Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Eyes on VLM: Benchmarking Gaze Following and Social Gaze Prediction in Vision Language Models
Hengfei Wang, Anshul Gupta, Pierre Vuillecard +1
Vision-language models (VLMs) have rapidly evolved into general-purpose multimodal reasoners with strong zero-shot generalization. In this context, VLMs could greatly benefit the a…
cs.CV2024
Exploring the Zero-Shot Capabilities of Vision-Language Models for Improving Gaze Following
Anshul Gupta, Pierre Vuillecard, Arya Farkhondeh +1
Contextual cues related to a person's pose and interactions with objects and other people in the scene can provide valuable information for gaze following. While existing methods h…