conftrace_

action-scene hallucination

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

disentangled spatial temporal representation (1) masked attention mechanism (1) video large language model (1) spatial-temporal representation (1) masked attention (1) rotary position embedding (1) hallucination mitigation (1) video understanding (1)

Papers

MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations CVPR 2025