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 • 2 Feb 2021 • Yi-Jun Cao, Chuan Lin, Yong-Jie Li
Significant progress has been made in boundary detection with the help of convolutional neural networks.
no code implementations • 1 Dec 2020 • Peng Peng, Yong-Jie Li
The proposed structure is simple yet effective; the rich context information of RGB and depth can be appropriately extracted and fused by the proposed structure efficiently.
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 • 6 Sep 2016 • Shao-Bing Gao, Ming Zhang, Chao-Yi Li, Yong-Jie Li
Most color constancy (CC) models have been designed to first estimate the illuminant color, which is then removed from the color biased image to obtain an image taken under white light, without the explicit consideration of CSS effect on CC.
no code implementations • 9 Sep 2015 • Teng Qiu, Yong-Jie Li
Due to some beautiful and effective features, this IT structure proves well suited for data clustering.
no code implementations • 29 Jul 2015 • Teng Qiu, Yong-Jie Li
But if we can effectively map those IT structures into a visualized space in which the salient features of those undesired edges are preserved, then the undesired edges in the IT structures can still be visually determined in a visualization environment.
no code implementations • 19 Jun 2015 • Teng Qiu, Yong-Jie Li
Previously, we proposed a physically inspired rule to organize the data points in a sparse yet effective structure, called the in-tree (IT) graph, which is able to capture a wide class of underlying cluster structures in the datasets, especially for the density-based datasets.
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 • 17 Feb 2015 • Teng Qiu, Yong-Jie Li
In our physically inspired in-tree (IT) based clustering algorithm and the series after it, there is only one free parameter involved in computing the potential value of each point.
no code implementations • 16 Feb 2015 • Teng Qiu, Yong-Jie Li
In our previous works, we proposed a physically-inspired rule to organize the data points into an in-tree (IT) structure, in which some undesired edges are allowed to occur.
no code implementations • 26 Jan 2015 • Teng Qiu, Yong-Jie Li
Scientists in many fields have the common and basic need of dimensionality reduction: visualizing the underlying structure of the massive multivariate data in a low-dimensional space.
no code implementations • 18 Jan 2015 • Teng Qiu, Yong-Jie Li
A recently proposed clustering method, called the Nearest Descent (ND), can organize the whole dataset into a sparsely connected graph, called the In-tree.
no code implementations • 24 Dec 2014 • Teng Qiu, Yong-Jie Li
Nowadays, data are generated massively and rapidly from scientific fields as bioinformatics, neuroscience and astronomy to business and engineering fields.
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.
no code implementations • CVPR 2013 • Kaifu Yang, Shao-Bing Gao, Chaoyi Li, Yong-Jie Li
Color information plays an important role in better understanding of natural scenes by at least facilitating discriminating boundaries of objects or areas.