Pattern Recognition

Papers
(The median citation count of Pattern Recognition is 9. 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 2021-11-01 to 2025-11-01.)
ArticleCitations
Self-supervised video object segmentation via pseudo label rectification434
Spectral Contrastive Clustering400
Robust multilayer bootstrap networks in ensemble for unsupervised representation learning and clustering336
Deep graph matching meets mixed-integer linear programming: Relax or not ?308
Beyond mask: Rethinking guidance types in few-shot segmentation288
Striving for understanding: Deconstructing neural networks in side-channel analysis252
Looking beyond input frames: Self-supervised adaptation for video super-resolution225
Effective action recognition with embedded key point shifts219
GriT-DBSCAN: A spatial clustering algorithm for very large databases212
A modified interval type-2 Takagi-Sugeno fuzzy neural network and its convergence analysis210
Thermal to Visual Person Re-Identification Using Collaborative Metric Learning Based on Maximum Margin Matrix Factorization210
Bounded exponential loss function based AdaBoost ensemble of OCSVMs200
SpatioTemporal focus for skeleton-based action recognition197
Distance-aware network for physical-world object distribution estimation and counting190
An illumination-guided dual attention vision transformer for low-light image enhancement186
Occlusion-guided multi-modal fusion for vehicle-infrastructure cooperative 3D object detection184
Dynamic weighted knowledge distillation for brain tumor segmentation182
ANNE: Adaptive Nearest Neighbours and Eigenvector-based sample selection for robust learning with noisy labels174
Hyper-feature aggregation and relaxed distillation for class incremental learning172
DynamicKD: An effective knowledge distillation via dynamic entropy correction-based distillation for gap optimizing170
Multi-task meta label correction for time series prediction166
MTS2Graph: Interpretable multivariate time series classification with temporal evolving graphs160
Unsupervised person re-identification via multi-domain joint learning155
Head pose estimation using deep neural networks and 3D point clouds154
Robust Table Detection and Structure Recognition from Heterogeneous Document Images150
Fast adaptively balanced min-cut clustering149
A dense light field reconstruction algorithm for four-dimensional optical flow constraint equation149
Two phase cooperative learning for supervised dimensionality reduction149
Dynamic feature fusion with spatial-temporal context for robust object tracking149
Balanced seed selection for K-means clustering with determinantal point process148
CORE: Learning consistent ordinal representations with convex optimization for image ordinal estimation148
Deep reinforcement learning with credit assignment for combinatorial optimization148
DCFusion: Difference correlation-driven fusion mechanism of infrared and visible images145
Consistency-driven feature scoring and regularization network for visible–infrared person re-identification145
Extrinsic kernel ridge regression classifier for Kendall’s planar shape space142
Cross-Modality Interactive Attention Network for AI-generated image quality assessment140
Support subsets estimation for support vector machines retraining138
Progressive downsampling and adaptive guidance networks for dynamic scene deblurring135
Intensity mixture and band-adaptive detail fusion for pansharpening135
Mutual Domain Adaptation132
Editorial Board128
An entity-weights-based convolutional neural network for large-sale complex knowledge embedding127
Cross-modal co-feedback cellular automata for RGB-T saliency detection125
A generalized multi-aspect distance metric for mixed-type data clustering123
FastOPM—A practical method for partial match of time series121
Sequence patterns and HMM profiles to predict proteome wide zinc finger motifs119
FoCL: Feature-oriented continual learning for generative models117
Bi-Attention enhanced representation learning for image-text matching116
Spectral approximation of Gaussian random graph Laplacians and applications to pattern recognition113
A cross-network node classification method in open-set scenario112
Gradual interaction network for stereo matching110
Unsupervised learning non-uniform face enhancement under physics-guided model of illumination decoupling110
Kinship verification using multi-level dictionary pair learning for multiple resolution images109
RESKM: A General Framework to Accelerate Large-Scale Spectral Clustering109
