1 code implementation • 29 Sep 2024 • Xiaofeng Cong, Jing Zhang, Yeying Jin, JunMing Hou, Yu Zhao, Jie Gui, James Tin-Yau Kwok, Yuan Yan Tang
ColorCode offers three key features: 1) color enhancement, producing an enhanced image with a fixed color; 2) color adaptation, enabling controllable adjustments of long-wavelength color components using guidance images; and 3) color interpolation, allowing for the smooth generation of multiple colors through continuous sampling of the color code.
no code implementations • 26 Sep 2024 • Chengze Jiang, Junkai Wang, Minjing Dong, Jie Gui, Xinli Shi, Yuan Cao, Yuan Yan Tang, James Tin-Yau Kwok
Based on the analysis, we mainly attribute the observed misalignment and disparity to the imbalanced optimization in FAT, which motivates us to optimize different training data adaptively to enhance robustness.
no code implementations • 23 Sep 2024 • Yifan Wang, Jie Gui, Yuan Yan Tang, James Tin-Yau Kwok
BWR-ROIAlign can directly plug into the model to introduce the above features for DCNN-based finger vein recognition systems.
no code implementations • 22 Sep 2024 • Jidong Kuang, Hongsong Wang, Chaolei Han, Jie Gui
The DA module maps the skeleton features to the semantic space through a specially designed visual projector, followed by the SDE, which is based on cross-attention to enhance the connection between skeleton and text, thereby reducing the gap between modalities.
no code implementations • 10 Sep 2024 • Siyu Zhai, Zhibo He, Xiaofeng Cong, JunMing Hou, Jie Gui, Jian Wei You, Xin Gong, James Tin-Yau Kwok, Yuan Yan Tang
In this paper, we propose a general adversarial attack protocol.
no code implementations • 22 Jul 2024 • Jie Gui, Chengze Jiang, Minjing Dong, Kun Tong, Xinli Shi, Yuan Yan Tang, DaCheng Tao
However, FAT suffers from catastrophic overfitting, which leads to a performance drop compared with multi-step adversarial training.
no code implementations • 13 Jul 2024 • Hongsong Wang, Jianhua Zhao, Jie Gui
Human action understanding is a fundamental and challenging task in computer vision.
no code implementations • 30 May 2024 • Xiaofeng Cong, Yu Zhao, Jie Gui, JunMing Hou, DaCheng Tao
Underwater image enhancement (UIE) presents a significant challenge within computer vision research.
1 code implementation • 29 May 2024 • Lanting Fang, Yulian Yang, Kai Wang, Shanshan Feng, Kaiyu Feng, Jie Gui, Shuliang Wang, Yew-Soon Ong
We aim to predict future links within the dynamic graph while simultaneously providing causal explanations for these predictions.
1 code implementation • 22 Apr 2024 • Yu-Xin Zhang, Jie Gui, Xiaofeng Cong, Xin Gong, Wenbing Tao
Point cloud registration (PCR) involves determining a rigid transformation that aligns one point cloud to another.
1 code implementation • CVPR 2024 • Xiaofeng Cong, Jie Gui, Jing Zhang, JunMing Hou, Hao Shen
There are two distinctions between nighttime and daytime haze.
1 code implementation • 9 Jun 2023 • Jie Gui, Xiaofeng Cong, Lei He, Yuan Yan Tang, James Tin-Yau Kwok
On the one hand, the dehazing task is an illposedness problem, which means that no unique solution exists.
no code implementations • 31 Mar 2023 • Biwei Cao, Lulu Hua, Jiuxin Cao, Jie Gui, Bo Liu, James Tin-Yau Kwok
Different from popular methods which take full advantage of the propagation topology structure, in this paper, we propose a novel framework for fake news detection from perspectives of semantic, emotion and data enhancement, which excavates the emotional evolution patterns of news participants during the propagation process, and a dual deep interaction channel network of semantic and emotion is designed to obtain a more comprehensive and fine-grained news representation with the consideration of comments.
1 code implementation • 30 Mar 2023 • Jie Gui, Xiaofeng Cong, Chengwei Peng, Yuan Yan Tang, James Tin-Yau Kwok
In this paper, we focus on designing a group of attack methods based on first order gradient to verify the robustness of the existing dehazing algorithms.
1 code implementation • 13 Jan 2023 • Jie Gui, Tuo Chen, Jing Zhang, Qiong Cao, Zhenan Sun, Hao Luo, DaCheng Tao
Deep supervised learning algorithms typically require a large volume of labeled data to achieve satisfactory performance.
1 code implementation • 8 Jan 2023 • Jidong Ge, Yuxiang Liu, Jie Gui, Lanting Fang, Ming Lin, James Tin-Yau Kwok, LiGuo Huang, Bin Luo
However, the relation between these two losses is not clear.
