Gazeformer: Scalable, effective and fast prediction of goal-directed human attention

S Mondal, Z Yang, S Ahn, D Samaras… - Proceedings of the …, 2023 - openaccess.thecvf.com
Predicting human gaze is important in Human-Computer Interaction (HCI). However, to
practically serve HCI applications, gaze prediction models must be scalable, fast, and …

Target-absent human attention

Z Yang, S Mondal, S Ahn, G Zelinsky, M Hoai… - … on Computer Vision, 2022 - Springer
The prediction of human gaze behavior is important for building human-computer interaction
systems that can anticipate the user's attention. Computer vision models have been …

Visual Scanpath transformer: guiding computers to see the world

M Qiu, Q Rong, D Liang, H Tu - 2023 IEEE International …, 2023 - ieeexplore.ieee.org
We propose to exploit the scanpath prediction technology to simulate human visual system
to automatically generate gaze scanpaths for VR/AR applications, to alleviate the equipment …

Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers

Z Yang, S Mondal, S Ahn, R Xue… - Proceedings of the …, 2024 - openaccess.thecvf.com
Most models of visual attention aim at predicting either top-down or bottom-up control as
studied using different visual search and free-viewing tasks. In this paper we propose the …

Gaze Scanpath Transformer: Predicting Visual Search Target by Spatiotemporal Semantic Modeling of Gaze Scanpath

T Nishiyasu, Y Sato - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
We introduce a new method called the Gaze Scanpath Transformer for predicting a search
target category during a visual search task. Previous methods for estimating visual search …

UniAR: Unifying Human Attention and Response Prediction on Visual Content

P Li, J He, G Li, R Bhargava, S Shen… - arXiv preprint arXiv …, 2023 - arxiv.org
Progress in human behavior modeling involves understanding both implicit, early-stage
perceptual behavior such as human attention and explicit, later-stage behavior such as …

Predicting human attention using computational attention

Z Yang, S Mondal, S Ahn, G Zelinsky, M Hoai… - arXiv preprint arXiv …, 2023 - arxiv.org
Most models of visual attention are aimed at predicting either top-down or bottom-up control,
as studied using different visual search and free-viewing tasks. We propose Human …

Reconstructing the Objects of Attention

S Ahn - 2023 - search.proquest.com
Humans can dream and imagine things. These quintessentially human capabilities require
the brain to generate percepts. I propose that our generation capabilities likely evolved, not …

[PDF][PDF] Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers Supplementary Material

Z Yang, S Mondal, S Ahn, R Xue, G Zelinsky, M Hoai… - openaccess.thecvf.com
To further validate the effectiveness of our proposed HAT in free-viewing scanpath
prediction, we compare HAT to the previous state-of-the-art method in free-viewing scanpath …