Loading [MathJax]/extensions/MathZoom.js
Deming Zhai - IEEE Xplore Author Profile
Subscribe
ADVANCED SEARCH

Author details

< Back

Deming Zhai

Publications
33
Citations
546
Publications by Year
20112025
Co-Authors:
Show All Co-Authors (41)
Image of author Deming Zhai

Deming Zhai

Affiliation

Faculty of Computing
Harbin Institute of Technology
Harbin, China

Publication Topics

Biography

Deming Zhai received the B.S., M.S., and Ph.D. (Hons.) degrees in computer science from the Harbin Institute of Technology (HIT), Harbin, China, in 2007, 2009, and 2014, respectively. In 2011, she was with The Hong Kong University of Science and Technology, as a Visiting Student. In 2012, she was with GRASP Laboratory, University of Pennsylvania, Philadelphia, PA, USA, as a Visiting Scholar. From 2014 to 2016, she was a Project Researcher with the National Institute of Informatics, Tokyo, Japan. She is currently an Assistant Professor with the Department of Computer Science, HIT. Her research interests include machine learning and its applications in computer version.(Based on document published on 1 January 2019).
Publications
33
Citations
546
Publications by Year
20112025
Co-Authors:
Show All Co-Authors (41)
Author's Published Works

Showing 1-25 of 33 results

  • Sort

Filter Results

Show

Sort By

Results

Learning Lossless Compression for High Bit-Depth Volumetric Medical Image

Kai Wang;Yuanchao Bai;Daxin Li;Deming Zhai;Junjun Jiang;Xianming Liu

IEEE Transactions on Image Processing
Year: 2025 | Volume: 34 | Journal Article |
Recent advances in learning-based methods have markedly enhanced the capabilities of image compression. However, these methods struggle with high bit-depth volumetric medical images, facing issues such as degraded performance, increased memory demand, and reduced processing speed. To address these challenges, this paper presents the Bit-Division based Lossless Volumetric Image Compression (BD-LVIC...Show More

Learning Lossless Compression for High Bit-Depth Volumetric Medical Image

Kai Wang;Yuanchao Bai;Daxin Li;Deming Zhai;Junjun Jiang;Xianming Liu

Year: 2025 | Volume: 34 | Journal Article |

Enhancing Privacy-Utility Tradeoff with Few-Round Strategy in Heterogeneous Federated Learning

Qingbin Wei;Feilong Zhang;Yuanchao Bai;Deming Zhai;Junjun Jiang;Xianming Liu

2024 IEEE International Conference on Visual Communications and Image Processing (VCIP)
Year: 2024 | Conference Paper |
Federated learning inherently provides a certain level of privacy protection, which however is often inadequate in many real-world scenarios. Existing privacy-preserving methods frequently incur unbearable time overheads or result in non-negligible deterioration to model performance, thus suffering from the tradeoff between performance and privacy. In this work, we propose a novel Federated Privac...Show More

Enhancing Privacy-Utility Tradeoff with Few-Round Strategy in Heterogeneous Federated Learning

Qingbin Wei;Feilong Zhang;Yuanchao Bai;Deming Zhai;Junjun Jiang;Xianming Liu

Year: 2024 | Conference Paper |

Learning Lossless Compression for High Bit-Depth Medical Imaging

Kai Wang;Yuanchao Bai;Deming Zhai;Daxin Li;Junjun Jiang;Xianming Liu

2023 IEEE International Conference on Multimedia and Expo (ICME)
Year: 2023 | Conference Paper |
Cited by: Papers (4)
We propose a learned lossless image compression method for high bit-depth medical imaging (up to 16 bit-depths). Instead of compressing a high bit-depth medical image as a whole, we split it into two low bit-depth subimages, i.e., the most significant bytes (MSB) subimage and the least significant bytes (LSB) subimage, respectively. The MSB subimage depicts piece-wise smooth structure information ...Show More