Synthetic unknown class learning for learning unknowns107
Cascaded learning with transformer for simultaneous eye landmark, eye state and gaze estimation106
SARS-Net: COVID-19 detection from chest x-rays by combining graph convolutional network and convolutional neural network105
A Sampling-Based Density Peaks Clustering Algorithm for Large-Scale Data105
eX-ViT: A Novel explainable vision transformer for weakly supervised semantic segmentation104
Neural Normalized Cut: A differential and generalizable approach for spectral clustering102
Privileged multi-task learning for attribute-aware aesthetic assessment102
Identifying the key frames: An attention-aware sampling method for action recognition101
Explainable AI in human motion: A comprehensive approach to analysis, modeling, and generation100
Unsupervised update summarization of news events100
Scaled robust linear embedding with adaptive neighbors preserving99
DC-AD: A Divide-and-Conquer Method for Few-Shot Anomaly Detection96
DA-GAN: Dual-attention generative adversarial networks for real-world exquisite makeup transfer96
Improving the Facial Expression Recognition and Its Interpretability via Generating Expression Pattern-map96
Generalization capacity of multi-class SVM based on Markovian resampling96
Supervised penalty-based aggregation applied to motor-imagery based brain-computer-interface95
MSAN: Multiscale self-attention network for pansharpening95
Dynamic selection for reconstructing instance-dependent noisy labels94
Deep and wide nonnegative matrix factorization with embedded regularization94
Pseudo-labeling with keyword refining for few-supervised video captioning93
A neighborhood-based method for mining and fusing positive and negative false samples93
Leveraging tensor kernels to reduce objective function mismatch in deep clustering91
Adapt only once: Fast unsupervised person re-identification via relevance-aware guidance90
Temporal sparse adversarial attack on sequence-based gait recognition88
DM-GAN: CNN hybrid vits for training GANs under limited data88
PSCFormer: A lightweight hybrid network for gas identification in electronic nose system88
Robust deep fuzzy K-means clustering for image data87
A bijective inference network for interpretable identification of RNA N86
BiconNet: An edge-preserved connectivity-based approach for salient object detection86
Sketches by MoSSaRT: Representative selection from manifolds with gross sparse corruptions85
Distribution alignment for cross-device palmprint recognition85
Holistic word descriptor for lexicon reduction in handwritten arabic documents85
Inter-Attribute awareness for pedestrian attribute recognition84
Switching clusters’ synchronization for discrete space-time complex dynamical networks via boundary feedback controls83
Knowledge memorization and generation for action recognition in still images82
TBConvL-Net: A hybrid deep learning architecture for robust medical image segmentation82
Implicit face model: Depth super-resolution for 3D face recognition82
Phase Randomization: A data augmentation for domain adaptation in human action recognition82
A Dual Self-Attention mechanism for vehicle re-Identification81
Mix-ViT: Mixing attentive vision transformer for ultra-fine-grained visual categorization79
Rank-revealing fully-connected tensor network decomposition and its application to tensor completion78
Enhanced visible–infrared person re-identification based on cross-attention multiscale residual vision transformer78
A unified framework for unsupervised action learning via global-to-local motion transformer77
BE-ECM: Belief Entropy-based Evidential C-Means and its application in data clustering76
Dual-branch adjacent connection and channel mixing network for video crowd counting76
Early gesture detection in untrimmed streams: A controlled CTC approach for reliable decision-making76
Practical protection against video data leakage via universal adversarial head75
A landmark-free approach for automatic, dense and robust correspondence of 3D faces74
Elucidating robust learning with uncertainty-aware corruption pattern estimation74
Center Prediction Loss for Re-identification74
Generalization of deep learning models for natural gas indication in 2D seismic data74
Binary feature learning with local spectral context-aware attention for classification of hyperspectral images74
Editorial Board73
DecloudFormer: Quest the key to consistent thin cloud removal of wide-swath multi-spectral images73
Unsupervised multiplex graph representation learning via maximizing coding rate reduction72
