Query：
学者姓名：陈建章
Refining：
Year
Type
Indexed by
Source
Complex
Co-Author
Language
Clean All
Abstract ：
Fine-grained image classification focuses on distinguishing subclasses. In food image classification, food's shape, color, and texture are easily influenced by cooking methods, presentation, and lighting. This makes differences among the same kind of food more subtle and harder to capture. To address this, we propose a multimodal framework fusing image and text modalities. The text modality, with distinct statistical properties, data attributes, and relational structures compared to images, enables precise characterization of fine-grained food features, providing complementary semantic information for classification. Specifically, cross-modal knowledge distillation is employed to transfer textual semantics into the image feature space, while contrastive learning is leveraged to discriminate between homogeneous and heterogeneous features across modalities and facilitate feature complementarity. Experiments on benchmark fine-grained food datasets VegFru, FoodX-251, and CNFood show that the proposed method achieves classification accuracies of 97.22 %, 83.25 %, and 84.96 %, respectively, outperforming state-of-the-art (SOTA) methods and validating the effectiveness of the multimodal cross-modal fusion strategy in fine-grained food classification tasks.
Keyword ：
Contrastive learning Contrastive learning Fine-grained image classification Fine-grained image classification Knowledge distillation Knowledge distillation Multi-modal paradigm Multi-modal paradigm
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Cheng, Li , Lan, Linyi , Xiao, Zhongjie et al. Fine-grained food image classification with multi-modal collaboration [J]. | NEUROCOMPUTING , 2026 , 660 . |
| MLA | Cheng, Li et al. "Fine-grained food image classification with multi-modal collaboration" . | NEUROCOMPUTING 660 (2026) . |
| APA | Cheng, Li , Lan, Linyi , Xiao, Zhongjie , Chen, Jianzhang , Lu, Jiaxiong , Wang, Huanrong et al. Fine-grained food image classification with multi-modal collaboration . | NEUROCOMPUTING , 2026 , 660 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Recently, CNN-based all-in-one image enhancement methods have been proposed to solve multiple image degradation tasks. However, these CNN-based methods usually have two limitations. One limitation is that they usually design a specific encoder for each image enhancement task, lacking of a unified and simple framework. The other limitation is that they can not effectively capture global image degradation information, as use of the CNN-based encoders has a limited local receptive field. In this work, we propose a TransEncoder-based All-in-one Image Enhancement Network (TAENet), with a single encoder and a decoder, for simultaneously handling multiple image enhancement tasks. Specifically, we propose a Transformer-based Encoder (TransEncoder), which introduces instance normalization to transformer for color recovery. The TransEncoder model global degradation information by using the transformer's global self-attention mechanism. Additionally, inspired by the Mie scattering model, we propose a novel depth loss function for perceiving image depth information by minimizing the depth difference between the enhanced image and the ground-truth, thus further improving model performance. Moreover, a novel contrastive loss is introduced to strengthen task-generalization performance by enhancing the model's representation capability. Experiments show that the TAENet outperforms 24 state-of-the-art methods on image dehazing, image deraining, and low-light image enhancement.
Keyword ：
All-in-one image enhancement All-in-one image enhancement Depth loss function Depth loss function Instance normalization Instance normalization TransEncoder TransEncoder
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Fang, Wanchuan , Wang, Chuansheng , Li, Zuoyong et al. TAENet: transencoder-based all-in-one image enhancement with depth awareness [J]. | APPLIED INTELLIGENCE , 2024 , 54 (15-16) : 7509-7530 . |
| MLA | Fang, Wanchuan et al. "TAENet: transencoder-based all-in-one image enhancement with depth awareness" . | APPLIED INTELLIGENCE 54 . 15-16 (2024) : 7509-7530 . |
| APA | Fang, Wanchuan , Wang, Chuansheng , Li, Zuoyong , Grau, Antoni , Lai, Taotao , Chen, Jianzhang . TAENet: transencoder-based all-in-one image enhancement with depth awareness . | APPLIED INTELLIGENCE , 2024 , 54 (15-16) , 7509-7530 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Differential privacy, a cornerstone of privacy-preserving techniques, plays an indispensable role in ensuring the secure handling and sharing of sensitive data analysis across domains such as in census, healthcare, and social networks. Histograms, serving as a visually compelling tool for presenting analytical outcomes, are widely employed in these sectors. Currently, numerous algorithms for publishing histograms under differential privacy have been developed, striving to balance privacy protection with the provision of useful data. Nonetheless, the pivotal challenge concerning the effective enhancement of precision for small bins (those intervals that are narrowly defined or contain a relatively small number of data points) within histograms has yet to receive adequate attention and in-depth investigation from experts. In standard DP histogram publishing, adding noise without regard for bin size can result in small data bins being disproportionately influenced by noise, potentially severely impairing the overall accuracy of the histogram. In response to this challenge, this paper introduces the SReB_GCA sanitization algorithm designed to enhance the accuracy of small bins in DP histograms. The SReB_GCA approach involves sorting the bins from smallest to largest and applying a greedy grouping strategy, with a predefined lower bound on the mean relative error required for a bin to be included in a group. Our theoretical analysis reveals that sorting bins in ascending order prior to grouping effectively prioritizes the accuracy of smaller bins. SReB_GCA ensures strict (Formula presented.) -DP compliance and strikes a careful balance between reconstruction error and noise error, thereby not only initially improving the accuracy of small bins but also approximately optimizing the mean relative error of the entire histogram. To validate the efficiency of our proposed SReB_GCA method, we conducted extensive experiments using four diverse datasets, including two real-life datasets and two synthetic ones. The experimental results, quantified by the Kullback–Leibler Divergence (KLD), show that the SReB_GCA algorithm achieves substantial performance enhancement compared to the baseline method (DP_BASE) and several other established approaches for differential privacy histogram publication. © 2024 by the authors.
