level visual details. Notably, Chat-UniVi is trained on a mixed dataset containing both images and videos, allowing direct application to tasks involving both mediums without requiring any modifications. Extensive experimental results demonstrate that Chat-UniVi consistently outperforms even existing methods exclusively designed for either images or videos. Code is available at https://github.com/PKU-YuanGroup/Chat-UniVi.","url_abs":"https://arxiv.org/abs/2311.08046v3","url_pdf":"https://arxiv.org/pdf/2311.08046v3.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":"chat-univi-unified-visual-representation","repo_url":"https://github.com/pku-yuangroup/chat-univi","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"chat-univi-unified-visual-representation","repo_url":"https://github.com/pku-yuangroup/video-bench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"chat-univi-unified-visual-representation","repo_url":"https://github.com/skyworkai/moe-plus-plus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"chat-univi-unified-visual-representation","repo_url":"https://github.com/skyworkai/moh","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Image-based Generative Performance Benchmarking"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"science-question-answering","task_name":"Science Question Answering"},{"task_slug":"vcgbench-diverse","task_name":"VCGBench-Diverse"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"video-based-generative-performance","task_name":"Video-based Generative Performance Benchmarking"},{"task_slug":"video-based-generative-performance-5","task_name":"Video-based Generative Performance Benchmarking (Consistency)"},{"task_slug":"video-based-generative-performance-3","task_name":"Video-based Generative Performance Benchmarking (Contextual Understanding)"},{"task_slug":"video-based-generative-performance-1","task_name":"Video-based Generative Performance Benchmarking (Correctness of Information)"},{"task_slug":"video-based-generative-performance","task_name":"Video-based Generative Performance Benchmarking (Correctness of Information) on VideoInstruct"},{"task_slug":"video-based-generative-performance-2","task_name":"Video-based Generative Performance Benchmarking (Detail Orientation))"},{"task_slug":"video-based-generative-performance-4","task_name":"Video-based Generative Performance Benchmarking (Temporal Understanding)"},{"task_slug":"zeroshot-video-question-answer","task_name":"Zero-Shot Video Question Answer"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/science-question-answering-on-scienceqa","task":"Science Question Answering","dataset":"ScienceQA","model":"Chat-UniVi-13B","rank_in_archive_order":5,"of":10,"metrics":{"Avg. Accuracy":"90.99","Grades 1-6":"91.19","Grades 7-12":"90.64","Image Context":"88.05","Language Science":"88.91","Natural Science":"90.41","No Context":"90.94","Social Science":"95.05","Text Context":"89.64"},"uses_additional_data":true},{"leaderboard":"/sota/vcgbench-diverse-on-videoinstruct","task":"VCGBench-Diverse","dataset":"VideoInstruct","model":"Chat-UniVi","rank_in_archive_order":2,"of":6,"metrics":{"Consistency":"2.36","Contextual Understanding":"2.66","Correctness of Information":"2.29","Dense Captioning":"1.33","Detail Orientation":"2.56","Reasoning":"3.59","Spatial Understanding":"2.36","Temporal Understanding":"1.56","mean":"2.29"},"uses_additional_data":false},{"leaderboard":"/sota/video-question-answering-on-activitynet-qa","task":"Video Question Answering","dataset":"ActivityNet-QA","model":"Chat-UniVi-13B","rank_in_archive_order":13,"of":36,"metrics":{"Accuracy":"46.4","Confidence score":"3.3"},"uses_additional_data":false},{"leaderboard":"/sota/video-based-generative-performance","task":"Video-based Generative Performance Benchmarking","dataset":"VideoInstruct","model":"Chat-UniVi","rank_in_archive_order":14,"of":23,"metrics":{"Consistency":"2.81","Contextual Understanding":"3.46","Correctness of Information":"2.89","Detail Orientation":"2.91","Temporal Understanding":"2.39","mean":"2.99"},"uses_additional_data":false},{"leaderboard":"/sota/video-based-generative-performance-2","task":"Video-based