Vjepa 21 Unlocking Dense Features In Video Selfsupervised Learning
1 mentions across 1 person
Visit ↗All mentions
“We present V-JEPA 2.1, a family of self-supervised models that learn dense, high-quality visual representations for both images and videos while retaining strong global scene understanding.”
V-JEPA 2.1: Advancing Dense Vision and World Modeling through Self-Supervised Le ↗