VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
Paper • 2607.14935 • Published • 172
VideoChat3
-
-
MCG-NJU/I3D-ViT
Image Feature Extraction • 0.4B • Updated • 10.7k • 12 -
MCG-NJU/VideoChat3-4B
Video-Text-to-Text • 4B • Updated • 4.01k • 23 -
MCG-NJU/VideoChat3-LV116k
Viewer • Updated • 8.07k • 80.2k • 15 -
MCG-NJU/VideoChat3-Academic2M
Viewer • Updated • 19.2k • 6.11k • 23 -
MCG-NJU/VideoChat3-OL617k
Preview • Updated • 1.48k • 12 -
lmwang/VideoChat3-Stage3-Training-Data
Preview • Updated • 4.94k • 5 -
MCG-NJU/VideoChat3-4B-Stage1
4B • Updated • 21 • 2 -
MCG-NJU/VideoChat3-4B-Stage2
4B • Updated • 23 • 2 -
MCG-NJU/VideoChat3-Training-Data-Annotations
Updated • 1.99k • 2