Keyword ：
Errors Errors Graphic methods Graphic methods Privacy-preserving techniques Privacy-preserving techniques Sensitive data Sensitive data Sorting Sorting
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Jianzhang , Zhou, Shuo , Qiu, Jie et al. A Histogram Publishing Method under Differential Privacy That Involves Balancing Small-Bin Availability First [J]. | Algorithms , 2024 , 17 (7) . |
| MLA | Chen, Jianzhang et al. "A Histogram Publishing Method under Differential Privacy That Involves Balancing Small-Bin Availability First" . | Algorithms 17 . 7 (2024) . |
| APA | Chen, Jianzhang , Zhou, Shuo , Qiu, Jie , Xu, Yixin , Zeng, Bozhe , Fang, Wanchuan et al. A Histogram Publishing Method under Differential Privacy That Involves Balancing Small-Bin Availability First . | Algorithms , 2024 , 17 (7) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Due to the asymmetry of quantum errors, phase-shift errors are more likely to occur than qubit-flip errors. Consequently, there is a need to develop asymmetric quantum error-correcting (QEC) codes that can safeguard quantum information transmitted through asymmetric channels. Currently, a significant body of literature has investigated the construction of asymmetric QEC codes. However, the asymmetry of most QEC codes identified in the literature is limited by the dual-containing condition within the Calderbank-Shor-Steane (CSS) framework. This limitation restricts the exploration of their full potential in terms of asymmetry. In order to enhance the asymmetry of asymmetric QEC codes, we utilize entanglement-assisted technology and exploit the algebraic structure of cyclotomic cosets of constacyclic codes to achieve this goal. In this paper, we generalize the decomposition method of the defining set for constacyclic codes and apply it to count the number of pre-shared entangled states in order to construct four new classes of asymmetric entanglement-assisted quantum maximal-distance separable (EAQMDS) codes that satisfy the asymmetric entanglement-assisted quantum Singleton bound. Compared with the codes existing in the literature, the lengths of the constructed EAQMDS codes and the number of pre-shared entangled states are more general, and the codes constructed in this paper have greater asymmetry.
Keyword ：
asymmetric entanglement-assisted quantum codes asymmetric entanglement-assisted quantum codes constacyclic codes constacyclic codes maximal-distance separable codes maximal-distance separable codes
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Jianzhang , Fang, Wanchuan , Zhou, Shuo et al. Asymmetric Entanglement-Assisted Quantum MDS Codes Constructed from Constacyclic Codes [J]. | ENTROPY , 2023 , 25 (12) . |
| MLA | Chen, Jianzhang et al. "Asymmetric Entanglement-Assisted Quantum MDS Codes Constructed from Constacyclic Codes" . | ENTROPY 25 . 12 (2023) . |
| APA | Chen, Jianzhang , Fang, Wanchuan , Zhou, Shuo , Qiu, Jie , Zhang, Chenyang , Xu, Yixin et al. Asymmetric Entanglement-Assisted Quantum MDS Codes Constructed from Constacyclic Codes . | ENTROPY , 2023 , 25 (12) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Differential privacy (DP) has become a de facto standard to achieve data privacy. However, the utility of DP solutions with the premise of privacy priority is often unacceptable in real-world applications. In this paper, we propose the best-effort differential privacy (B-DP) to promise the preference for utility first and design two new metrics including the point belief degree and the regional average belief degree to evaluate its privacy from a new perspective of preference for privacy. Therein, the preference for privacy and utility is referred to as expected privacy protection (EPP) and expected data utility (EDU), respectively. We also investigate how to realize B-DP with an existing DP mechanism (KRR) and a newly constructed mechanism (EXPQ) in the dynamic check-in data collection and publishing. Extensive experiments on two real-world check-in datasets verify the effectiveness of the concept of B-DP. Our newly constructed EXPQ can also satisfy a better B-DP than KRR to provide a good trade-off between privacy and utility.
