DAMO-NLP-SG / VideoLLaMA2

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
Apache License 2.0
752 stars 50 forks source link

Datasets download for MSVC #53

Closed 1xbq1 closed 2 months ago

1xbq1 commented 2 months ago

Don't seem to see the download link for the MSVC benchmark dataset? Where can I download it?

lixin4ever commented 2 months ago

The annotation file for our MSVC benchmark is available at: https://huggingface.co/datasets/DAMO-NLP-SG/Multi-Source-Video-Captioning. For the raw videos, you need to download them manually according to the provided video ids.

1xbq1 commented 2 months ago

Ok, thanks.