AI RESEARCH

SlotVTG: Object-Centric Adapter for Generalizable Video Temporal Grounding

arXiv CS.CV

ArXi:2603.25733v1 Announce Type: new Multimodal Large Language Models (MLLMs) have shown strong performance on Video Temporal Grounding (VTG). However, their coarse recognition capabilities are insufficient for fine-grained temporal understanding, making task-specific fine-tuning indispensable. This fine-tuning causes models to memorize dataset-specific shortcuts rather than faithfully grounding in the actual visual content, leading to poor Out-of-Domain (OOD) generalization.