Deep Fuzzy Hashing Network for Efficient Image Retrieval
The DOI matches its Crossref record; 61 of the 64 references it cites were found in a registry or an index.
Abstract
Hashing methods for efficient image retrieval aim at learning hash functions that map similar images to semantically correlated binary codes in the Hamming space with similarity well preserved. The traditional hashing methods usually represent image content by hand-crafted features. Deep hashing methods based on deep neural network (DNN) architectures can generate more effective image features and obtain better retrieval performance. However, the underlying data structure is hardly captured by existing DNN models. Moreover, the similarity (either visually or semantically) between pairwise images is ambiguous, even uncertain, to be measured in the existing deep hashing methods. In this article, we propose a novel hashing method termed deep fuzzy hashing network (DFHN) to overcome the shortcomings of existing deep hashing approaches. Our DFHN method combines the fuzzy logic technique and the DNN to learn more effective binary codes, which can leverage fuzzy rules to model the uncertainties underlying the data. Derived from fuzzy logic theory, the generalized hamming distance is devised in the convolutional layers and fully connected layers in our DFHN to model their outputs, which come from an efficientxoroperation on given inputs and weights. Extensive experiments show that our DFHN method obtains competitive retrieval accuracy with highly efficient training speed compared with several state-of-the-art deep hashing approaches on two large-scale image datasets: CIFAR-10 and NUS-WIDE.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 2×
“Inspired by the powerful capability on visual representation [10], [35], [36], some deep hashing methods have been proposed [5], [20], [23], [24] to learn more effective hash codes by taking advantage of sophisticated DNNs.”
BackgroundMethodVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 2×
“Inspired by the powerful capability on visual representation [10], [35], [36], some deep hashing methods have been proposed [5], [20], [23], [24] to learn more effective hash codes by taking advantage of sophisticated DNNs.”
BackgroundMethodU-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“The major innovations in the CNN have been proposed since the remarkable classification performance achieved by AlexNet [10] trained on the large-scale ImageNet dataset [34].”
MethodDistinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589 · cited 2×
“Earlierworkcommonlyutilizes hand-crafted real-valued features [1], [2], [7]–[9] for image representations and rank the images in the database regarding their distances (e.g., Euclidian or cosine distance) to the query image in the feature space.”
BackgroundDensely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,395
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 1×
“, image classification [13], [14], object detection [15], image segmentation [16], image-text matching [17], etc.”
Background
Research works printed but not linked: 1
- krizhevsky, 0, ImagNet classification with deep convolutional neural networks, Proc Annu Conf Neural Inf Process Syst, 1106
Cited by
Items 101–200 of 341
POFMakeup: A style transfer method for Peking Opera makeup
Zhang, F., Liang, X., Sun, Y., Lin, M., Jin, X., & Zhao, H. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108459 · Cited by 12
Analysis of Content Based Image Retrieval using Deep Feature Extraction and Similarity Matching
Mathews, A., Sejal, N., & Venugopal, K. R. (2022) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2022.0131277 · Cited by 12
“While some of the algorithms identified approximate regions of the objects in an image using attention sub-network, focusing mainly on the foreground objects [13], image features extracted using deep hashing methods with deep neural networks (DNN) gave better image retrieval performance [14].”
MethodEstimating a 2D pose from a tiny person image with super-resolution reconstruction
Zhang, Z., Wan, L., Xu, W., & Wang, S. (2021) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2021.107192 · Cited by 15
A database of students’ spontaneous actions in the real classroom environment
Che, B., Li, X., Sun, Y., Yang, F., Liu, P., & Lu, W. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108075 · Cited by 12
Single shot multibox detector for honeybee detection
Cai, J., Makita, Y., Zheng, Y., Takahashi, S., Hao, W., & Nakatoh, Y. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108465 · Cited by 12
Privacy-preserving image retrieval based on additive secret sharing in cloud environment
Zhang, B., Xu, Y., Yan, Y., & Wang, Z. (2024) · Cluster Computing · doi:10.1007/s10586-023-04213-5 · Cited by 11
“Nevertheless, most approaches [13 and 14] that utilize CNN as feature extractors are primarily concerned with image and retrieval result privacy, neglecting the security of neural network models.”
