Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
OACap: Caption-Guided Active Observation for Detailed Video Captioning
Hao Shi, Hong Yan, Xiaoyang Zhang +3
Unlike question answering, where a query specifies a perceptual target, open-ended detailed captioning must determine what evidence to acquire and how to integrate it into a cohere…
cs.CV2026
ZoomCap: Evidence-Routed Visual Zooming for Recoverable Visual Information Transfer
Hao Shi, Jiafeng Wang, Yuzhuo Fu +5
Detailed captions transfer visual information into vision-language model supervision, but quality is easily conflated with length: long single-pass outputs still miss small objects…