An Inter-observer consistent deep adversarial training for visual scanpath prediction
This work addresses the challenge of predicting human visual attention patterns, which is important for applications in computer vision and human-computer interaction, but it appears incremental as it builds on existing adversarial methods.
The paper tackled the problem of predicting visual scanpaths, which are sequences of gaze points, by proposing an inter-observer consistent adversarial training approach with a lightweight deep neural network. The result showed competitiveness with state-of-the-art methods, though no concrete numbers were provided.
The visual scanpath is a sequence of points through which the human gaze moves while exploring a scene. It represents the fundamental concepts upon which visual attention research is based. As a result, the ability to predict them has emerged as an important task in recent years. In this paper, we propose an inter-observer consistent adversarial training approach for scanpath prediction through a lightweight deep neural network. The adversarial method employs a discriminative neural network as a dynamic loss that is better suited to model the natural stochastic phenomenon while maintaining consistency between the distributions related to the subjective nature of scanpaths traversed by different observers. Through extensive testing, we show the competitiveness of our approach in regard to state-of-the-art methods.