AI RESEARCH
CAST: Modeling Visual State Transitions for Consistent Video Retrieval
arXiv CS.CV
•
ArXi:2603.08648v1 Announce Type: new As video content creation shifts toward long-form narratives, composing short clips into coherent storylines becomes increasingly important. However, prevailing retrieval formulations remain context-agnostic at inference time, prioritizing local semantic alignment while neglecting state and identity consistency. To address this structural limitation, we formalize the task of Consistent Video Retrieval (CVR) and