VideoLLaMA2
🎥
162
Media understanding
VideoLLaMA2
Optimized VideoLLaMA with improved spatial-temporal modeling and better audio understanding capability
-
-
VideoLLaMA2 AV
🚀16VideoLLaMA2-AV
-
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
Paper • 2406.07476 • Published • 36 -
DAMO-NLP-SG/VideoLLaMA2.1-7B-16F
Video-Text-to-Text • 8B • Updated • 2.83k • 10 -
DAMO-NLP-SG/VideoLLaMA2.1-7B-AV
Visual Question Answering • 9B • Updated • 3.19k • 16 -
DAMO-NLP-SG/VideoLLaMA2-7B
Visual Question Answering • 8B • Updated • 832 • 42 -
DAMO-NLP-SG/VideoLLaMA2-7B-16F
Visual Question Answering • 8B • Updated • 55 • 14 -
DAMO-NLP-SG/VideoLLaMA2-72B
Visual Question Answering • 75B • Updated • 14 • 10 -
DAMO-NLP-SG/VideoLLaMA2-72B-Base
Visual Question Answering • Updated • 2 • 1 -
DAMO-NLP-SG/VideoLLaMA2-7B-Base
Visual Question Answering • Updated • 9 • 6 -
DAMO-NLP-SG/VideoLLaMA2-7B-16F-Base
Visual Question Answering • Updated • 3 • 2 -
DAMO-NLP-SG/VideoLLaMA2.1-7B-16F-Base
Visual Question Answering • Updated • 5 • 1 -
DAMO-NLP-SG/Multi-Source-Video-Captioning
Viewer • Updated • 1.5k • 40 • 7