A projected gradient solution to the minimum connector problem with extensions to support vector machines72
OpenInst: A simple query-based method for open-world instance segmentation71
Weakly supervised 3D human pose estimation based on PnP projection model71
Feature-matching method based on keypoint response constraint using binary encoding of phase congruency71
Deep evidential clustering based on feature representation learning and belief function theory71
Table representation learning using heterogeneous graph embedding71
Rank Gap Sensitive Deep AUC maximization for CTR prediction70
A uniform representation model for OCT-based fingerprint presentation attack detection and reconstruction69
Super-encoder with cooperative autoencoder networks69
Towards Automatic Model Compression via a Unified Two-Stage Framework69
Stain-adaptive self-supervised learning for histopathology image analysis68
HMSFT: Hierarchical Multi-scale Spatial-Frequency-Temporal collaborative transformer for 3D human pose estimation68
A multi-resolution self-supervised learning framework for semantic segmentation in histopathology67
GraphXCOVID: Explainable deep graph diffusion pseudo-Labelling for identifying COVID-19 on chest X-rays67
CLEAR: Cross-Transformers With Pre-Trained Language Model for Person Attribute Recognition and Retrieval66
Privacy-preserving speaker verification system using Ranking-of-Element hashing66
Multi-proxy feature learning for robust fine-grained visual recognition66
Graph Attentive Dual Ensemble learning for Unsupervised Domain Adaptation on point clouds65
A spatially constrained skew Student’s-t mixture model for brain MR image segmentation and bias field correction65
Mitigate the classification ambiguity via localization-classification sequence in object detection64
IMCSN: An improved neighborhood aggregation interaction strategy for multi-scale contrastive Siamese networks64
Robust sparse and low-redundancy multi-label feature selection with dynamic local and global structure preservation64
Joint multi-label learning and feature extraction for temporal link prediction64
Geometric-inspired graph-based Incomplete Multi-view Clustering64
Indefinite twin support vector machine with DC functions programming64
Towards better long-tailed oracle character recognition with adversarial data augmentation63
BEST: Building evidences from scattered templates for accurate contactless palmprint recognition63
Trajectory-User Linking via Multi-Scale Graph Attention Network63
Learning a bi-directional discriminative representation for deep clustering63
Human interaction recognition framework based on interacting body part attention63
Deep contrastive representation learning for supervised tasks63
Generating Transferable Adversarial Examples for Speech Classification62
Collaborative contrastive learning for cross-domain gaze estimation62
Efficient federated multi-view learning62
GDB: Gated Convolutions-based Document Binarization62
Learning sequentially diversified representations for fine-grained categorization62
Multi-modal brain tumor segmentation via disentangled representation learning and region-aware contrastive learning62
Local-enhanced representation for text-based person search62
Image analysis by fractional-order weighted spherical Bessel-Fourier moments61
MCE: Towards a General Framework for Handling Missing Modalities under Imbalanced Missing Rates61
A feature pair-based neural network embedded decision tree for synergistic drug combination prediction61
Feature decoupling and regeneration towards wifi-based human activity recognition60
Semantic perceptive infrared and visible image fusion Transformer60
Bayesian mixture of gaussian processes for data association problem60
TreEnhance: A tree search method for low-light image enhancement60
Homogeneous and heterogeneous relational graph for visible-infrared person re-identification60
Consistency and label constrained transfer low-rank representation for cross-light finger vein recognition60
RhythmFormer: Extracting patterned rPPG signals based on periodic sparse attention60
Estimating fund-raising performance for start-up projects from a market graph perspective59
Progressive modality-complement aggregative multitransformer for domain multi-modal neural machine translation59
Variable multi-scale attention fusion network and adaptive correcting gradient optimization for multi-task learning59
Not All Samples Are Born Equal: Towards Effective Clean-Label Backdoor Attacks58
