VideoLLaMA2
🎥
160
Media understanding
VideoLLaMA2
Optimized VideoLLaMA with improved spatial-temporal modeling and better audio understanding capability
-
-
VideoLLaMA2 AV
🚀17VideoLLaMA2-AV
-
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
Paper • 2406.07476 • Published • 37 -
DAMO-NLP-SG/VideoLLaMA2.1-7B-16F
Video-Text-to-Text • 8B • Updated • 5.52k • 9 -
DAMO-NLP-SG/VideoLLaMA2.1-7B-AV
Visual Question Answering • 9B • Updated • 2.43k • 16 -
DAMO-NLP-SG/VideoLLaMA2-7B
Visual Question Answering • 8B • Updated • 324 • 40 -
DAMO-NLP-SG/VideoLLaMA2-7B-16F
Visual Question Answering • 8B • Updated • 123 • 14 -
DAMO-NLP-SG/VideoLLaMA2-72B
Visual Question Answering • 75B • Updated • 17 • 10 -
DAMO-NLP-SG/VideoLLaMA2-72B-Base
Visual Question Answering • Updated • 6 • 1 -
DAMO-NLP-SG/VideoLLaMA2-7B-Base
Visual Question Answering • Updated • 18 • 5 -
DAMO-NLP-SG/VideoLLaMA2-7B-16F-Base
Visual Question Answering • Updated • 8 • 2 -
DAMO-NLP-SG/VideoLLaMA2.1-7B-16F-Base
Visual Question Answering • Updated • 10 • 1 -
DAMO-NLP-SG/Multi-Source-Video-Captioning
Viewer • Updated • 1.5k • 108 • 7