Pattern Recognition

Papers
(The median citation count of Pattern Recognition is 7. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 250 papers]. The publications cover those that have been published in the past four years, i.e., from 2021-05-01 to 2025-05-01.)
ArticleCitations
Editorial Board324
Retraction Notice311
A cross-network node classification method in open-set scenario267
Cross-modal co-feedback cellular automata for RGB-T saliency detection246
Effective action recognition with embedded key point shifts222
Holistic word descriptor for lexicon reduction in handwritten arabic documents219
Progressive downsampling and adaptive guidance networks for dynamic scene deblurring207
Distance-aware network for physical-world object distribution estimation and counting192
Robust multilayer bootstrap networks in ensemble for unsupervised representation learning and clustering184
FastOPM—A practical method for partial match of time series183
Two phase cooperative learning for supervised dimensionality reduction183
A neighborhood-based method for mining and fusing positive and negative false samples183
Deep graph matching meets mixed-integer linear programming: Relax or not ?174
Looking beyond input frames: Self-supervised adaptation for video super-resolution169
Privileged multi-task learning for attribute-aware aesthetic assessment163
An entity-weights-based convolutional neural network for large-sale complex knowledge embedding161
A Sampling-Based Density Peaks Clustering Algorithm for Large-Scale Data160
Occlusion-guided multi-modal fusion for vehicle-infrastructure cooperative 3D object detection160
Fast adaptively balanced min-cut clustering149
DA-GAN: Dual-attention generative adversarial networks for real-world exquisite makeup transfer141
Knowledge memorization and generation for action recognition in still images138
Synthetic unknown class learning for learning unknowns138
Sketches by MoSSaRT: Representative selection from manifolds with gross sparse corruptions135
Phase Randomization: A data augmentation for domain adaptation in human action recognition134
DCFusion: Difference correlation-driven fusion mechanism of infrared and visible images133
CORE: Learning consistent ordinal representations with convex optimization for image ordinal estimation133
Leveraging tensor kernels to reduce objective function mismatch in deep clustering130
Extrinsic kernel ridge regression classifier for Kendall’s planar shape space126
Thermal to Visual Person Re-Identification Using Collaborative Metric Learning Based on Maximum Margin Matrix Factorization125
Kinship verification using multi-level dictionary pair learning for multiple resolution images124
Hyper-feature aggregation and relaxed distillation for class incremental learning122
DynamicKD: An effective knowledge distillation via dynamic entropy correction-based distillation for gap optimizing119
Robust Table Detection and Structure Recognition from Heterogeneous Document Images117
Sequence patterns and HMM profiles to predict proteome wide zinc finger motifs116
Mutual Domain Adaptation113
Cascaded learning with transformer for simultaneous eye landmark, eye state and gaze estimation113
MTS2Graph: Interpretable multivariate time series classification with temporal evolving graphs112
Unsupervised update summarization of news events110
A modified interval type-2 Takagi-Sugeno fuzzy neural network and its convergence analysis109
Crossover-Net: Leveraging vertical-horizontal crossover relation for robust medical image segmentation109
A dense light field reconstruction algorithm for four-dimensional optical flow constraint equation109
Multi-task meta label correction for time series prediction109
Improving the Facial Expression Recognition and Its Interpretability via Generating Expression Pattern-map107
An illumination-guided dual attention vision transformer for low-light image enhancement106
PSCFormer: A lightweight hybrid network for gas identification in electronic nose system106
Enhanced visible–infrared person re-identification based on cross-attention multiscale residual vision transformer105
Intensity mixture and band-adaptive detail fusion for pansharpening105
Switching clusters’ synchronization for discrete space-time complex dynamical networks via boundary feedback controls104
Support subsets estimation for support vector machines retraining103
SARS-Net: COVID-19 detection from chest x-rays by combining graph convolutional network and convolutional neural network102
Identifying the key frames: An attention-aware sampling method for action recognition101
Bounded exponential loss function based AdaBoost ensemble of OCSVMs100
Unsupervised person re-identification via multi-domain joint learning99
DM-GAN: CNN hybrid vits for training GANs under limited data98
A generalized multi-aspect distance metric for mixed-type data clustering97
Temporal sparse adversarial attack on sequence-based gait recognition97
RESKM: A General Framework to Accelerate Large-Scale Spectral Clustering96
eX-ViT: A Novel explainable vision transformer for weakly supervised semantic segmentation93
Distribution alignment for cross-device palmprint recognition92
