google-deepmind/tapnet
Tracks any point in a video
View on index · View in 3D Map
Related repos
- Infrastructure for building video analytics pipelines
- Video embeddings for search and classification
- AI vision for camera streams
- connects images and text for zero-shot predictions
- Trains agents to act from videos
- Video models like SlowFast help computers spot actions and understand what’s happening in videos by combining slow and fast motion cues
- open suite of AI video foundation models for text-to-video, image-to-video, video editing, text-to-image, and video-to-audio tasks
- video and image watermarking code for training and inference
- Workflow for building apps with AI assistance
- turn a photo and audio into a talking video with AI