Keyword ：
B-DP B-DP check-in data check-in data DP DP dynamic collection and publishing dynamic collection and publishing
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Youqin , Xu, Zhengquan , Chen, Jianzhang et al. B-DP: Dynamic Collection and Publishing of Continuous Check-In Data with Best-Effort Differential Privacy [J]. | ENTROPY , 2022 , 24 (3) . |
| MLA | Chen, Youqin et al. "B-DP: Dynamic Collection and Publishing of Continuous Check-In Data with Best-Effort Differential Privacy" . | ENTROPY 24 . 3 (2022) . |
| APA | Chen, Youqin , Xu, Zhengquan , Chen, Jianzhang , Jia, Shan . B-DP: Dynamic Collection and Publishing of Continuous Check-In Data with Best-Effort Differential Privacy . | ENTROPY , 2022 , 24 (3) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
By combining randomized response with Laplace distribution, it obtains a new kind of differential privacy mechanism called Pseudo-Laplace mechanism. By analyzing the privacy and data availability of the mechanism, as well as an optimization problem that provides better privacy protection than the Laplace mechanism based solely on the Laplace distribution (traditional Laplace mechanism) under the same data availability, and the instantiations of the mechanism obtained in the approximate optimization algorithm, it finds that the mechanism could have almost the same privacy protection level in the middle and high privacy protection region (approximately © 2021 IEEE.
Keyword ：
Data privacy Data privacy Laplace transforms Laplace transforms Optimization Optimization
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Youqin , Xu, Zhengquan , Chen, Jianzhang . A Differential Privacy Mechanism Combining Randomized Response with Laplace Distribution [J]. | 2021 7th International Conference on Computer and Communications, ICCC 2021 , 2021 : 570-577 . |
| MLA | Chen, Youqin et al. "A Differential Privacy Mechanism Combining Randomized Response with Laplace Distribution" . | 2021 7th International Conference on Computer and Communications, ICCC 2021 (2021) : 570-577 . |
| APA | Chen, Youqin , Xu, Zhengquan , Chen, Jianzhang . A Differential Privacy Mechanism Combining Randomized Response with Laplace Distribution . | 2021 7th International Conference on Computer and Communications, ICCC 2021 , 2021 , 570-577 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Quantum maximum-distance-separable (MDS) codes form an important family of quantum codes. Quantum MDS codes are optimal, which can attain the quantum Singleton bound. In this paper, using some classes of constacyclic codes and Hermitian constructions, we propose the constructions of optimal quantum convolutional codes and optimal asymmetric quantum codes in the sense of the quantum Singleton bound. Compared with the codes obtained in the literature, the parameters of the constructed quantum codes are new as well as the distance of optimal asymmetric quantum codes [[n, k, d(z)/d(x)]](q2) constructed in this paper is larger.
Keyword ：
Asymmetric quantum codes Asymmetric quantum codes constacyclic codes constacyclic codes quantum convolutional codes quantum convolutional codes quantum Singleton bound quantum Singleton bound
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Jianzhang , Huang, Yuanyuan , Feng, Chunhui et al. Some families of optimal quantum codes derived from constacyclic codes [J]. | LINEAR & MULTILINEAR ALGEBRA , 2019 , 67 (4) : 725-742 . |
| MLA | Chen, Jianzhang et al. "Some families of optimal quantum codes derived from constacyclic codes" . | LINEAR & MULTILINEAR ALGEBRA 67 . 4 (2019) : 725-742 . |
| APA | Chen, Jianzhang , Huang, Yuanyuan , Feng, Chunhui , Chen, Riqing . Some families of optimal quantum codes derived from constacyclic codes . | LINEAR & MULTILINEAR ALGEBRA , 2019 , 67 (4) , 725-742 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In this paper, some families of asymmetric quantum codes and quantum convolutional codes that satisfy the quantum Singleton bound are constructed by utilizing constacyclic codes with length n = q(2+1)/10h, where q is an odd prime power with the form q = 10hm + t or q = 10hm + 10h - t, where m is a positive integer, and both h and t are odd with 10h = t(2) + 1 and t = 3. Compared with those codes constructed in the literature, the parameters of these constructed quantum codes in this paper are more general. Moreover, the distance dz of optimal asymmetric quantum codes [[n, k, d(z)/d(x)]](q2) here is larger than most of the ones given in the literature.
