HKUDS/VideoRAG
Retrieves information from videos through natural language conversations
View on index · View in 3D Map
Related repos
- Framework for video understanding and generation
- Generates multi-person talking videos from audio
- Agentic video generation through scriptwriting and storyboarding
- Downloads videos from platforms using Python
- Generates short videos from text scripts
- Library for video understanding research
- Analyzes videos using vision models and Whisper
- browser-based video calls app built on Mediasoup
- Multimodal foundation models for video understanding
