In this paper, we initiate an attempt of developing an end-to-end chat-centric video understanding system, coined as VideoChat. It integrates video foundation models and large language models via a learnable neural interface, excelling in spatiotemporal reasoning, event localization, and causal relationship inference. To instructively tune this system, we build a video-centric instruction dataset, composed of thousands of videos associated with detailed descriptions and conversations. This dataset emphasizes spatiotemporal reasoning and captures causal relationships, providing a valuable asset for training our chat-centric video understanding system. Preliminary qualitative experiments demonstrate the potential of our system across a broad spectrum of video applications, which could serve as a simple prototype system for future research on chat-centric video understanding. Access our code and data at https://github.com/OpenGVLab/Ask-Anything
@article{arxiv.2305.06355,
title = {VideoChat: Chat-Centric Video Understanding},
author = {KunChang Li and Yinan He and Yi Wang and Yizhuo Li and Wenhai Wang and Ping Luo and Yali Wang and Limin Wang and Yu Qiao},
journal= {arXiv preprint arXiv:2305.06355},
year = {2024}
}