Keyword ：
Asymmetric quantum codes Asymmetric quantum codes Constacyclic codes Constacyclic codes Quantum convolutional codes Quantum convolutional codes Quantum Singleton bound Quantum Singleton bound
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Jianzhang , Chen, Youqin , Huang, Yuanyuan et al. New optimal asymmetric quantum codes and quantum convolutional codes derived from constacyclic codes [J]. | QUANTUM INFORMATION PROCESSING , 2019 , 18 (2) . |
| MLA | Chen, Jianzhang et al. "New optimal asymmetric quantum codes and quantum convolutional codes derived from constacyclic codes" . | QUANTUM INFORMATION PROCESSING 18 . 2 (2019) . |
| APA | Chen, Jianzhang , Chen, Youqin , Huang, Yuanyuan , Feng, Chunhui . New optimal asymmetric quantum codes and quantum convolutional codes derived from constacyclic codes . | QUANTUM INFORMATION PROCESSING , 2019 , 18 (2) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Generally, it is not easy to construct quantum maximal-distance-separable (MDS) codes with the minimum distance greater than q/2+1. The minimum distance of quantum MDS codes can achieve q/2+1 or exceed q/2+1 by adopting pre-shared entanglement. In this work, some new families of entanglement-assisted quantum MDS codes that satisfy the quantum Singleton bound are constructed and the number of maximally entangled states required is determined to make the minimum distance of some constructed codes achieve q/2+1 or exceed q/2+1 by utilizing the decomposition of the defining set and q(2)-cyclotomic cosets of constacyclic codes with length q(2)+1/gamma, where gamma = t(2) + 1, t is a power of 2 and q = t(e) > 4 with e 1 mod 4 or e 3 mod 4. Moreover, the parameters of these codes constructed in this paper are more general relative to the ones in the literature and the minimum distance of some codes constructed in this paper is larger than q/2+1.
Keyword ：
Constacyclic codes Constacyclic codes entanglement-assisted quantum codes entanglement-assisted quantum codes maximal-distance-separable (MDS) codes maximal-distance-separable (MDS) codes
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Jianzhang , Chen, Youqin , Yu, Dong et al. Applications of Constacyclic Codes to Some New Entanglement-Assisted Quantum MDS Codes [J]. | IEEE ACCESS , 2019 , 7 : 136641-136657 . |
| MLA | Chen, Jianzhang et al. "Applications of Constacyclic Codes to Some New Entanglement-Assisted Quantum MDS Codes" . | IEEE ACCESS 7 (2019) : 136641-136657 . |
| APA | Chen, Jianzhang , Chen, Youqin , Yu, Dong , Feng, Chunhui , Huang, Yuanyuan , Chen, Riqing . Applications of Constacyclic Codes to Some New Entanglement-Assisted Quantum MDS Codes . | IEEE ACCESS , 2019 , 7 , 136641-136657 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Although quantum maximal-distance-separable (MDS) codes that satisfy the quantum singleton bound have become an important research topic in the quantum coding theory, it is not an easy task to search for quantum MDS codes with the minimum distance that is larger than (q/2) + 1. The pre-shared entanglement between the sender and the receiver can improve the minimum distance of quantum MDS codes such that the minimum distance of some constructed codes achieves (q/2) + 1 or exceeds (q/2) + 1. Meanwhile, how to determine the required number of maximally entangled states to make the minimum distance of quantum MDS codes larger than (q/2) + 1 is an interesting problem in the quantum coding theory. In this paper, we utilize the decomposition of the defining set and q(2)-cyclotomic cosets of constacyclic codes with the form q = alpha m + t or q = alpha m + alpha - t and n = (q(2) + 1/alpha) to construct some new families of entanglement-assisted quantum MDS codes that satisfy the entanglement-assisted quantum singleton bound, where q is an odd prime power and m is a positive integer, while both alpha and t are positive integers such that alpha = t(2) + 1. The parameters of these codes constructed in this paper are more general compared with the ones in the literature. Moreover, the minimum distance of some codes in this paper is larger than (q/2) + 1 or q + 1.
Keyword ：
constacyclic codes constacyclic codes Entanglement-assisted quantum codes Entanglement-assisted quantum codes maximal-distance-separable (MDS) codes maximal-distance-separable (MDS) codes
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Jianzhang , Chen, Youqin , Feng, Chunhui et al. Some New Classes of Entanglement-Assisted Quantum MDS Codes Derived From Constacyclic Codes [J]. | IEEE ACCESS , 2019 , 7 : 91679-91695 . |
| MLA | Chen, Jianzhang et al. "Some New Classes of Entanglement-Assisted Quantum MDS Codes Derived From Constacyclic Codes" . | IEEE ACCESS 7 (2019) : 91679-91695 . |
| APA | Chen, Jianzhang , Chen, Youqin , Feng, Chunhui , Huang, Yuanyuan , Chen, Riqing . Some New Classes of Entanglement-Assisted Quantum MDS Codes Derived From Constacyclic Codes . | IEEE ACCESS , 2019 , 7 , 91679-91695 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