Deep reinforcement learning with credit assignment for combinatorial optimization91
Bi-Attention enhanced representation learning for image-text matching91
Adapt only once: Fast unsupervised person re-identification via relevance-aware guidance88
GriT-DBSCAN: A spatial clustering algorithm for very large databases87
Pseudo-labeling with keyword refining for few-supervised video captioning87
Dynamic selection for reconstructing instance-dependent noisy labels87
Consistency-driven feature scoring and regularization network for visible–infrared person re-identification87
Inter-Attribute awareness for pedestrian attribute recognition86
Robust deep fuzzy K-means clustering for image data86
Explainable AI in human motion: A comprehensive approach to analysis, modeling, and generation84
BiconNet: An edge-preserved connectivity-based approach for salient object detection84
Adaptive, Hybrid Feature Selection (AHFS)84
FoCL: Feature-oriented continual learning for generative models84
Generalization capacity of multi-class SVM based on Markovian resampling84
SpatioTemporal focus for skeleton-based action recognition83
LCU-Net: A novel low-cost U-Net for environmental microorganism image segmentation83
Dynamic feature fusion with spatial-temporal context for robust object tracking83
Head pose estimation using deep neural networks and 3D point clouds83
TBConvL-Net: A hybrid deep learning architecture for robust medical image segmentation83
Offline signature verification using a region based deep metric learning network82
Supervised penalty-based aggregation applied to motor-imagery based brain-computer-interface79
ANNE: Adaptive Nearest Neighbours and Eigenvector-based sample selection for robust learning with noisy labels79
A Dual Self-Attention mechanism for vehicle re-Identification79
Deep and wide nonnegative matrix factorization with embedded regularization78
Dynamic weighted knowledge distillation for brain tumor segmentation78
A landmark-free approach for automatic, dense and robust correspondence of 3D faces77
A unified framework for unsupervised action learning via global-to-local motion transformer77
Mix-ViT: Mixing attentive vision transformer for ultra-fine-grained visual categorization77
Indefinite twin support vector machine with DC functions programming77
Privacy-preserving speaker verification system using Ranking-of-Element hashing76
A kernel path algorithm for general parametric quadratic programming problem75
Stain-adaptive self-supervised learning for histopathology image analysis75
BEST: Building evidences from scattered templates for accurate contactless palmprint recognition75
Jointly learning compact multi-view hash codes for few-shot FKP recognition75
Mitigate the classification ambiguity via localization-classification sequence in object detection74
GraphXCOVID: Explainable deep graph diffusion pseudo-Labelling for identifying COVID-19 on chest X-rays73
Table representation learning using heterogeneous graph embedding72
Weighting and pruning based ensemble deep random vector functional link network for tabular data classification72
Efficient federated multi-view learning71
Checklist for responsible deep learning modeling of medical images based on COVID-19 detection studies71
Homogeneous and heterogeneous relational graph for visible-infrared person re-identification71
Feature-matching method based on keypoint response constraint using binary encoding of phase congruency70
Towards Automatic Model Compression via a Unified Two-Stage Framework70
A uniform representation model for OCT-based fingerprint presentation attack detection and reconstruction69
Bayesian mixture of gaussian processes for data association problem69
Marginal debiased network for fair visual recognition68
Trajectory-User Linking via Multi-Scale Graph Attention Network68
Progressive modality-complement aggregative multitransformer for domain multi-modal neural machine translation67
Sparse and robust support vector machine with capped squared loss for large-scale pattern classification67
Consistency and label constrained transfer low-rank representation for cross-light finger vein recognition67
Image analysis by fractional-order weighted spherical Bessel-Fourier moments67
Table Structure Recognition and Form Parsing by End-to-End Object Detection and Relation Parsing66
Feature decoupling and regeneration towards wifi-based human activity recognition66
Binary feature learning with local spectral context-aware attention for classification of hyperspectral images65
Robust image hiding network with Frequency and Spatial Attentions64
Investigating the effectiveness of data augmentation from similarity and diversity: An empirical study63
Multi-proxy feature learning for robust fine-grained visual recognition62
Learning a bi-directional discriminative representation for deep clustering62
Linearized alternating direction method of multipliers for elastic-net support vector machines62
Collaborative contrastive learning for cross-domain gaze estimation61
Not All Samples Are Born Equal: Towards Effective Clean-Label Backdoor Attacks61
Local-enhanced representation for text-based person search61
