5 citations · 6 across the 5 of their papers we have counts for
5 papers · 1 filter
A biological vision inspired framework for machine perception of abutting grating illusory contours
Xiao Zhang, Kai-Fu Yang, Xian-Shi Zhang +3
Higher levels of machine intelligence demand alignment with human perception and cognition. Deep neural networks (DNN) dominated machine intelligence have demonstrated exceptional…
Toward Better SSIM Loss for Unsupervised Monocular Depth Estimation
Yijun Cao, Fuya Luo, Yongjie Li
Unsupervised monocular depth learning generally relies on the photometric relation among temporally adjacent images. Most of previous works use both mean absolute error (MAE) and s…
PESFormer: Boosting Macro- and Micro-expression Spotting with Direct Timestamp Encoding
Wang-Wang Yu, Kai-Fu Yang, Xiangrui Hu +3
The task of macro- and micro-expression spotting aims to precisely localize and categorize temporal expression instances within untrimmed videos. Given the sparse distribution and…
Weak Supervision with Arbitrary Single Frame for Micro- and Macro-expression Spotting
Wang-Wang Yu, Xian-Shi Zhang, Fu-Ya Luo +4
Frame-level micro- and macro-expression spotting methods require time-consuming frame-by-frame observation during annotation. Meanwhile, video-level spotting lacks sufficient infor…
Weakly-supervised Micro- and Macro-expression Spotting Based on Multi-level Consistency
Wang-Wang Yu, Kai-Fu Yang, Hong-Mei Yan +1
Most micro- and macro-expression spotting methods in untrimmed videos suffer from the burden of video-wise collection and frame-wise annotation. Weakly-supervised expression spotti…