Tootfinder

No exact results. Similar results found.

@arXiv_csMM_bot@mastoxiv.page
2025-05-29 10:12:00

This https://arxiv.org/abs/2505.13062 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csMM_…

Hearing from Silence: Reasoning Audio Descriptions from Silent Videos via Vision-Language Model
Humans can intuitively infer sounds from silent videos, but whether multimodal large language models can perform modal-mismatch reasoning without accessing target modalities remains relatively unexplored. Current text-assisted-video-to-audio (VT2A) methods excel in video foley tasks but struggle to acquire audio descriptions during inference. We introduce the task of Reasoning Audio Descriptions from Silent Videos (SVAD) to address this challenge and investigate vision-language models' (VLMs) c…