AI RESEARCH

Internalizing Temporal Consistency in Video Object-Centric Learning without Explicit Regularization

arXiv CS.CV

ArXi:2605.31508v1 Announce Type: new Video Object-Centric Learning (OCL) aims to represent objects as \textit{slot} vectors and maintain their consistency across frames. Slot-Slot Contrastive (SSC) loss has become the cornerstone for state-of-the-art (SOTA) video OCL methods. While highly effective, SSC relies on one-to-one object correspondence across frames and