Learning Lossless Compression for High Bit-Depth Medical Imaging

Kai Wang;Yuanchao Bai;Deming Zhai;Daxin Li;Junjun Jiang;Xianming Liu

Year: 2023 | Conference Paper |

Unsupervised Deep Exemplar Colorization via Pyramid Dual Non-Local Attention

Hanzhang Wang;Deming Zhai;Xianming Liu;Junjun Jiang;Wen Gao

IEEE Transactions on Image Processing
Year: 2023 | Volume: 32 | Journal Article |
Cited by: Papers (4)
Exemplar-based colorization is a challenging task, which attempts to add colors to the target grayscale image with the aid of a reference color image, so as to keep the target semantic content while with the reference color style. In order to achieve visually plausible chromatic results, it is important to sufficiently exploit the global color style and the semantic color information of the refere...Show More

Unsupervised Deep Exemplar Colorization via Pyramid Dual Non-Local Attention

Hanzhang Wang;Deming Zhai;Xianming Liu;Junjun Jiang;Wen Gao

Year: 2023 | Volume: 32 | Journal Article |

Self-Supervised Arbitrary-Scale Implicit Point Clouds Upsampling

Wenbo Zhao;Xianming Liu;Deming Zhai;Junjun Jiang;Xiangyang Ji

IEEE Transactions on Pattern Analysis and Machine Intelligence
Year: 2023 | Volume: 45, Issue: 10 | Journal Article |
Cited by: Papers (1)
Point clouds upsampling (PCU), which aims to generate dense and uniform point clouds from the captured sparse input of 3D sensor such as LiDAR, is a practical yet challenging task. It has potential applications in many real-world scenarios, such as autonomous driving, robotics, AR/VR, etc. Deep neural network based methods achieve remarkable success in PCU. However, most existing deep PCU methods ...Show More

Self-Supervised Arbitrary-Scale Implicit Point Clouds Upsampling

Wenbo Zhao;Xianming Liu;Deming Zhai;Junjun Jiang;Xiangyang Ji

Year: 2023 | Volume: 45, Issue: 10 | Journal Article |

Super-Resolving Face Image by Facial Parsing Information

Chenyang Wang;Junjun Jiang;Zhiwei Zhong;Deming Zhai;Xianming Liu

IEEE Transactions on Biometrics, Behavior, and Identity Science
Year: 2023 | Volume: 5, Issue: 4 | Journal Article |
Cited by: Papers (6)
Face super-resolution is a technology that transforms a low-resolution face image into the corresponding high-resolution one. In this paper, we build a novel parsing map guided face super-resolution network which extracts the face prior (i.e., parsing map) directly from low-resolution face image for the following utilization. To exploit the extracted prior fully, a parsing map attention fusion blo...Show More

Super-Resolving Face Image by Facial Parsing Information

Chenyang Wang;Junjun Jiang;Zhiwei Zhong;Deming Zhai;Xianming Liu

Year: 2023 | Volume: 5, Issue: 4 | Journal Article |

Asymmetric Loss Functions for Noise-Tolerant Learning: Theory and Applications

Xiong Zhou;Xianming Liu;Deming Zhai;Junjun Jiang;Xiangyang Ji

IEEE Transactions on Pattern Analysis and Machine Intelligence
Year: 2023 | Volume: 45, Issue: 7 | Journal Article |
Cited by: Papers (21)
Supervised deep learning has achieved tremendous success in many computer vision tasks, which however is prone to overfit noisy labels. To mitigate the undesirable influence of noisy labels, robust loss functions offer a feasible approach to achieve noise-tolerant learning. In this work, we systematically study the problem of noise-tolerant learning with respect to both classification and regressi...Show More

Asymmetric Loss Functions for Noise-Tolerant Learning: Theory and Applications

Xiong Zhou;Xianming Liu;Deming Zhai;Junjun Jiang;Xiangyang Ji

Year: 2023 | Volume: 45, Issue: 7 | Journal Article |

Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon

Yiqi Zhong;Xianming Liu;Deming Zhai;Junjun Jiang;Xiangyang Ji

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2022 | Conference Paper |
Cited by: Papers (77)
Estimating the risk level of adversarial examples is essential for safely deploying machine learning models in the real world. One popular approach for physical-world attacks is to adopt the “sticker-pasting” strategy, which however suffers from some limitations, including difficulties in access to the target or printing by valid colors. A new type of non-invasive attacks emerged recently, which a...Show More

Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon

Yiqi Zhong;Xianming Liu;Deming Zhai;Junjun Jiang;Xiangyang Ji

Year: 2022 | Conference Paper |

Learning with Noisy Labels via Sparse Regularization

Xiong Zhou;Xianming Liu;Chenyang Wang;Deming Zhai;Junjun Jiang;Xiangyang Ji

2021 IEEE/CVF International Conference on Computer Vision (ICCV)
Year: 2021 | Conference Paper |
Cited by: Papers (43)
Learning with noisy labels is an important and challenging task for training accurate deep neural networks. Some commonly-used loss functions, such as Cross Entropy (CE), suffer from severe overfitting to noisy labels. Robust loss functions that satisfy the symmetric condition were tailored to remedy this problem, which however encounter the underfitting effect. In this paper, we theoretically pro...Show More

Learning with Noisy Labels via Sparse Regularization

Xiong Zhou;Xianming Liu;Chenyang Wang;Deming Zhai;Junjun Jiang;Xiangyang Ji

Year: 2021 | Conference Paper |

Semi-Supervised Graph Convolutional Hashing Network For Large-Scale Cross-Modal Retrieval

Zhanjian Shen;Deming Zhai;Xianming Liu;Junjun Jiang

2020 IEEE International Conference on Image Processing (ICIP)
Year: 2020 | Conference Paper |
Cited by: Papers (5)
Cross-modal retrieval aims to provide flexible retrieval results across different types of multimedia data. To confront with scalability issue, binary codes learning (a.k.a. hash technique) is advocated since it permits exact top-K retrieval with sub-linear time complexity. In this paper, we propose a new method called Semi-supervised Graph Convolutional Hashing network (SGCH), which tries to lear...Show More

Semi-Supervised Graph Convolutional Hashing Network For Large-Scale Cross-Modal Retrieval

Zhanjian Shen;Deming Zhai;Xianming Liu;Junjun Jiang

Year: 2020 | Conference Paper |

Parsing Map Guided Multi-Scale Attention Network For Face Hallucination

Chenyang Wang;Zhiwei Zhong;Junjun Jiang;Deming Zhai;Xianming Liu

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2020 | Conference Paper |
Cited by: Papers (10)
Face hallucination that aims to transform a low-resolution (LR) face image to a high-resolution (HR) one is an active domain-specific image super-resolution problem. The performance of existing methods is usually not satisfactory, especially when the upscaling factor is large, such as 8×. In this paper, we propose an effective two- step face hallucination method based on a deep neural network with...Show More

Parsing Map Guided Multi-Scale Attention Network For Face Hallucination

Chenyang Wang;Zhiwei Zhong;Junjun Jiang;Deming Zhai;Xianming Liu

Year: 2020 | Conference Paper |

ADRN: Attention-Based Deep Residual Network for Hyperspectral Image Denoising

Yongsen Zhao;Deming Zhai;Junjun Jiang;Xianming Liu

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2020 | Conference Paper |
Cited by: Papers (26)
Hyperspectral image (HSI) denoising is of crucial importance for many subsequent applications, such as HSI classification and interpretation. In this paper, we propose an attention-based deep residual network to directly learn a mapping from noisy HSI to the clean one. To jointly utilize the spatial-spectral information, the current band and its K adjacent bands are simultaneously exploited as the...Show More

