V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mur-Labadia, Lorenzo, Muckley, Matthew, Bar, Amir, Assran, Mido, Sinha, Koustuv, Rabbat, Mike, LeCun, Yann, Ballas, Nicolas, Bardes, Adrien
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.14482