Zhuowei Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Zhuowei Xu has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Miaohui Wang
Shenzhen University
6 shared publications - Wuyuan Xie
Shenzhen University
3 shared publications - Weisi Lin
Nanyang Technological University
2 shared publications - Bin Zheng
College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China
1 shared publication Jian Xiong
College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China
1 shared publication- Mai Xu
Beihang University
1 shared publication
Latest Publications
- 18 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 1849-1863
Visual Quality Assessment of Composite Images: A Compression-Oriented Database and Measurement
Composite images (CIs) have experienced unprecedented growth, especially with the prosperity of a large number of generative AI technologies. They are usually created by combining multiple visual elements from different sources to form a single cohesive composition, which have an increasing impact on a variety of vision applications. However, transmission of CIs can degrade their visual quality, especially undergoing lossy compression to reduce bandwidth and storage. To facilitate the development of objective measurements for CIs and investigate the influence of compression distortions on their perception, we establish a compression-oriented image quality assessment (CIQA) database for CIs (called ciCIQA) with 30 typical encoding distortions. Compressed with six representative codecs, we have carried out a large-scale subjective experiment that delivered 3,000 encoded CIs with labeled quality scores, making ciCIQA one of the earliest CI databases with the most compression types. ciCIQA enables us to explore the encoding effects on visual quality from the first five just noticeable difference (JND) points, offering insights for perceptual CI compression and related tasks. Moreover, we have proposed a new multi-masked blind CIQA method (called mmCIQA), including a multi-masked quality representation module, a self-supervised quality alignment module, and a multi-masked attentive fusion module. Experimental results demonstrate the outstanding performance of our mmCIQA in assessing the quality of CIs, outperforming 17 competitive approaches. The proposed method and database as well as the collected objective metrics are made publicly available on https://charwill.github.io/mmCIQA.html.
- 18 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 1849-1863
Visual Quality Assessment of Composite Images: A Compression-Oriented Database and Measurement
Composite images (CIs) have experienced unprecedented growth, especially with the prosperity of a large number of generative AI technologies. They are usually created by combining multiple visual elements from different sources to form a single cohesive composition, which have an increasing impact on a variety of vision applications. However, transmission of CIs can degrade their visual quality, especially undergoing lossy compression to reduce bandwidth and storage. To facilitate the development of objective measurements for CIs and investigate the influence of compression distortions on their perception, we establish a compression-oriented image quality assessment (CIQA) database for CIs (called ciCIQA) with 30 typical encoding distortions. Compressed with six representative codecs, we have carried out a large-scale subjective experiment that delivered 3,000 encoded CIs with labeled quality scores, making ciCIQA one of the earliest CI databases with the most compression types. ciCIQA enables us to explore the encoding effects on visual quality from the first five just noticeable difference (JND) points, offering insights for perceptual CI compression and related tasks. Moreover, we have proposed a new multi-masked blind CIQA method (called mmCIQA), including a multi-masked quality representation module, a self-supervised quality alignment module, and a multi-masked attentive fusion module. Experimental results demonstrate the outstanding performance of our mmCIQA in assessing the quality of CIs, outperforming 17 competitive approaches. The proposed method and database as well as the collected objective metrics are made publicly available on https://charwill.github.io/mmCIQA.html.
- 16 October 2024
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (4) , 1665-1688
Blind Multimodal Quality Assessment of Low-Light Images
- 16 October 2024
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (4) , 1665-1688
Blind Multimodal Quality Assessment of Low-Light Images
- 15 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (8) , 10657-10668
BinaryFormer: A Hierarchical-Adaptive Binary Vision Transformer (ViT) for Efficient Computing
Vision Transformer (ViT) has recently demonstrated impressive nonlinear modeling capabilities and achieved state-of-the-art performance in various industrial applications, such as object recognition, anomaly detection, and robot control. However, their practical deployment can be hindered by high storage requirements and computational intensity. To alleviate these challenges, we propose a binary transformer called BinaryFormer, which quantizes the learned weights of the ViT module from 32-b precision to 1 b. Furthermore, we propose a hierarchical-adaptive architecture that replaces expensive matrix operations with more affordable addition and bit operations by switching between two attention modes. As a result, BinaryFormer is able to effectively compress the model size as well as reduce the computation cost of ViT. Experimental results on the ImageNet-1K benchmark datasets show that BinaryFormer reduces the size of a typical ViT model by an average of 27.7× and converts over 99% of multiplication operations into bit operations while maintaining reasonable accuracy.
