[ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about videos. It combines the capabilities of LLMs with a pretrained visual encoder adapted for spatiotemporal video representation. We also introduce a rigorous 'Quantitative Evaluation Benchmarking' for video-based conversational models.
The code uses the path Video-ChatGPT/video_chatgpt/demo/demo_sample_videos/ instead of Video-ChatGPT/video_chatgpt/demo/serve/demo_sample_videos/ written in the git readme #17
Hi @willzli
Thank you for your interest in our work and pointing out the typo. We have updated the Readme.