Deep contrastive representation learning for supervised tasks61
Editorial Board60
Elucidating robust learning with uncertainty-aware corruption pattern estimation60
PSSS-EEG: A Probabilistic-masking Self-Supervised Swin-transformer model for EEG-based drowsiness recognition60
Generalization of deep learning models for natural gas indication in 2D seismic data60
Practical protection against video data leakage via universal adversarial head60
Metaheuristic Search Based Feature Selection Methods for Classification of Cancer59
Cross-scene foreground segmentation with supervised and unsupervised model communication59
Early gesture detection in untrimmed streams: A controlled CTC approach for reliable decision-making59
A spatially constrained skew Student’s-t mixture model for brain MR image segmentation and bias field correction59
Deep evidential clustering based on feature representation learning and belief function theory59
Graph Attentive Dual Ensemble learning for Unsupervised Domain Adaptation on point clouds59
OpenInst: A simple query-based method for open-world instance segmentation59
Robust sparse and low-redundancy multi-label feature selection with dynamic local and global structure preservation58
Semantic perceptive infrared and visible image fusion Transformer58
Super-encoder with cooperative autoencoder networks58
Towards better long-tailed oracle character recognition with adversarial data augmentation58
Human interaction recognition framework based on interacting body part attention58
Estimating fund-raising performance for start-up projects from a market graph perspective57
Multivariate time series clustering based on complex network57
Methods for segmenting cracks in 3d images of concrete: A comparison based on semi-synthetic images57
A survey of robust adversarial training in pattern recognition: Fundamental, theory, and methodologies57
TreEnhance: A tree search method for low-light image enhancement56
Joint multi-label learning and feature extraction for temporal link prediction56
Learning sequentially diversified representations for fine-grained categorization56
IMCSN: An improved neighborhood aggregation interaction strategy for multi-scale contrastive Siamese networks56
GDB: Gated Convolutions-based Document Binarization56
A multi-resolution self-supervised learning framework for semantic segmentation in histopathology56
Geometric-inspired graph-based Incomplete Multi-view Clustering55
Multi-modal brain tumor segmentation via disentangled representation learning and region-aware contrastive learning55
Driver multi-task emotion recognition network based on multi-modal facial video analysis54
Generating Transferable Adversarial Examples for Speech Classification54
Multi scale pixel attention and feature extraction based neural network for image denoising54
A survey of human-computer interaction (HCI) & natural habits-based behavioural biometric modalities for user recognition schemes54
Auto-attention mechanism for multi-view deep embedding clustering53
Editorial Board53
Center Prediction Loss for Re-identification53
Cross-View kernel transfer53
A novel relation aware wrapper method for feature selection53
Region-wise loss for biomedical image segmentation53
Online portfolio selection with predictive instantaneous risk assessment53
PDRLRR: A novel low-rank representation with projection distance regularization via manifold optimization for clustering52
TCFAP-Net: Transformer-based Cross-feature Fusion and Adaptive Perception Network for large-scale point cloud semantic segmentation52
End-to-end kernel learning via generative random Fourier features52
Editorial Board52
ERAT:Eyeglasses removal with attention52
Mutual information regularized identity-aware facial expression recognition in compressed video51
BDNet: A BERT-based dual-path network for text-to-image cross-modal person re-identification51
Weak segmentation supervised deep neural networks for pedestrian detection51
ELSED: Enhanced line SEgment drawing51
Mathematical formula detection in document images: A new dataset and a new approach51
Learning discriminative feature representation with pixel-level supervision for forest smoke recognition51
Co-regularized optimal high-order graph embedding for multi-view clustering51
Hybrid-context-based multi-prior entropy modeling for learned lossless image compression50
Distributional and spatial-temporal robust representation learning for transportation activity recognition50
Joint spatial and scale attention network for multi-view facial expression recognition50
Learning to match features with discriminative sparse graph neural network49
Fully context-aware image inpainting with a learned semantic pyramid49
Consensus Incomplete Multi-View Clustering with Nonconvex Tensor Smooth Graph Learning49
Contrastive Generative Network with Recursive-Loop for 3D point cloud generalized zero-shot classification49
Scene Chinese Recognition with Local and Global Attention49
Weakly privileged learning with knowledge extraction49
A recurrent graph neural network for inductive representation learning on dynamic graphs49
Weighted clustering: Towards solving the user’s dilemma49
