Temporal Self-Distillation: Learning Visual State Tracking in Videos Without Supervision

Paper recorded by Signals 4 on 2026-09-03 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-03 on arXiv · recorded by Signals 4 on 2026-09-04

Category: cs.CV · 计算机视觉 · first seen 2026-09-04

Abstract

We introduce S$^3$T (Self-Supervised Self-Distillation over Time), which, to the best of our knowledge, is the first fully self-contained framework for continuous video state tracking. Our method treats temporal sampling density as privileged information, based on the hypothesis that a denser view of the same clip recovers the running state more accurately. This view serves as the teacher, while a

Read on arXiv →