VLMs are evaluated on gaze following and social gaze prediction using existing datasets in zero-shot and fine-tuned settings, revealing they currently lack precise capabilities compared to visual models.
Attention flow: End-to-end joint attention estimation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Eyes on VLM: Benchmarking Gaze Following and Social Gaze Prediction in Vision Language Models
VLMs are evaluated on gaze following and social gaze prediction using existing datasets in zero-shot and fine-tuned settings, revealing they currently lack precise capabilities compared to visual models.