[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.
Is it possible to get the video frame timestamp in your approach? I do not see you are extracting time info while dataset creation so I am guessing no.
Is it possible to get the video frame timestamp in your approach? I do not see you are extracting time info while dataset creation so I am guessing no.
Please suggest.