Paper recorded by Signals 4 on 2026-09-01 in cs.CV. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-01 on arXiv · recorded by Signals 4 on 2026-09-02
Category: cs.CV · 计算机视觉 · first seen 2026-09-02
Self-supervised video foundation models learn rich spatiotemporal representations, yet it remains unclear what visual concepts these representations encode, where they emerge across transformer layers, and how they are geometrically organized. In this work, we tackle these three questions through a systematic layer-wise analysis of V-JEPA 2 and VideoMAE-v2. We leverage lightweight probes trained t