Video Captioning in Low-Light Conditions through Efficient Uncertainty-Aware Caption Correction
arXiv:2609.31697v1 Announce Type: new Abstract: Low-light conditions can significantly degrade the ability of vision-language models (VLMs) to accurately describe human actions in videos. In this work, I propose an efficient uncertainty-aware representation correction framework for improving captio…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-09-29 04:00 · arXiv cs.CV
Video Captioning in Low-Light Conditions through Efficient Uncertainty-Aware Caption Correction