Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction

Huiwon Jang, Sihyun Yu, Jinwoo Shin, Pieter Abbeel, Younggyo Seo. Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2025, Nashville, TN, USA, June 11-15, 2025. pages 22853-22863, Computer Vision Foundation / IEEE, 2025. [doi]

Abstract

Abstract is missing.