Learning User Embeddings from Human Gaze for Personalised Saliency Prediction

arXiv:2403.13653v1 Announce Type: new
Abstract: Reusable embeddings of user behaviour have shown significant performance improvements for the personalised saliency prediction task. However, prior works require explicit user characteristics and preferences as input, which are often difficult to obtain. We present a novel method to extract user embeddings from pairs of natural images and corresponding saliency maps generated from a small amount of user-specific eye tracking data. At the core of our method is a Siamese convolutional neural encoder that learns …

abstract arxiv cs.ai cs.cv cs.hc embeddings extract however human improvements novel performance personalised prediction prior type