ScanDiff generates diverse, text-conditioned gaze scanpaths with a diffusion-ViT architecture and reports state-of-the-art results on three benchmarks.
Active Vision
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Modeling Human Gaze Behavior with Diffusion Models for Unified Scanpath Prediction
ScanDiff generates diverse, text-conditioned gaze scanpaths with a diffusion-ViT architecture and reports state-of-the-art results on three benchmarks.