ADRN: Attention-Based Deep Residual Network for Hyperspectral Image Denoising

Yongsen Zhao;Deming Zhai;Junjun Jiang;Xianming Liu

Year: 2020 | Conference Paper |

Contrast Enhancement via Dual Graph Total Variation-Based Image Decomposition

Xianming Liu;Deming Zhai;Yuanchao Bai;Xiangyang Ji;Wen Gao

IEEE Transactions on Circuits and Systems for Video Technology
Year: 2020 | Volume: 30, Issue: 8 | Journal Article |
Cited by: Papers (11)
Images captured in low lighting environment suffer from both low luminance contrast and noise corruption. However, most existing contrast enhancement algorithms only consider contrast boosting, which tends to reveal or amplify noise that is originally not visible in the dark areas. In this paper, we propose a joint contrast enhancement and denoising algorithm, which is based on structure/texture l...Show More

Contrast Enhancement via Dual Graph Total Variation-Based Image Decomposition

Xianming Liu;Deming Zhai;Yuanchao Bai;Xiangyang Ji;Wen Gao

Year: 2020 | Volume: 30, Issue: 8 | Journal Article |

Color-Guided Depth Image Recovery With Adaptive Data Fidelity and Transferred Graph Laplacian Regularization

Yongbing Zhang;Yihui Feng;Xianming Liu;Deming Zhai;Xiangyang Ji;Haoqian Wang;Qionghai Dai

IEEE Transactions on Circuits and Systems for Video Technology
Year: 2020 | Volume: 30, Issue: 2 | Journal Article |
Cited by: Papers (20)
Depth images play an important role and are prevalently used in many computer vision and computational imaging tasks. However, due to the limitation of active sensing technology, the captured depth images in practice usually suffer from low resolution and noise, which prevents its further applications. To remedy this problem, in this paper, we first propose an adaptive data fidelity formulation to...Show More

Color-Guided Depth Image Recovery With Adaptive Data Fidelity and Transferred Graph Laplacian Regularization

Yongbing Zhang;Yihui Feng;Xianming Liu;Deming Zhai;Xiangyang Ji;Haoqian Wang;Qionghai Dai

Year: 2020 | Volume: 30, Issue: 2 | Journal Article |

Joint Gaze Correction and Face Beautification for Conference Video Using Dual Sparsity Prior

Deming Zhai;Xianming Liu;Xiangyang Ji;Debin Zhao;Wen Gao

IEEE Transactions on Industrial Electronics
Year: 2019 | Volume: 66, Issue: 12 | Journal Article |
Cited by: Papers (5)
Gaze mismatch is a common problem in video conferencing, where the viewpoint captured by a camera (usually located above or below a display monitor) is not aligned with the gaze direction of the human subject, who typically looks at his counterpart in the center of the screen. This means that the two parties cannot converse eye-to-eye, hampering the visual communication experience. A recent popula...Show More

Joint Gaze Correction and Face Beautification for Conference Video Using Dual Sparsity Prior

Deming Zhai;Xianming Liu;Xiangyang Ji;Debin Zhao;Wen Gao

Year: 2019 | Volume: 66, Issue: 12 | Journal Article |

Depth Super-Resolution via Joint Color-Guided Internal and External Regularizations

Xianming Liu;Deming Zhai;Rong Chen;Xiangyang Ji;Debin Zhao;Wen Gao

IEEE Transactions on Image Processing
Year: 2019 | Volume: 28, Issue: 4 | Journal Article |
Cited by: Papers (52)
Depth information is being widely used in many real-world applications. However, due to the limitation of depth sensing technology, the captured depth map in practice usually has much lower resolution than that of color image counterpart. In this paper, we propose to combine the internal smoothness prior and external gradient consistency constraint in graph domain for depth super-resolution. On on...Show More

Depth Super-Resolution via Joint Color-Guided Internal and External Regularizations

Xianming Liu;Deming Zhai;Rong Chen;Xiangyang Ji;Debin Zhao;Wen Gao

Year: 2019 | Volume: 28, Issue: 4 | Journal Article |

Depth Restoration From RGB-D Data via Joint Adaptive Regularization and Thresholding on Manifolds

