TY - GEN
T1 - Scanpaths Generation for Target Search Based on Deep Learning
AU - Wu, Jinghan
AU - Lu, Meiqi
AU - Lin, Yuping
AU - Zhang, Xuetao
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/11/6
Y1 - 2020/11/6
N2 - Scanpath is a sequence of gaze fixations changing with time when browsing something, which records eyes' movement dynamically. Accurate prediction of scanpaths can help computers better predict which area human pay attention to and drive the development of next-generation systems that can understand human behavior and needs. Therefore, this paper introduces an algorithm of scanpaths generation for target search. Based on one-shot learning network, the algorithm extracts the target map with task information, and then imports it into a visual model of the superior colliculus to predict the task-drive scanpaths. The results are similar to the gaze behavior of human eyes in shape, direction and length. At the same time, the algorithm also has the ability to predict the scanpaths based on unseen categories.
AB - Scanpath is a sequence of gaze fixations changing with time when browsing something, which records eyes' movement dynamically. Accurate prediction of scanpaths can help computers better predict which area human pay attention to and drive the development of next-generation systems that can understand human behavior and needs. Therefore, this paper introduces an algorithm of scanpaths generation for target search. Based on one-shot learning network, the algorithm extracts the target map with task information, and then imports it into a visual model of the superior colliculus to predict the task-drive scanpaths. The results are similar to the gaze behavior of human eyes in shape, direction and length. At the same time, the algorithm also has the ability to predict the scanpaths based on unseen categories.
KW - Computer Vision
KW - Deep Learning
KW - Scanpaths Generation
KW - Target Search
UR - https://www.scopus.com/pages/publications/85100940810
U2 - 10.1109/CAC51589.2020.9327358
DO - 10.1109/CAC51589.2020.9327358
M3 - 会议稿件
AN - SCOPUS:85100940810
T3 - Proceedings - 2020 Chinese Automation Congress, CAC 2020
SP - 1443
EP - 1448
BT - Proceedings - 2020 Chinese Automation Congress, CAC 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 Chinese Automation Congress, CAC 2020
Y2 - 6 November 2020 through 8 November 2020
ER -