Zhao, Z., Lü, W., Peng, X., Xing, L., Zhang, W., & Zheng, C. (2024) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2024.3419447 · Cited by 14
“Whether it’s on a smartphone, smart TV, or smart home appliance, these applications connect us with our devices, offering convenience, efficiency, and heightened interactivity [3], [4].”
Tian, W., Chen, Z., Shen, J., Huang, F., & Xu, L. (2021) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-021-03420-5 · Cited by 11
“Traditional applications include hydrographic survey, subsea engineering site selection, detection of underwater targets such as aircraft wrecks and shipwrecks, sediment classification, marine surveys, and marine science research (Wilken et al. 2019; Wang et al. 2016; Lu et al. 2018, 2020, 2021) .”
BackgroundDuCL: Dual-stage contrastive learning framework for Chinese semantic textual matching
Zuo, Y., Lü, W., Peng, X., Wang, S., Zhang, W., & Qiao, X. (2023) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108574 · Cited by 10
Cheng, Q., Guo, Q., & Gu, X. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120731 · Cited by 11
Extraction and analysis algorithms for Sanxingdui cultural relics based on hyperspectral imaging
Qiu, S., Zhang, P., Li, S., & Hu, B. (2023) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2023.108982 · Cited by 10
Joint Objective and Subjective Fuzziness Denoising for Multimodal Sentiment Analysis
Jiang, X., Xu, X., Lu, H., He, L., & Shen, H. T. (2024) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2024.3405541 · Cited by 15
Self-citationA new emotion analysis fusion and complementary model based on online food reviews
Li, Y., Xiaojun, Y., Liu, Y., Ruijun, L., & Qingyu, J. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.107679 · Cited by 10
Self-citationModality-specific matrix factorization hashing for cross-modal retrieval
Xiong, H., Ou, W., Yan, Z., Gou, J., Zhou, Q., & Wang, A. (2020) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-020-02177-7 · Cited by 10
“…2014; Singh and Gordon 2008; Wang and Lu 2013; Ding et al. 2016; Li et al. 2018) have been proposed for cross-modal retrieval, based on the assumption that the pairwise data should have the same latent semantic representation (Xu et al. 2017; Jacobs et al. 2012; Wang et al. 2016; Lu et al. 2020).”
BackgroundKoga, S., Hamamoto, K., Lu, H., & Nakatoh, Y. (2024) · Cognitive Robotics · doi:10.1016/j.cogr.2024.01.001 · Cited by 10
Self-citationRetractedFuzzy Multimodal Graph Reasoning for Human-Centric Instructional Video Grounding
Li, Y., Jiang, X., Xu, X., Lu, H., & Shen, H. T. (2024) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2024.3436030 · Cited by 9
“For example, Lu et al. [38] combined the fuzzy logic technique and the DNN to learn more effective binary codes, which can leverage fuzzy rules to model the uncertainties underlying the data.”
MethodSelf-citationA deep learning based interval type-2 fuzzy approach for image retrieval systems
Ghozzi, Y., Hamdani, T. M., Hagras, H., Ouahada, K., Chabchoub, H., & Alimi, A. M. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128251 · Cited by 11
Attention-enhanced and trusted multimodal learning for micro-video venue recognition
Wang, B., Huang, X., Cao, G., Yang, L., Wei, X., & Tao, Z. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108127 · Cited by 9
Query-Specific Embedding Co-Adaptation Improve Few-Shot Image Classification
Fu, W., Zhou, L., & Chen, J. (2023) · IEEE Signal Processing Letters · doi:10.1109/lsp.2023.3289761 · Cited by 9
“D EEP learning has achieved state-of-the-art performance in a wide range of vision tasks [1], [2], [3], [4].”
BackgroundZhou, Z., Ning, Y., Zhou, X., & Zheng, F. (2023) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2023.108838 · Cited by 9
Weakly-Supervised Semantic Segmentation Network With Iterative dCRF
Li, Y., Sun, J., & Li, Y. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3141107 · Cited by 9
“IMAGE semantic segmentation [1]–[3] is to segment pixels according to the different semantic meanings expressed in the image, and it is widely used in automatic driving [6], [7] and scene analysis [4], [5].”
