16 citations · 39 across the 6 of their papers we have counts for
7 papers
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…
Vector-Symbolic Architecture for Event-Based Optical Flow
Hongzhi You, Yijun Cao, Wei Yuan +3
From a perspective of feature matching, optical flow estimation for event cameras involves identifying event correspondences by comparing feature similarity across accompanying eve…
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…
Nighttime Thermal Infrared Image Colorization with Feedback-based Object Appearance Learning
Fu-Ya Luo, Shu-Lin Liu, Yi-Jun Cao +4
Stable imaging in adverse environments (e.g., total darkness) makes thermal infrared (TIR) cameras a prevalent option for night scene perception. However, the low contrast and lack…
Unsupervised Visual Odometry and Action Integration for PointGoal Navigation in Indoor Environment
Yijun Cao, Xianshi Zhang, Fuya Luo +2
PointGoal navigation in indoor environment is a fundamental task for personal robots to navigate to a specified point. Recent studies solved this PointGoal navigation task with nea…
Memory-Guided Collaborative Attention for Nighttime Thermal Infrared Image Colorization
Fu-Ya Luo, Yi-Jun Cao, Kai-Fu Yang +1
Nighttime thermal infrared (NTIR) image colorization, also known as translation of NTIR images into daytime color images (NTIR2DC), is a promising research direction to facilitate…
Learning Generalized Visual Odometry Using Position-Aware Optical Flow and Geometric Bundle Adjustment
Yijun Cao, Xianshi Zhang, Fuya Luo +2
Recent visual odometry (VO) methods incorporating geometric algorithm into deep-learning architecture have shown outstanding performance on the challenging monocular VO task. Despi…