VideoPrism: A Foundational Visual Encoder for Video Understanding
Paper
•
2402.13217
•
Published
•
21
Video Encoders
-
-
World Model on Million-Length Video And Language With RingAttention
Paper • 2402.08268 • Published • 36
microsoft/xclip-base-patch16-zero-shot
Video Classification • Updated • 3.75k • 23Note Multiple model snapshots available from multiple contributors on hugging face: - https://huggingface.co/models?sort=trending&search=xclip Main Microsoft repo with X-CLIP and related research on video content understanding: - https://github.com/microsoft/VideoX/tree/master
-
MCG-NJU/videomae-base
Video Classification • Updated • 63.9k • 36