BackgroundSelf-citationA circle chaos random search strategy particle swarm optimization with its application
Xiang, X., Yan, X., Gao, C., Zhu, S., Xi, M., & Gao, H. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108219 · Cited by 9
CBA-GAN: Cartoonization style transformation based on the convolutional attention module
Zhang, F., Zhao, H., Li, Y., Wu, Y., & Sun, X. (2023) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108575 · Cited by 9
“Cartoons are usually created by cartoonists through sketching [1-2], pencil drawing [3], or other artistic painting methods.”
BackgroundSelf-citationHR-Net: Point cloud registration with hierarchical coarse-to-fine regression network
Zhao, Y., Chen, L., Hu, B., Wang, H., & Ren, M. (2023) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2023.109056 · Cited by 9
MCCA-Net: Multi-color convolution and attention stacked network for Underwater image classification
Qu, P., Li, T., Li, G., Tian, Z., Xie, X., Zhao, W., Pan, X., & Zhang, W. (2022) · Cognitive Robotics · doi:10.1016/j.cogr.2022.08.002 · Cited by 10
Multi-granularity interaction model based on pinyins and radicals for Chinese semantic matching
Zhao, P., Lü, W., Wang, S., Peng, X., Jian, P., Wu, H., & Zhang, W. (2022) · World Wide Web · doi:10.1007/s11280-022-01037-y · Cited by 8
“In recent years, deep learning has been applied widely in various domains [19, 22, 35, 36], and has achieved great successes in semantic matching task [5, 14, 21, 42, 43].”
BackgroundSynergistic compensation for RGB-based blind color image watermarking to withstand JPEG compression
Hu, H.-T. (2023) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2023.103673 · Cited by 8
AUV Path Planning Based on the Flow Field Method and Dynamic Window Approach
Gao, X., Jia, D., Liu, X., Du, J., & Zhang, H. (2025) · IEEE Access · doi:10.1109/access.2025.3570790 · Cited by 8
Research on image super-resolution algorithm based on mixed deep convolutional networks
Zuo, J., Wang, Z., Zhang, Y., Yan, Z., Zhao, Y., & Chen, Y. (2021) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2021.107422 · Cited by 8
RETRACTED: Identification and retrieval of medicinal plants of Southern India using EfficientB4Net
Uma, K., Bama, B. S., Sabarinathan, D., & Roomi, S. M. M. (2022) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-211426 · Cited by 8
RetractedSingle-branch self-supervised learning with hybrid tasks
Zhao, W., Pan, X., Xu, Y., & Yang, H. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108168 · Cited by 8
Xing, L., Jin, H., Li, H.-A., & Li, Z. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108270 · Cited by 8
3D Object detector: A multiscale region proposal network based on autonomous driving
Chen, X., Yang, S., Li, Y., Li, Y., & Nakatoh, Y. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108412 · Cited by 9
Self-citationUnsupervised domain adaptation based on adaptive local manifold learning
Shi, K., Liu, Z., Lü, W., Ou, W., & Yang, C. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.107941 · Cited by 7
Pmir: an efficient privacy-preserving medical images search in cloud-assisted scenario
Li, D., Yan-ling, W., Lü, Q., Zhang, K., Wang, Z., & Wu, J. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-09118-3 · Cited by 7
Gesture formation: A crucial building block for cognitive-based Human–Robot Partnership
Morasso, P. (2021) · Cognitive Robotics · doi:10.1016/j.cogr.2021.06.004 · Cited by 7
A hashtag-based sub-event detection framework for social media
Lu, G., Mu, Y., Gu, J., Kouassi, F. A. P., Lu, C., Wang, R., & Chen, A. (2021) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2021.107317 · Cited by 7
GR-LO: A specific lidar odometry system optimized with ground and road edges
Chen, L., Hu, B., Xu, F., & Ren, M. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108258 · Cited by 7
Blind Watermarking for Hiding Color Images in Color Images with Super-Resolution Enhancement
Hu, H.-T., Hsu, L.-Y., & Wu, S.-T. (2022) · Sensors · doi:10.3390/s23010370 · Cited by 7
“, text, images, audio, and video), color images are the most frequently used data on openly accessible network platforms [1,2].”