Xianming Liu;Deming Zhai;Rong Chen;Xiangyang Ji;Debin Zhao;Wen Gao

IEEE Transactions on Image Processing
Year: 2019 | Volume: 28, Issue: 3 | Journal Article |
Cited by: Papers (33)
In this paper, we propose a novel depth restoration algorithm from RGB-D data through combining characteristics of local and non-local manifolds, which provide low-dimensional parameterizations of the local and non-local geometry of depth maps. Specifically, on the one hand, a local manifold model is defined to favor local neighboring relationship of pixels in depth, according to which, manifold r...Show More

Depth Restoration From RGB-D Data via Joint Adaptive Regularization and Thresholding on Manifolds

Xianming Liu;Deming Zhai;Rong Chen;Xiangyang Ji;Debin Zhao;Wen Gao

Year: 2019 | Volume: 28, Issue: 3 | Journal Article |

Color-Guided Depth Map Super-Resolution via Joint Graph Laplacian and Gradient Consistency Regularization

Rong Chen;Deming Zhai;Xianming Liu;Debin Zhao

2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP)
Year: 2018 | Conference Paper |
Cited by: Papers (1)
Depth information is being widely used in many real-world applications. However, due to the limitation of depth sensing technology, the captured depth map in practice usually has much lower resolution than that of color image counterpart. In this paper, we propose to joint exploit the internal smoothness prior and external gradient consistency constraint in graph domain for depth super-resolution....Show More

Color-Guided Depth Map Super-Resolution via Joint Graph Laplacian and Gradient Consistency Regularization

Rong Chen;Deming Zhai;Xianming Liu;Debin Zhao

Year: 2018 | Conference Paper |

Robust Contrast Enhancement via Graph-Based Cartoon-Texture Decomposition

Deming Zhai;Xianming Lu;Xiangyang Ji;Yuanchao Bai;Debin Zhao;Wen Gao

2018 IEEE International Conference on Multimedia and Expo (ICME)
Year: 2018 | Conference Paper |
Cited by: Papers (1)
In this paper, we propose a robust contrast enhancement algorithm based on cartoon and texture layer decomposition. Specifically, the cartoon layer is expected to be generally smoothing but with sharp edges at the foreground and background boundaries, for which we propose a quadratic form of graph total variation (GTV) as the prior to promote signal smoothness along graph structure. For the textur...Show More

Robust Contrast Enhancement via Graph-Based Cartoon-Texture Decomposition

Deming Zhai;Xianming Lu;Xiangyang Ji;Yuanchao Bai;Debin Zhao;Wen Gao

Year: 2018 | Conference Paper |

Noise-Aware Super-Resolution of Depth Maps Via Graph-Based Plug-And-Play Framework

Rong Chen;Deming Zhai;Xianming Liu;Debin Zhao

2018 25th IEEE International Conference on Image Processing (ICIP)
Year: 2018 | Conference Paper |
Cited by: Papers (1)
Depth information is being widely used in many real-world tasks, such as 3DTV, 3D scene reconstruction, multi-view rendering, etc. However, the captured depth maps in practice usually suffer from quality degradations, including low-resolution and noise corruption, which limit their further applications. Noise-aware super-resolution of depth maps is a challenging task and has received increasingly ...Show More

Noise-Aware Super-Resolution of Depth Maps Via Graph-Based Plug-And-Play Framework

Rong Chen;Deming Zhai;Xianming Liu;Debin Zhao

Year: 2018 | Conference Paper |

Adaptive Screen Content Image Enhancement Strategy using Layer-based Segmentation

Zhaohui Che;Guangtao Zhai;Ke Gu;Patrick Le Callet;Xianming Liu;Deming Zhai;Xiao Gu

2018 IEEE International Symposium on Circuits and Systems (ISCAS)
Year: 2018 | Conference Paper |
Cited by: Papers (3)
The ubiquitous screen content images (SCIs) play a significant role in various scenarios currently. However, most SCIs captured by consumer devices are frequently corrupted with distortions, especially contrast distortion. Unlike the natural images, SCIs are composed of text, graphics and natural scene pictures so that traditional image enhancement methods are not suitable for these compound image...Show More

