Keke Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Keke Zhang has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Tiesong Zhao
Fuzhou University, Fuzhou, China
5 shared publications - Weiling Chen
Fujian Key Laboratory for Intelligent Processing and Wireless Transmission of Media Information, Fuzhou University, Fuzhou, China
3 shared publications - Yuzhen Niu
College of Computer and Data Science, Fuzhou University, Fuzhou, China
2 shared publications - Bin Dai
School of Information Science and Technology, Southwest Jiaotong University, Chengdu, China
1 shared publication Bin Liu
Fuzhou Institute of Technology
1 shared publication- Danling Kang
Fuzhou University
1 shared publication
Latest Publications
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. 8 (4) , 477-486
Machine Vision-Oriented Image Quality Evaluation for Face Super-Resolution
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biometrics, Behavior, and Identity Science
- Vol. 8 (4) , 477-486
Machine Vision-Oriented Image Quality Evaluation for Face Super-Resolution
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33, 3576-3580
MSDS: Deep Structural Similarity With Multiscale Representation
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33, 3576-3580
MSDS: Deep Structural Similarity With Multiscale Representation
- 3 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 10816-10827
Toward Efficient Video Compression Artifact Detection and Removal: A Benchmark Dataset
Video compression leads to compression artifacts, among which Perceivable Encoding Artifacts (PEAs) degrade user perception. Most of existing state-of-the-art Video Compression Artifact Removal (VCAR) methods indiscriminately process all artifacts, thus leading to over-enhancement in non-PEA regions. Therefore, accurate detection and location of PEAs is crucial. In this paper, we propose the largest-ever Fine-grained PEA database (FPEA). First, we employ the popular video codecs, VVC and AVS3, as well as their common test settings, to generate four types of spatial PEAs (blurring, blocking, ringing and color bleeding) and two types of temporal PEAs (flickering and floating). Second, we design a labeling platform and recruit sufficient subjects to manually locate all the above types of PEAs. Third, we propose a voting mechanism and feature matching to synthesize all subjective labels to obtain the final PEA labels with fine-grained locations. Besides, we also provide Mean Opinion Score (MOS) values of all compressed video sequences. Experimental results show the effectiveness of FPEA database on both VCAR and compressed Video Quality Assessment (VQA). We envision that FPEA database will benefit the future development of VCAR, VQA and perception-aware video encoders. The FPEA database has been made publicly available.
- 3 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 10816-10827
Toward Efficient Video Compression Artifact Detection and Removal: A Benchmark Dataset
Video compression leads to compression artifacts, among which Perceivable Encoding Artifacts (PEAs) degrade user perception. Most of existing state-of-the-art Video Compression Artifact Removal (VCAR) methods indiscriminately process all artifacts, thus leading to over-enhancement in non-PEA regions. Therefore, accurate detection and location of PEAs is crucial. In this paper, we propose the largest-ever Fine-grained PEA database (FPEA). First, we employ the popular video codecs, VVC and AVS3, as well as their common test settings, to generate four types of spatial PEAs (blurring, blocking, ringing and color bleeding) and two types of temporal PEAs (flickering and floating). Second, we design a labeling platform and recruit sufficient subjects to manually locate all the above types of PEAs. Third, we propose a voting mechanism and feature matching to synthesize all subjective labels to obtain the final PEA labels with fine-grained locations. Besides, we also provide Mean Opinion Score (MOS) values of all compressed video sequences. Experimental results show the effectiveness of FPEA database on both VCAR and compressed Video Quality Assessment (VQA). We envision that FPEA database will benefit the future development of VCAR, VQA and perception-aware video encoders. The FPEA database has been made publicly available.
- 12 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (7) , 5897-5907
Perception-Driven Similarity-Clarity Tradeoff for Image Super-Resolution Quality Assessment
Super-Resolution (SR) algorithms aim to enhance the resolutions of images. Massive deep-learning-based SR techniques have emerged in recent years. In such case, a visually appealing output may contain additional details compared with its reference image. Accordingly, fully referenced Image Quality Assessment (IQA) cannot work well; however, reference information remains essential for evaluating the qualities of SR images. This poses a challenge to SR-IQA: How to balance the referenced and no-reference scores for user perception? In this paper, we propose a Perception-driven Similarity-Clarity Tradeoff (PSCT) model for SR-IQA. Specifically, we investigate this problem from both referenced and no-reference perspectives, and design two deep-learning-based modules to obtain referenced and no-reference scores. We present a theoretical analysis based on Human Visual System (HVS) properties on their tradeoff and also calculate adaptive weights for them. Experimental results indicate that our PSCT model is superior to the state-of-the-arts on SR-IQA. In addition, the proposed PSCT model is also capable of evaluating quality scores in other image enhancement scenarios, such as deraining, dehazing and underwater image enhancement. The source code is available at https://github.com/kekezhang112/PSCT.
