作者位次 #5/10ACL 2026Findings· Findings of ACL
Vision-Language Models Mistake Head Orientation for Gaze Direction: Nonverbal Conversation Cues
Zory Zhang · Pinyuan Feng · Bingyang Wang · Tianwei Zhao · Suyang Yu · Qingying Gao · Hokin Deng · Ziqiao Ma · Yijiang Li · Dezhi Luo
摘要
Where someone looks is a nonverbal communication cue that children and adults readily use.How well can Vision-Language Models (VLMs) infer gaze targets? To construct evaluation stimuli, we captured 1,360 real-world photos of scenes in which a person gazes at one of several objects on a table. Imp...