no code implementations • 21 Mar 2024 • Wang-Wang Yu, Xian-Shi Zhang, Fu-Ya Luo, Yijun Cao, Kai-Fu Yang, Hong-Mei Yan, Yong-Jie Li
Frame-level micro- and macro-expression spotting methods require time-consuming frame-by-frame observation during annotation.
1 code implementation • 24 Oct 2023 • Fu-Ya Luo, Shu-Lin Liu, Yi-Jun Cao, Kai-Fu Yang, Chang-Yong Xie, Yong liu, Yong-Jie Li
Extensive experiments illustrate that the proposed FoalGAN is not only effective for appearance learning of small objects, but also outperforms other image translation methods in terms of semantic preservation and edge consistency for the NTIR2DC task.
no code implementations • 4 May 2023 • Wang-Wang Yu, Kai-Fu Yang, Hong-Mei Yan, Yong-Jie Li
The inter-sample gap is primarily from the sample distribution and duration.
1 code implementation • 5 Aug 2022 • Fu-Ya Luo, Yi-Jun Cao, Kai-Fu Yang, Yong-Jie Li
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 nighttime scene perception for humans and intelligent systems under unfavorable conditions (e. g., complete darkness).
no code implementations • 16 Feb 2022 • Kai-Fu Yang, Cheng Cheng, Shi-Xuan Zhao, Xian-Shi Zhang, Yong-Jie Li
Light adaptation or brightness correction is a key step in improving the contrast and visual appeal of an image.
no code implementations • 19 Dec 2019 • Kai-Fu Yang, Wen-Wen Jiang, Teng-Fei Zhan, Yong-Jie Li
In order to verify the specific roles of scene layout and regional cues in guiding visual attention, we executed a psychophysical experiment to record the human fixations on line drawings of natural scenes with an eye-tracking system in this work.
no code implementations • CVPR 2015 • Kai-Fu Yang, Shao-Bing Gao, Yong-Jie Li
Illuminant estimation is a key step for computational color constancy.
no code implementations • 17 May 2015 • Kai-Fu Yang, Hui Li, Chao-Yi Li, Yong-Jie Li
We define the task of salient structure (SS) detection to unify the saliency-related tasks like fixation prediction, salient object detection, and other detection of structures of interest.
no code implementations • 7 Dec 2014 • Teng Qiu, Kai-Fu Yang, Chao-Yi Li, Yong-Jie Li
In particular, the rule of ND works to select the nearest node in the descending direction of potential as the parent node of each node, which is in essence different from the classical Gradient Descent or Steepest Descent.