Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Mondal, Sounak"'
Autor:
Mondal, Sounak, Ahn, Seoyoung, Yang, Zhibo, Balasubramanian, Niranjan, Samaras, Dimitris, Zelinsky, Gregory, Hoai, Minh
For computer systems to effectively interact with humans using spoken language, they need to understand how the words being generated affect the users' moment-by-moment attention. Our study focuses on the incremental prediction of attention as a pers
Externí odkaz:
http://arxiv.org/abs/2407.19605
Autor:
Miao, Qiaomu, Graikos, Alexandros, Zhang, Jingwei, Mondal, Sounak, Hoai, Minh, Samaras, Dimitris
Training gaze following models requires a large number of images with gaze target coordinates annotated by human annotators, which is a laborious and inherently ambiguous process. We propose the first semi-supervised method for gaze following by intr
Externí odkaz:
http://arxiv.org/abs/2406.02774
Predicting human gaze is important in Human-Computer Interaction (HCI). However, to practically serve HCI applications, gaze prediction models must be scalable, fast, and accurate in their spatial and temporal gaze predictions. Recent scanpath predic
Externí odkaz:
http://arxiv.org/abs/2303.15274
Autor:
Yang, Zhibo, Mondal, Sounak, Ahn, Seoyoung, Xue, Ruoyu, Zelinsky, Gregory, Hoai, Minh, Samaras, Dimitris
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 Human Attention Transformer (HAT), a single model that predicts both
Externí odkaz:
http://arxiv.org/abs/2303.09383
The prediction of human gaze behavior is important for building human-computer interactive systems that can anticipate a user's attention. Computer vision models have been developed to predict the fixations made by people as they search for target ob
Externí odkaz:
http://arxiv.org/abs/2207.01166
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 Attention Transformer (HAT), a single model predicting both forms of atten
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c9997ff49947569fbc5dd7332130aea7
http://arxiv.org/abs/2303.09383
http://arxiv.org/abs/2303.09383
Autor:
Yang Z; Stony Brook University, Stony Brook, NY 11794, USA., Mondal S; Stony Brook University, Stony Brook, NY 11794, USA., Ahn S; Stony Brook University, Stony Brook, NY 11794, USA., Zelinsky G; Stony Brook University, Stony Brook, NY 11794, USA., Hoai M; Stony Brook University, Stony Brook, NY 11794, USA., Samaras D; Stony Brook University, Stony Brook, NY 11794, USA.
Publikováno v:
Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision [Comput Vis ECCV] 2022 Oct; Vol. 13664, pp. 52-68. Date of Electronic Publication: 2022 Oct 23.