BackgroundLiu, Y., Han, Z., Liu, X., Wang, J., Wang, C., & Liu, R. (2023) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2023.108696 · Cited by 7
Li, X., Mo, H., & Liu, F. (2023) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2023.108841 · Cited by 7
Remaining lifespan prediction on multiple types of hard disks under conditions of data imbalance
Wang, Q., Wang, X., Wang, F., Liu, H., Gou, J., & Chen, W. (2024) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2024.109195 · Cited by 7
SOM-based binary coding for single sample face recognition
Liu, F., Wang, F., Ding, Y., & Yang, S. (2021) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-021-03255-0 · Cited by 7
“Artificial intelligence methods have been applied in various fields, such as image retrieval (Lu et al. 2020a), unmanned aerial vehicles (Lu et al. 2017), vehicle communications (Lu et al. 2020b), blockchain (Singh et al. 2020) and underwater image dehazing (Serikawa and Lu 2014).”
MethodPPIS-JOIN: A Novel Privacy-Preserving Image Similarity Join Method
Zhang, C., Xie, F., Yu, H., Zhang, J., Zhu, L., & Li, Y. (2021) · Neural Processing Letters · doi:10.1007/s11063-021-10537-3 · Cited by 9
Self-citationLabel embedding semantic-guided hashing
Long, J., Sun, L., Lin, G., Hua, L., & Yang, Z. (2022) · Neurocomputing · doi:10.1016/j.neucom.2021.12.073 · Cited by 7
Intelligent Based Waste Management Awareness Developed by Transfer Learning
Mridha, K., Shaw, R. N., & Ghosh, A. (2021) · IEEE International Conference on Computing, Power and Communication Technologies (IC2PCT) · doi:10.1109/gucon50781.2021.9573586 · Cited by 7
Regional attention reinforcement learning for rapid object detection
Yao, H., Dong, P., Cheng, S., Yu, J., & Jiang, H. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.107747 · Cited by 8
Obstacle Avoidance Capability for Multi-Target Path Planning in Different Styles of Search
Alhassow, M. M., Ata, O., & Atilla, D. Ç. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.055592 · Cited by 6
Vibration-based terrain classification recognition using a six-axis accelerometer
Liu, R., Zhang, B., Yu, Z., Han, Z., Wu, J., & Wang, T. (2021) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2021.107556 · Cited by 6
Aesthetic image captioning on the FAE-Captions dataset
Jin, X., Lv, J., Zhou, X., Xiao, C., Li, X., & Zhao, S. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.107866 · Cited by 6
Verifiable speech retrieval algorithm based on KNN secure hashing
Li, A., Huang, Y., & Zhang, Q. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13387-w · Cited by 6
“[21] proposed a deep fuzzy hash network (DFHN), which combines fuzzy logic technology and DNN to learn more effective binary codes.”
A new direct acyclic graph task scheduling method for heterogeneous Multi-Core processors
Xiao, F., Shushan, C., Xingxing, H., Shujuan, H., & Wenjuan, Z. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108464 · Cited by 6
Lü, W., Zhao, P., Li, Y., Wang, S., Huang, H., Shi, S., & Wu, H. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.109795 · Cited by 6
Self-citationMerging Grid Maps in Diverse Resolutions by the Context-based Descriptor
Lin, Z., Zhu, J., Jiang, Z., Li, Y., Li, Y., & Li, Z. (2021) · ACM Transactions on Internet Technology · doi:10.1145/3403948 · Cited by 6
“[ 17, 27, 28].”
