[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.
I downloaded the dataset through the link of MBZuAIAC at a very slow speed (1M/s). Could you upload the dataset to Google Cloud Drive or Hugging Face please ? (including videos of activitynet)
mmaaz60
commented
6 months ago
I downloaded the dataset through the link of MBZuAIAC at a very slow speed (1M/s). Could you upload the dataset to Google Cloud Drive or Hugging Face please ? (including videos of activitynet)