- 15 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (8) , 10657-10668
BinaryFormer: A Hierarchical-Adaptive Binary Vision Transformer (ViT) for Efficient Computing
Vision Transformer (ViT) has recently demonstrated impressive nonlinear modeling capabilities and achieved state-of-the-art performance in various industrial applications, such as object recognition, anomaly detection, and robot control. However, their practical deployment can be hindered by high storage requirements and computational intensity. To alleviate these challenges, we propose a binary transformer called BinaryFormer, which quantizes the learned weights of the ViT module from 32-b precision to 1 b. Furthermore, we propose a hierarchical-adaptive architecture that replaces expensive matrix operations with more affordable addition and bit operations by switching between two attention modes. As a result, BinaryFormer is able to effectively compress the model size as well as reduce the computation cost of ViT. Experimental results on the ImageNet-1K benchmark datasets show that BinaryFormer reduces the size of a typical ViT model by an average of 27.7× and converts over 99% of multiplication operations into bit operations while maintaining reasonable accuracy.
- 26 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (3) , 4440-4450
ReferPose: Distance Optimization-Based Reference Learning for Human Pose Estimation and Monitoring
Existing deep learning models for human pose estimation (HPE) have shown satisfactory performance in monitoring human actions. However, they usually face a dilemma between complexity and accuracy. To address this challenge, we propose an effective reference learning method for HPE (namely ReferPose), which is based on a new distance optimization strategy. Specifically, we utilize a reference model for pose learning and representation. The pose representation learned from the entire database is merged into the reference model, providing continuous reference learning guidance for an in-training model. In addition, we design a new cosine annealing-based reference guidance for temporal denoising and further develop a distance optimization strategy to provide joint guidance from pose knowledge, model representation, and temporal experience. Experimental results on two benchmark databases and a human fall monitoring system demonstrate that our ReferPose not only achieves promising accuracy improvement compared with several representative HPE models, but also offers low cost and high efficiency.
- 26 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 20 (3) , 4440-4450
ReferPose: Distance Optimization-Based Reference Learning for Human Pose Estimation and Monitoring
Existing deep learning models for human pose estimation (HPE) have shown satisfactory performance in monitoring human actions. However, they usually face a dilemma between complexity and accuracy. To address this challenge, we propose an effective reference learning method for HPE (namely ReferPose), which is based on a new distance optimization strategy. Specifically, we utilize a reference model for pose learning and representation. The pose representation learned from the entire database is merged into the reference model, providing continuous reference learning guidance for an in-training model. In addition, we design a new cosine annealing-based reference guidance for temporal denoising and further develop a distance optimization strategy to provide joint guidance from pose knowledge, model representation, and temporal experience. Experimental results on two benchmark databases and a human fall monitoring system demonstrate that our ReferPose not only achieves promising accuracy improvement compared with several representative HPE models, but also offers low cost and high efficiency.
- 4 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 18 (10) , 6865-6875
Perceptually Quasi-Lossless Compression of Screen Content Data Via Visibility Modeling and Deep Forecasting
Screen content data, such as computer-generated photographs, desktop sharing, remote education, video game streaming and screenshot, is one of the most popular visual information carriers in Internet of Video Things. Although lossless compression can guarantee high quality of service for these screen content based industrial applications, it also causes considerable storage space and transmission bandwidth issues. To alleviate these challenges, in this article, we present a visually quasi-lossless coding approach to control the compression distortion below visibility threshold in the human visual system. Specifically, to better quantify the visual redundancy for screen content data, a new visibility threshold method is designed by incorporating blur sensitivity and oblique correction effects. Then, an end-to-end mapping between the visibility threshold and quality control factor is learned and represented as a deep convolutional neural network. The experimental results demonstrate that the proposed method saves the average encoding bits up to 23.15% compared with the latest scheme under the same perceptual quality.
- 4 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 18 (10) , 6865-6875
Perceptually Quasi-Lossless Compression of Screen Content Data Via Visibility Modeling and Deep Forecasting
Screen content data, such as computer-generated photographs, desktop sharing, remote education, video game streaming and screenshot, is one of the most popular visual information carriers in Internet of Video Things. Although lossless compression can guarantee high quality of service for these screen content based industrial applications, it also causes considerable storage space and transmission bandwidth issues. To alleviate these challenges, in this article, we present a visually quasi-lossless coding approach to control the compression distortion below visibility threshold in the human visual system. Specifically, to better quantify the visual redundancy for screen content data, a new visibility threshold method is designed by incorporating blur sensitivity and oblique correction effects. Then, an end-to-end mapping between the visibility threshold and quality control factor is learned and represented as a deep convolutional neural network. The experimental results demonstrate that the proposed method saves the average encoding bits up to 23.15% compared with the latest scheme under the same perceptual quality.
- 30 September 2021
- Published by Springer Nature
- p. 265-274
Deep Human Pose Estimation via Self-guided Learning
- 30 September 2021
- Published by Springer Nature
- p. 265-274
Deep Human Pose Estimation via Self-guided Learning