Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models
This work addresses the under-explored field of video-based conversation for users needing detailed video analysis, though it is incremental as it builds on existing image-based models.
The paper tackles the problem of video-based conversation by introducing Video-ChatGPT, a multimodal model that merges a video-adapted visual encoder with a large language model, enabling detailed video understanding and conversation generation, and it includes a new dataset of 100,000 video-instruction pairs and a quantitative evaluation framework.
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.