Call for Papers
Visual attention refers to the human ability to focus on the most relevant parts of a visual scene (e.g. images or videos). Over the past decades, it has been extensively studied, leading to the proposal of numerous computational models aimed at predicting attention allocation on visual stimuli. While these models were initially developed in the field of psychology and neuroscience, the computer vision and pattern recognition community has become increasingly interested in this problem. This interest has been driven by the growing number of potential applications such as image/video compression, autonomous driving, and robotics.
The workshop will investigate a range of topics covering (but not limited to) the following:
Computational models of visual attention
Scanpath prediction models on images or videos
Active vision and its applications
(Deep) visual saliency models and their applications
Eye-tracking technology and its applications
Human visual perception and its implications for computer vision
Benchmarking and evaluation of visual attention and gaze analysis models
Applications of visual attention and gaze analysis in image and video processing, robotics, and human-computer interaction
Eye-gaze models for biometrics, health, driving, virtual reality, education and social sciences.
The workshop aims to bring together researchers and practitioners in the field of computer vision and image processing to exchange ideas and discuss recent advances in visual attention, gaze analysis and modelling, visual saliency, active vision, and deep saliency models. The workshop will provide a platform for researchers to present their work, share experiences, and discuss the challenges and opportunities in the field.