Generative Performance Benchmarking (Consistency)","dataset":"VideoInstruct","model":"Chat-UniVi","rank_in_archive_order":6,"of":18,"metrics":{"gpt-score":"2.81"},"uses_additional_data":false},{"leaderboard":"/sota/video-based-generative-performance-3","task":"Video-based Generative Performance Benchmarking (Contextual Understanding)","dataset":"VideoInstruct","model":"Chat-UniVi","rank_in_archive_order":10,"of":18,"metrics":{"gpt-score":"3.46"},"uses_additional_data":false},{"leaderboard":"/sota/video-based-generative-performance-1","task":"Video-based Generative Performance Benchmarking (Correctness of Information)","dataset":"VideoInstruct","model":"Chat-UniVi","rank_in_archive_order":10,"of":18,"metrics":{"gpt-score":"2.89"},"uses_additional_data":false},{"leaderboard":"/sota/video-based-generative-performance-4","task":"Video-based Generative Performance Benchmarking (Detail Orientation))","dataset":"VideoInstruct","model":"Chat-UniVi","rank_in_archive_order":10,"of":18,"metrics":{"gpt-score":"2.91"},"uses_additional_data":false},{"leaderboard":"/sota/video-based-generative-performance-5","task":"Video-based Generative Performance Benchmarking (Temporal Understanding)","dataset":"VideoInstruct","model":"Chat-UniVi","rank_in_archive_order":11,"of":18,"metrics":{"gpt-score":"2.39"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-activitynet","task":"Zero-Shot Video Question Answer","dataset":"ActivityNet-QA","model":"Chat-UniVi-13B","rank_in_archive_order":17,"of":28,"metrics":{"Accuracy":"46.4","Confidence Score":"3.6"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-activitynet","task":"Zero-Shot Video Question Answer","dataset":"ActivityNet-QA","model":"Chat-UniVi","rank_in_archive_order":19,"of":28,"metrics":{"Accuracy":"46.1","Confidence Score":"3.3"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-msrvtt-qa","task":"Zero-Shot Video Question Answer","dataset":"MSRVTT-QA","model":"Chat-UniVi-7B","rank_in_archive_order":22,"of":30,"metrics":{"Accuracy":"55.0","Confidence Score":"3.1"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-msvd-qa","task":"Zero-Shot Video Question Answer","dataset":"MSVD-QA","model":"Chat-UniVi-7B","rank_in_archive_order":21,"of":28,"metrics":{"Accuracy":"69.3","Confidence Score":"3.7"},"uses_additional_data":false},{"leaderboard":"/sota/zeroshot-video-question-answer-on-tgif-qa","task":"Zero-Shot Video Question Answer","dataset":"TGIF-QA","model":"Chat-UniVi-7B","rank_in_archive_order":10,"of":14,"metrics":{"Accuracy":"69.0","Confidence Score":"3.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.08046","atlas_url":"https://app.syntology.ai/?focus=2311.08046","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2311.08046"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2311.08046\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2311.08046"},"call":"get_concepts_for_paper(arxiv_id=\"2311.08046\")"}],"by_repo":[{"repo":"pku-yuangroup/chat-univi","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2410.11842","Jin_Chat-UniVi_Unified_Visual_Representation_Empowers_Large_Language_Models_with_Image_CVPR_2024_paper"],"harvested_for_calls":[{"arxiv_id":"2410.11842","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.11842"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.11842\")"}]},{"repo":"pku-yuangroup/video-bench","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"skyworkai/moe-plus-plus","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2410.11842"],"harvested_for_calls":[{"arxiv_id":"2410.11842","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.11842"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.11842\")"}]},{"repo":"skyworkai/moh","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2410.11842"],"harvested_for_calls":[{"arxiv_id":"2410.11842","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.11842"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.11842\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b371d8999bfdce2402663cf872da58dc11dc54ce0c20bac9d31137e39602d8a0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}