Self-citationZhou, Z., Qiu, F., Zheng, F., & Ye, M. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108093 · Cited by 6
PET-CT image Co-segmentation of lung tumor using joint level set model
Chen, Z., Qiu, N., Feng, H. J., & Dai, D. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108545 · Cited by 6
Deep Semantic Tuplet-Based Hashing by Hypergraph Modeling for Cross-Modal Retrieval
Qin, Q., Wu, L., Zhang, W., Zhang, H., Huang, L., & Nie, J. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3623497 · Cited by 7
“Additionally, depending on the utilization of label information, cross-modal hashing is further divided into supervised cross-modal hashing and unsupervised cross-modal hashing [2], [10], [16], [17].”
Fixed/Prescribed-Time Synchronization of Hybrid Delayed Fuzzy Inertial Memristive Neural Networks
Wang, X., Chen, G., Wen, S., Wang, L., & Hu, J. (2025) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2025.3635786 · Cited by 5
Similarity Retrieval Based on Image Background Analysis
Zhu, C., Jiang, W., Zhou, W., & Xiao, H. Y. (2022) · International Journal of Software Science and Computational Intelligence · doi:10.4018/ijssci.309426 · Cited by 5
Dureja, A., & Pahwa, P. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13991-w · Cited by 5
“The most commonly used technique of image retrieval process is content filtering and consecutive filtering [16, 18].”
MethodZhao, D. (2023) · Cognitive Robotics · doi:10.1016/j.cogr.2023.08.002 · Cited by 5
Guo, C., Li, X., Ma, J., Li, Y., Liu, Y., Qi, H., Zhang, L., & Jin, Y. (2024) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2024.3425664 · Cited by 8
Self-citationUsing EGDL to represent domain knowledge for imperfect information automated negotiations
Lv, Y., Zhu, J., & Jiang, Y. (2020) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-020-02274-7 · Cited by 5
“The existing work proposes a good negotiation mechanism for automatic negotiation (Lu et al. 2020).”
BackgroundMulti-feature fusion point cloud completion network
Chen, X., Li, Y., & Li, Y. (2021) · World Wide Web · doi:10.1007/s11280-021-00938-8 · Cited by 5
“Nowadays, artificial intelligence is developing rapidly [12–16, 25, 29, 38–40].”
BackgroundSelf-citationRM-IQA: A new no-reference image quality assessment framework based on range mapping method
Yuan, T., Li, C., Tian, L., & Li, G. (2021) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2021.107508 · Cited by 5
Projective Fisher Information for Natural Gradient Descent
Kaul, P., & Lall, B. (2022) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2022.3153593 · Cited by 5
“Deep learning architectures have recently been extended to new problem domains like deep fuzzy hashing networks [24] for image retrieval and reinforcement learning [25] for a variety of tasks including anomaly detection [26].”
BackgroundAdaptive 2D skeleton deformation based on view agnostic network for action recognition
Dong, Q., & Zhong, X. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108112 · Cited by 5
Breast Ultrasound Tumor Detection Based on Active Learning and Deep Learning
Liu, G., Tan, J., Yang, H., Li, Y., Sun, X. H., Wu, J., & Luo, B. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-7946-0_1 · Cited by 5
Self-citationWan, Y., Jia, S., Li, Y., Wang, R., Guo, K., Wang, M., & Liu, R. (2023) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2023.109011 · Cited by 5
Self-citationRepresentation separation adversarial networks for cross-modal retrieval
Deng, J., Ou, W., Gou, J., Song, H., Wang, A., & Xu, X. (2020) · Wireless Networks · doi:10.1007/s11276-020-02382-4 · Cited by 5
Self-citationResearch on improved hough algorithm and its application in lunar crater
Zhou, L., & Li, L. (2021) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-189707 · Cited by 5
Wang, S., Ge, H., Gou, J., Ou, W., Yin, H.-F., & Su, S. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.107684 · Cited by 5
Semantic Constraints Matrix Factorization Hashing for cross-modal retrieval
Li, W., Xiong, H., Ou, W., Gou, J., Deng, J., Liang, L., & Zhou, Q. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.107842 · Cited by 5
Cycle-autoencoder based block-sparse joint representation for single sample face recognition
Liu, F., Wang, F., Wang, Y., Zhou, J. W., & Xu, F. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108003 · Cited by 5
Disentangling latent space better for few-shot image-to-image translation
Liu, P., Wang, Y., Du, A., Zhang, L., Wei, B., Gu, Z., Wang, X., Zheng, H., & Li, J. (2022) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-022-01552-4 · Cited by 5
“However,in many situations,a data distribution is extremely imbalanced [2, 11, 12, 15, 28, 34] and one of the two domains usually has only a few (e.”
