Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding
This work addresses the problem of multimodal AI systems struggling with unified image and video processing for applications in conversational AI, though it appears incremental as it builds on existing vision-language models.
The authors tackled the challenge of enabling large language models to effectively handle both image and video understanding with limited visual tokens by introducing Chat-UniVi, a unified vision-language model that uses dynamic visual tokens and multi-scale representation, achieving consistent outperformance over existing methods designed for either images or videos.
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.