A review of deep-learning-based super-resolution: From methods to applications48
Retinal image enhancement with artifact reduction and structure retention48
Hiding multiple images into a single image via joint compressive autoencoders48
Exploring target-related information with reliable global pixel relationships for robust RGB-T tracking48
Hybrid routing transformer for zero-shot learning48
Coordinating explicit and implicit knowledge for knowledge-based VQA48
Expecting individuals’ body reaction to Covid-19 based on statistical Naïve Bayes technique48
Non-negative Tucker decomposition with graph regularization and smooth constraint for clustering48
MFSNet: A multi focus segmentation network for skin lesion segmentation48
Discriminative feature generation for classification of imbalanced data48
Crowd counting from single images using recursive multi-pathway zooming and foreground enhancement48
Arbitrary Order Total Variation for Deformable Image Registration47
Low-resolution human pose estimation47
Dynamic and reliable subtask tracker with general schatten p-norm regularization47
Doubly contrastive representation learning for federated image recognition47
Corrigendum to ‘Toward a Blind Image Quality Evaluator in the Wild by Learning beyond Human Opinion Scores’ Pattern Recognition. Volume 137 (2023) 10929647
Leveraging Transformer-based autoencoders for low-rank multi-view subspace clustering46
IRCNN: A novel signal decomposition approach based on iterative residue convolutional neural network46
Few pixels attacks with generative model46
Joint Intra-view and Inter-view Enhanced Tensor Low-rank Induced Affinity Graph Learning46
Coarse is better? A new pipeline towards self-supervised learning with uncurated images46
Rotation invariant point cloud analysis: Where local geometry meets global topology46
Deep neural network compression through interpretability-based filter pruning46
Editorial Board46
Example-based color transfer with Gaussian mixture modeling46
FeverNet: Enabling accurate and robust remote fever screening46
Versatile, full‐spectrum, and swift network sampling for model generation46
CPSS-FAT: A consistent positive sample selection for object detection with full adaptive threshold45
Rethinking convolutional neural networks for trajectory refinement45
Reconstruction regularized low-rank subspace learning for cross-modal retrieval45
Support structure representation learning for sequential data clustering45
Mixed-order spectral clustering for complex networks45
WB-LRP: Layer-wise relevance propagation with weight-dependent baseline44
Non-residual unrestricted pruned ultra-faster line detection for edge devices44
Dynamic and static mutual fitting for action recognition44
Poincaré Fréchet mean44
A deformable CNN-based triplet model for fine-grained sketch-based image retrieval44
Generalized pyramid co-attention with learnable aggregation net for video question answering43
Hierarchical Context Learning of object components for unsupervised semantic segmentation43
Efficient search of comprehensively robust neural architectures via multi-fidelity evaluation43
Temporal segment dropout for human action video recognition43
ResPrune: An energy-efficient restorative filter pruning method using stochastic optimization for accelerating CNN43
Cascaded feature fusion with multi-level self-attention mechanism for object detection42
A novel hybrid decoding neural network for EEG signal representation42
Federated learning for medical image analysis: A survey42
Real masks and spoof faces: On the masked face presentation attack detection42
An empirical study of the impact of masks on face recognition42
ADCNN: Towards learning adaptive dilation for convolutional neural networks42
NCL++: Nested Collaborative Learning for long-tailed visual recognition41
Compressing spectral kernels in Gaussian Process: Enhanced generalization and interpretability41
Robust and privacy-preserving feature extractor for perturbed images41
Siamese networks with an online reweighted example for imbalanced data learning41
GlobalAP: Global average precision optimization for person re-identification41
Multi-attention augmented network for single image super-resolution41
Supervised contrastive deep Q-Network for imbalanced radar automatic target recognition41
Recursive multi-model complementary deep fusion for robust salient object detection via parallel sub-networks41
A Comprehensive Survey of Image Augmentation Techniques for Deep Learning41
A novel GCN-based point cloud classification model robust to pose variances41
Multi-feature deep information bottleneck network for breast cancer classification in contrast enhanced spectral mammography41
An effective multi-scale interactive fusion network with hybrid Transformer and CNN for smoke image segmentation41
Semi-supervised multi-Layer convolution kernel learning in credit evaluation41
Understanding the vulnerability of skeleton-based Human Activity Recognition via black-box attack40
Collaborative boundary-aware context encoding networks for error map prediction40
Image inpainting via spatial projections40
Certainty weighted voting-based noise correction for crowdsourcing40
0.053125143051147