BackgroundResearch on wireless spectrum allocation and utility evaluation of cross-domain multi-slot radio
Li, X., Liu, W., & Zhu, J. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108329 · Cited by 5
Xu, Q., Wang, L., Liu, H., & Liu, N. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-7943-9_11 · Cited by 5
STRDD: Scene Text Removal with Diffusion Probabilistic Models
Yang, W., Liu, H., & Liu, N. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-7943-9_13 · Cited by 4
Zhang, Y., Wang, M., Wang, F., Guo, J., & Sui, X. (2024) · Fractal and Fractional · doi:10.3390/fractalfract8110637 · Cited by 4
“At the same time, it can be foreseen that the application prospects of fuzzy systems will be broader with the continuous application of fuzzy systems to other fields, such as in image recognition [22], natural language processing [23] and other fields.”
Recent advances in content based image retrieval using deep learning techniques: A survey
Ahmed, A. S. F., & Ibraheem, I. N. (2024) · AIP conference proceedings · doi:10.1063/5.0236594 · Cited by 4
Ou, W., Chen, Y., Liang, L., Gou, J., Xiong, J., Zhang, J., Lai, L., & Zhang, L. (2025) · Multimedia Systems · doi:10.1007/s00530-024-01649-6 · Cited by 4
“The first category is the hash mapping method, which typically represents the feature information of both the image and report using hash codes generated through data mapping [32, 36, 47, 48].”
Extend auction description language to represent and reason knowledge in auctions
Xu, Z., & Zhu, J. (2021) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2021.107595 · Cited by 4
Adversarial Watermark Based Image Privacy Protection Algorithm
Cao, Y., Lu, M., Li, S., Zhuang, Y., & Yang, A. (2022) · International Conference on Consumer Electronics and Computer Engineering (ICCECE) · doi:10.1109/iccece54139.2022.9712846 · Cited by 4
“Recent studies [2-5] have shown that deep neural networks (DNNs) employed in content-based image retrieval (CBIR) tasks can successfully obtain more compact image features to calculate similarities between images.”
BackgroundDeng, S., & Yuan, Y. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.052008 · Cited by 4
Estimation model of leaf nitrogen content based on GEP and leaf spectral reflectance
Yang, L., Deng, S., Ma, S., & Xiao, F. (2021) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2021.107648 · Cited by 4
Inspection route prediction in substation using long short-term memory networks
Yang, Y., Yang, F., & Wu, H. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.107680 · Cited by 4
Approximate Nearest Neighbor Search Using Enhanced Accumulative Quantization
Ai, L., Cheng, H., Wang, X., Chen, C., Liu, D., Zheng, X., & Wang, Y. (2022) · Electronics · doi:10.3390/electronics11142236 · Cited by 4
Cascaded multi-3D-view fusion for 3D-oriented object detection
Sun, J., Xu, J., Ji, Y., Wu, F., & Sun, Y. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108312 · Cited by 4
Device-Free Indoor Localization Based on Kernel Dictionary Learning
Jiang, Y., Tan, B., Ding, S., Chen, X., & Li, Y. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3314441 · Cited by 4
“Radar [5], [6], [7], [8], ultrasonic [9], [10], [11], and other location methods [12], [13], [14], [15], [16], [17] are commonly used for DFL.”