- 12 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (7) , 5897-5907
Perception-Driven Similarity-Clarity Tradeoff for Image Super-Resolution Quality Assessment
Super-Resolution (SR) algorithms aim to enhance the resolutions of images. Massive deep-learning-based SR techniques have emerged in recent years. In such case, a visually appealing output may contain additional details compared with its reference image. Accordingly, fully referenced Image Quality Assessment (IQA) cannot work well; however, reference information remains essential for evaluating the qualities of SR images. This poses a challenge to SR-IQA: How to balance the referenced and no-reference scores for user perception? In this paper, we propose a Perception-driven Similarity-Clarity Tradeoff (PSCT) model for SR-IQA. Specifically, we investigate this problem from both referenced and no-reference perspectives, and design two deep-learning-based modules to obtain referenced and no-reference scores. We present a theoretical analysis based on Human Visual System (HVS) properties on their tradeoff and also calculate adaptive weights for them. Experimental results indicate that our PSCT model is superior to the state-of-the-arts on SR-IQA. In addition, the proposed PSCT model is also capable of evaluating quality scores in other image enhancement scenarios, such as deraining, dehazing and underwater image enhancement. The source code is available at https://github.com/kekezhang112/PSCT.
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 9345-9349
Limited-Reference Image Quality Assessment: Paradigms and Discussions
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 9345-9349
Open AccessLimited-Reference Image Quality Assessment: Paradigms and Discussions
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 8125-8133
HCSD-Net: Single Image Desnowing with Color Space Transformation
Single-image desnowing aims at depressing snowflake noises while preserving a clean background. Existing methods usually mask the locations of noises and remove them in RGB color space. In this paper, we rethink this problem by investigating the impacts of color space selection. Theoretical analysis and experiments reveal that the feature of snowflake noises exhibit different distributions in different color spaces. In particular, these noises are barely seen in Hue channel, which inspires us to recover global structure and texture information of the clean background from Hue channel. More low-frequency information is also found in the Hue channel. With these observations, we propose a novel Hybrid-Color-Space-based Desnowing Network (HCSD-Net). The proposed HCSD-Net extracts low-frequency and high-frequency features in Hue channel and RGB color space, respectively. After that, it utilizes a multi-scale fusion module to enhance high-frequency details at a small feature resolution. These details are further used to supervise and supplement the background information. Extensive experiments demonstrate that our proposed HCSD-Net outperforms state-of-the-art methods on various synthetic and real-world desnowing datasets. Codes are available at https://github.com/ttz-rainbow/HCSD-Net.
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 8125-8133
Open AccessHCSD-Net: Single Image Desnowing with Color Space Transformation
Single-image desnowing aims at depressing snowflake noises while preserving a clean background. Existing methods usually mask the locations of noises and remove them in RGB color space. In this paper, we rethink this problem by investigating the impacts of color space selection. Theoretical analysis and experiments reveal that the feature of snowflake noises exhibit different distributions in different color spaces. In particular, these noises are barely seen in Hue channel, which inspires us to recover global structure and texture information of the clean background from Hue channel. More low-frequency information is also found in the Hue channel. With these observations, we propose a novel Hybrid-Color-Space-based Desnowing Network (HCSD-Net). The proposed HCSD-Net extracts low-frequency and high-frequency features in Hue channel and RGB color space, respectively. After that, it utilizes a multi-scale fusion module to enhance high-frequency details at a small feature resolution. These details are further used to supervise and supplement the background information. Extensive experiments demonstrate that our proposed HCSD-Net outperforms state-of-the-art methods on various synthetic and real-world desnowing datasets. Codes are available at https://github.com/ttz-rainbow/HCSD-Net.
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
On Asymptotic Analysis of Relative Generalized Hamming Weight
The relative generalized Hamming weight (RGHW) M r (C,C 1 ) of an [n, k] (linear) code C and an [n, k 1 ] subcode C 1 , a generalization of generalized Hamming weight (GHW), has been applied to wiretap channel, network coding, linear ramp secret sharing, and trellis complexity, etc. Asymptotic analysis of RGHW is useful for investigating the optimal performance of these applications when code length is sufficiently large. For linear ramp secret sharing schemes, the asymptotic metric we previously introduced is inconvenient for characterizing its performance mainly because the rate of information leakage is not considered.In this paper, we improve the previous work by introducing two new asymptotic metrics, respectively, for the cases that r is fixed and r is proportionally increasing with n. For fixed r, we show the asymptotic Singleton, Plotkin and Gilbert-Varshamov bounds on the first metric. For increasing r, we determine the value of the second metric.
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
On Asymptotic Analysis of Relative Generalized Hamming Weight
The relative generalized Hamming weight (RGHW) M r (C,C 1 ) of an [n, k] (linear) code C and an [n, k 1 ] subcode C 1 , a generalization of generalized Hamming weight (GHW), has been applied to wiretap channel, network coding, linear ramp secret sharing, and trellis complexity, etc. Asymptotic analysis of RGHW is useful for investigating the optimal performance of these applications when code length is sufficiently large. For linear ramp secret sharing schemes, the asymptotic metric we previously introduced is inconvenient for characterizing its performance mainly because the rate of information leakage is not considered.In this paper, we improve the previous work by introducing two new asymptotic metrics, respectively, for the cases that r is fixed and r is proportionally increasing with n. For fixed r, we show the asymptotic Singleton, Plotkin and Gilbert-Varshamov bounds on the first metric. For increasing r, we determine the value of the second metric.