1 code implementation • 3 Dec 2022 • Wenzhe Jia, Yuan Cao, Junwei Liu, Jie Gui
When a new query arrives, only the binary codes of the corresponding potential neighbors are updated.
1 code implementation • 28 Nov 2022 • Jie Gui, Tuo Chen, Minjing Dong, Zhengqi Liu, Hao Luo, James Tin-Yau Kwok, Yuan Yan Tang
To tackle this issue, we propose the Frequency \& Attention-driven Masking and Throwing Strategy (FAMT), which can extract semantic patches and reduce the number of training patches to boost model performance and training efficiency simultaneously.
no code implementations • 16 Nov 2022 • Biwei Cao, Jiuxin Cao, Jie Gui, Jiayun Shen, Bo Liu, Lei He, Yuan Yan Tang, James Tin-Yau Kwok
Such approaches, however, ignore the VE's unique nature of relation inference between the premise and hypothesis.
no code implementations • 20 Oct 2021 • Jianfeng Wu, Wenhui Zhu, Yi Su, Jie Gui, Natasha Lepore, Eric M. Reiman, Richard J. Caselli, Paul M. Thompson, Kewei Chen, Yalin Wang
We evaluate our framework on 925 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI).
no code implementations • 13 Jun 2021 • Huapeng Wu, Jie Gui, Jun Zhang, James T. Kwok, Zhihui Wei
Recently, convolutional neural network (CNN) based image super-resolution (SR) methods have achieved significant performance improvement.
no code implementations • 13 Jun 2021 • Huapeng Wu, Jie Gui, Jun Zhang, James T. Kwok, Zhihui Wei
Recently, deep convolutional neural network methods have achieved an excellent performance in image superresolution (SR), but they can not be easily applied to embedded devices due to large memory cost.
1 code implementation • 7 Jun 2021 • Jie Gui, Xiaofeng Cong, Yuan Cao, Wenqi Ren, Jun Zhang, Jing Zhang, Jiuxin Cao, DaCheng Tao
With the development of convolutional neural networks, hundreds of deep learning based dehazing methods have been proposed.
no code implementations • 1 Apr 2021 • Jie Gui, Haizhang Zhang
Multi-task learning is an important trend of machine learning in facing the era of artificial intelligence and big data.
1 code implementation • 22 Mar 2021 • Yuxiang Liu, Jidong Ge, Chuanyi Li, Jie Gui
We propose Parametric Weights Standardization (PWS), a fast and robust to mini-batch size module used for conv filters, to solve the shift of the average gradient.
no code implementations • 2 Apr 2020 • Xiaoyun Li, Jie Gui, Ping Li
In this paper, we propose the kernel version of multi-view discriminant analysis, called kernel multi-view discriminant analysis (KMvDA).
no code implementations • 20 Jan 2020 • Jie Gui, Zhenan Sun, Yonggang Wen, DaCheng Tao, Jieping Ye
Generative adversarial networks (GANs) are a hot research topic recently.
no code implementations • 1 Dec 2019 • Rujing Yao, Linlin Hou, Lei Yang, Jie Gui, Qing Yin, Ou wu
This study focuses on a reverse question answering (QA) procedure, in which machines proactively raise questions and humans supply the answers.
no code implementations • 26 Sep 2019 • Huapeng Wu, Zhengxia Zou, Jie Gui, Wen-Jun Zeng, Jieping Ye, Jun Zhang, Hongyi Liu, Zhihui Wei
In this paper, we make a thorough investigation on the attention mechanisms in a SR model and shed light on how simple and effective improvements on these ideas improve the state-of-the-arts.
1 code implementation • 25 Sep 2019 • Chenxingyu Zhao, Jie Gui, Yixiao Guo, Jie Jiang, Tong Yang, Bin Cui, Gong Zhang
Unlike the densification to fill the empty bins after they undesirably occur, our design goal is to balance the load so as to reduce the empty bins in advance.
no code implementations • 8 Apr 2019 • Yong Luo, Yonggang Wen, DaCheng Tao, Jie Gui, Chao Xu
The features used in many image analysis-based applications are frequently of very high dimension.
no code implementations • 7 Apr 2019 • Jie Gui, Tongliang Liu, Zhenan Sun, DaCheng Tao, Tieniu Tan
Rather than adopting this method, FSDH uses a very simple yet effective regression of the class labels of training examples to the corresponding hash code to accelerate the algorithm.
no code implementations • 7 Apr 2019 • Jie Gui, Tongliang Liu, Zhenan Sun, DaCheng Tao, Tieniu Tan
In SDHR, the regression target is instead optimized.