TrackTok: Object-Centric Video Tokenization with Semantically Persistent Tokens
Paper • 2610.33857 • Published • 5
Chen
Xinyaaa
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 hours ago
TrackTok: Object-Centric Video Tokenization with Semantically Persistent Tokens upvoted a paper 2 months ago
SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models upvoted a paper over 1 year ago
KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing ModelsOrganizations
None yet