MethodSelf-citationCao, G. (2024) · Communications in computer and information science · doi:10.1007/978-981-99-9109-9_35 · Cited by 4
Feature mixing and self-training for source-free active domain adaptation
Tian, Q., & Zhang, H. (2023) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2023.108966 · Cited by 3
Shen, Y., Liang, J., Kang, H., Sun, X., & Chen, Q. (2025) · Symmetry · doi:10.3390/sym17020153 · Cited by 3
Automatic small target detection in complex background: a state of-the-art survey
Ding, Y., Wang, Z., Li, B., Xu, G., & Deng, L. (2021) · International Symposium on Artificial Intelligence and Robotics (ISAIR) · doi:10.1117/12.2607142 · Cited by 3
“The relational graph between structural element of new Top-hat New Top-hat Opening and Closing Operations is, ff█BBooii(xx,yy) = (ff ⊕ ΔBB)⨀BBbb (8) ff□BBooii(xx,yy) = (ff⨀ΔBB) ⊕BBbb (9) The black hat and white hat that define the new top hat transformation is, NWTH(xx,yy) = ff(xx,yy) − min(ff█BBooii(xx,yy), ff(xx,yy)…”
BackgroundA Semi-supervised Road Segmentation Method for Remote Sensing Image Based on SegFormer
Ma, T., Zhou, X., Xi, R., Yang, J., Zhang, J., & Li, F. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-7943-9_16 · Cited by 3
Keyframe control for customizable choreography with style maintenance
Hu, M., Fan, D., Wan, L., Xu, W., & Wang, S. (2024) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2024.109267 · Cited by 3
PAIR: Pre-denosing Augmented Image Retrieval Model for Defending Adversarial Patches
Zhou, Z., Wang, P., Liang, Z., Zhang, R., & Haitao, B. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681398 · Cited by 5
“Deep neural networks are widely used in a variety of multimedia retrieval tasks, including content-based image retrieval [21, 22, 28] and text-based image retrieval [31, 36].”
A Study on the Selection of Performance Evaluation Metrics for Machine Learning Methods
Zhang, X., Sun, Y., & Xue, H. (2024) · International Conference on Computer, Big Data and Artificial Intelligence (ICCBD+AI) · doi:10.1109/iccbd-ai65562.2024.00081 · Cited by 3
“The Hemming distance [14] is used in scenarios where multiple labels of a sample need to be classified.”
Residual Fuzzy Alignment on Hypergraph for Open-Set 3D Cross-Modal Retrieval
Xu, Y., Feng, Y., Zhuang, X., Wang, J., Wu, Z., & Gao, Y. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3599081 · Cited by 4
“DFHN [58] is proposed for image retrieval tasks by combining fuzzy logic to address the challenges in deep hash networks.”
Colour Neural Descriptors for Instance Retrieval Using CNN Features and Colour Models
Saikia, S., Fernández-Robles, L., Fidalgo, E., & Alegre, E. (2021) · IEEE Access · doi:10.1109/access.2021.3056330 · Cited by 3
“Recently, to learn more effective binary codes, in [45], a new hashing method termed as DeepFuzzy Hashing Network is proposed, and Chen et al .”
MethodEssential multi-view graph learning for clustering
Ma, S., Zheng, Q., & Liu, Y. (2021) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-021-03002-5 · Cited by 3
Metadata
- Authors
- Lu, H., Zhang, M., Xu, X., Li, Y., & Shen, H. T.
- Affiliations
- Kyushu Institute of Technology (JP)
- University of Electronic Science and Technology of China (CN)
- Venue
- IEEE Transactions on Fuzzy Systems
- Published
- 2021-01
- Volume
- 29
- Issue
- 1
- Pages
- 166-176
- ISSN
- 1063-6706 (ISSN-L)
- 1941-0034
- OpenAlex
- W3014847672
- Cited by
- 340
- References
- 64
- Citations by year
- 2026: 9 · 2025: 31 · 2024: 52 · 2023: 38 · 2022: 139 · 2021: 63
- FWCI
- 24.11
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Fuzzy Systems (publishedVersion)
- Funders
- National Key Research and Development Program of China (2018AAA0102200)
- National Natural Science Foundation of China (61976049, 61632007)
- Leading Initiative for Excellent Young Researchers of Ministry of Education, Culture, Sports, Science and Technology, Japan (16809746)
- Sichuan Science and Technology Program, China (2019ZDZX0008, 2018GZDZX0032)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- deep hashing, image retrieval, fuzzy logic, binary codes, Hamming space, fuzzy rules, uncertainty modeling, convolutional layers, XOR operation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.