Adaptive Screen Content Image Enhancement Strategy using Layer-based Segmentation

Zhaohui Che;Guangtao Zhai;Ke Gu;Patrick Le Callet;Xianming Liu;Deming Zhai;Xiao Gu

Year: 2018 | Conference Paper |

Supervised Distributed Hashing for Large-Scale Multimedia Retrieval

Deming Zhai;Xianming Liu;Xiangyang Ji;Debin Zhao;Shin’ichi Satoh;Wen Gao

IEEE Transactions on Multimedia
Year: 2018 | Volume: 20, Issue: 3 | Journal Article |
Cited by: Papers (32)
Recent years have witnessed the growing popularity of hashing for large-scale multimedia retrieval. Extensive hashing methods have been designed for data stored in a single machine, that is, centralized hashing . In many real-world applications, however, the large-scale data are often distributed across different locations, servers, or sites. Although hashing for distributed data can be implemente...Show More

Supervised Distributed Hashing for Large-Scale Multimedia Retrieval

Deming Zhai;Xianming Liu;Xiangyang Ji;Debin Zhao;Shin’ichi Satoh;Wen Gao

Year: 2018 | Volume: 20, Issue: 3 | Journal Article |

Sparsity-Based Image Error Concealment via Adaptive Dual Dictionary Learning and Regularization

Xianming Liu;Deming Zhai;Jiantao Zhou;Shiqi Wang;Debin Zhao;Huijun Gao

IEEE Transactions on Image Processing
Year: 2017 | Volume: 26, Issue: 2 | Journal Article |
Cited by: Papers (27)
In this paper, we propose a novel sparsity-based image error concealment (EC) algorithm through adaptive dual dictionary learning and regularization. We define two feature spaces: the observed space and the latent space, corresponding to the available regions and the missing regions of image under test, respectively. We learn adaptive and complete dictionaries individually for each space, where th...Show More

Sparsity-Based Image Error Concealment via Adaptive Dual Dictionary Learning and Regularization

Xianming Liu;Deming Zhai;Jiantao Zhou;Shiqi Wang;Debin Zhao;Huijun Gao

Year: 2017 | Volume: 26, Issue: 2 | Journal Article |

Compressive Sampling-Based Image Coding for Resource-Deficient Visual Communication

Xianming Liu;Deming Zhai;Jiantao Zhou;Xinfeng Zhang;Debin Zhao;Wen Gao

IEEE Transactions on Image Processing
Year: 2016 | Volume: 25, Issue: 6 | Journal Article |
Cited by: Papers (41)
In this paper, a new compressive sampling-based image coding scheme is developed to achieve competitive coding efficiency at lower encoder computational complexity, while supporting error resilience. This technique is particularly suitable for visual communication with resource-deficient devices. At the encoder, compact image representation is produced, which is a polyphase down-sampled version of...Show More

Compressive Sampling-Based Image Coding for Resource-Deficient Visual Communication

Xianming Liu;Deming Zhai;Jiantao Zhou;Xinfeng Zhang;Debin Zhao;Wen Gao

Year: 2016 | Volume: 25, Issue: 6 | Journal Article |

Sparsity-based joint gaze correction and face beautification for conferencing video

Xianming Liu;Gene Cheung;Deming Zhai;Debin Zhao

2015 Visual Communications and Image Processing (VCIP)
Year: 2015 | Conference Paper |
Cited by: Papers (3)
A well-known problem in video conferencing is gaze mismatch. Instead of relying exclusively on online captured data for rendering, a recent work first trains offline dictionaries using a large image database of movie and TV stars to learn "beautiful" features. During real-time conferencing, one can then simultaneously correct gaze and beautify the subject's facial components in single images by se...Show More

Sparsity-based joint gaze correction and face beautification for conferencing video

Xianming Liu;Gene Cheung;Deming Zhai;Debin Zhao

Year: 2015 | Conference Paper |

IEEE Account

Purchase Details

Profile Information

Need Help?

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.