{"work":{"id":"51f627f4-8fae-4882-a3e9-abdf932ef27b","openalex_id":"https://openalex.org/W4380137126","doi":"10.48550/arxiv.2306.05424","arxiv_id":"2306.05424","raw_key":null,"title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","authors":null,"authors_text":"Muhammad Maaz, Hanoona Rasheed, Salman Khan, Fahad Shahbaz Khan","year":2023,"venue":"cs.CV","abstract":"Conversation agents fueled by Large Language Models (LLMs) are providing a new way to interact with visual data. While there have been initial attempts for image-based conversation models, this work addresses the under-explored field of \\emph{video-based conversation} by introducing Video-ChatGPT. It is a multimodal model that merges a video-adapted visual encoder with an LLM. The resulting model is capable of understanding and generating detailed conversations about videos. We introduce a new dataset of 100,000 video-instruction pairs used to train Video-ChatGPT acquired via manual and semi-automated pipeline that is easily scalable and robust to label noise. We also develop a quantitative evaluation framework for video-based dialogue models to objectively analyze the strengths and weaknesses of video-based dialogue models. Code: https://github.com/mbzuai-oryx/Video-ChatGPT.","external_url":"https://arxiv.org/abs/2306.05424","cited_by_count":16,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2306.05424","created_at":"2026-05-09T05:55:31.723872+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","render_title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models"},"hub":{"state":{"work_id":"51f627f4-8fae-4882-a3e9-abdf932ef27b","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":73,"external_cited_by_count":16,"distinct_field_count":8,"first_pith_cited_at":"2023-05-05T17:59:46+00:00","last_pith_cited_at":"2026-07-01T12:32:29+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T09:29:25.298636+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":11},{"context_role":"baseline","n":3},{"context_role":"dataset","n":3},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":11},{"context_polarity":"baseline","n":3},{"context_polarity":"use_dataset","n":3},{"context_polarity":"use_method","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}