Video saliency prediction with collective spatio-temporal attention
|更新时间:2025-05-26
|
Video saliency prediction with collective spatio-temporal attention
“In the field of video saliency prediction, researchers have proposed the joint spatiotemporal attention mechanism COStA, which effectively models the temporal and spatial relationships in video information and provides a solution for accurate prediction.”
Journal of Jilin University(Engineering and Technology Edition)Vol. 54, Issue 6, Pages: 1767-1776(2024)
SUN Ming-hui,XUE Hao,JIN Yu-bo,et al.Video saliency prediction with collective spatio-temporal attention[J].Journal of Jilin University(Engineering and Technology Edition),2024,54(06):1767-1776.
SUN Ming-hui,XUE Hao,JIN Yu-bo,et al.Video saliency prediction with collective spatio-temporal attention[J].Journal of Jilin University(Engineering and Technology Edition),2024,54(06):1767-1776. DOI: 10.13229/j.cnki.jdxbgxb.20220851.
Video saliency prediction with collective spatio-temporal attention