Beyond Average: Individualized Visual Scanpath Prediction

arXiv:2404.12235v1 Announce Type: new
Abstract: Understanding how attention varies across individuals has significant scientific and societal impacts. However, existing visual scanpath models treat attention uniformly, neglecting individual differences. To bridge this gap, this paper focuses on individualized scanpath prediction (ISP), a new attention modeling task that aims to accurately predict how different individuals shift their attention in diverse visual tasks. It proposes an ISP method featuring three novel technical components: (1) an observer encoder to characterize and integrate an observer's …

abstract arxiv attention beyond bridge cs.cv differences gap however impacts modeling paper prediction scientific shift type understanding visual