AI RESEARCH
Towards Mitigating Modality Bias in Vision-Language Models for Temporal Action Localization
arXiv CS.CV
•
ArXi:2601.21078v2 Announce Type: replace Temporal Action Localization (TAL) requires identifying both the boundaries and categories of actions in untrimmed videos. While vision-language models (VLMs) offer rich semantics to complement visual evidence, existing approaches tend to overemphasize linguistic priors at the expense of visual performance, leading to a pronounced modality bias. We propose ActionVLM, a vision-language aggregation framework that systematically mitigates modality bias in.