PSSS-EEG: A Probabilistic-masking Self-Supervised Swin-transformer model for EEG-based drowsiness recognition58
Investigating the effectiveness of data augmentation from similarity and diversity: An empirical study57
FSENet: Feature suppression and enhancement network for tiny object detection57
Linearized alternating direction method of multipliers for elastic-net support vector machines57
Driver multi-task emotion recognition network based on multi-modal facial video analysis57
Sparse and robust support vector machine with capped squared loss for large-scale pattern classification56
Marginal debiased network for fair visual recognition56
Shape-centered representation learning for visible–infrared person re-identification56
Editorial Board56
Table Structure Recognition and Form Parsing by End-to-End Object Detection and Relation Parsing56
A survey of robust adversarial training in pattern recognition: Fundamental, theory, and methodologies55
Weighting and pruning based ensemble deep random vector functional link network for tabular data classification55
A survey of human-computer interaction (HCI) & natural habits-based behavioural biometric modalities for user recognition schemes55
Auto-attention mechanism for multi-view deep embedding clustering55
Methods for segmenting cracks in 3d images of concrete: A comparison based on semi-synthetic images55
Robust image hiding network with Frequency and Spatial Attentions55
Metaheuristic Search Based Feature Selection Methods for Classification of Cancer55
Multi scale pixel attention and feature extraction based neural network for image denoising55
Adaptively robust high-order tensor factorization for low-rank tensor reconstruction54
Learning to match features with discriminative sparse graph neural network54
Poincaré Fréchet mean54
FeverNet: Enabling accurate and robust remote fever screening54
A novel relation aware wrapper method for feature selection54
Dynamic and static mutual fitting for action recognition54
Coordinating explicit and implicit knowledge for knowledge-based VQA54
Hybrid-context-based multi-prior entropy modeling for learned lossless image compression54
IRCNN: A novel signal decomposition approach based on iterative residue convolutional neural network54
Scene Chinese Recognition with Local and Global Attention53
Molecular graph contrastive learning with line graph53
Weakly privileged learning with knowledge extraction53
Contrastive Generative Network with Recursive-Loop for 3D point cloud generalized zero-shot classification53
Support structure representation learning for sequential data clustering53
Exploring target-related information with reliable global pixel relationships for robust RGB-T tracking52
Region-wise loss for biomedical image segmentation52
Editorial Board52
Multi-granularity interaction and feature recombination network for fine-grained visual classification51
Multimodal urban traffic flow prediction based on multi-scale time series imaging51
A novel GCN-based point cloud classification model robust to pose variances51
Rethinking convolutional neural networks for trajectory refinement51
ERAT:Eyeglasses removal with attention51
Arbitrary Order Total Variation for Deformable Image Registration51
Coarse is better? A new pipeline towards self-supervised learning with uncurated images51
Editorial Board50
Online portfolio selection with predictive instantaneous risk assessment50
Corrigendum to ‘Toward a Blind Image Quality Evaluator in the Wild by Learning beyond Human Opinion Scores’ Pattern Recognition. Volume 137 (2023) 10929650
GlobalAP: Global average precision optimization for person re-identification50
Non-residual unrestricted pruned ultra-faster line detection for edge devices50
CPSS-FAT: A consistent positive sample selection for object detection with full adaptive threshold50
Editorial Board49
Efficient search of comprehensively robust neural architectures via multi-fidelity evaluation49
Versatile, full‐spectrum, and swift network sampling for model generation48
Consensus Incomplete Multi-View Clustering with Nonconvex Tensor Smooth Graph Learning48
Few pixels attacks with generative model48
Cross-View kernel transfer48
Graph relation distillation for efficient biomedical instance segmentation48
BDNet: A BERT-based dual-path network for text-to-image cross-modal person re-identification48
Hierarchical Context Learning of object components for unsupervised semantic segmentation48
Mathematical formula detection in document images: A new dataset and a new approach48
Example-based color transfer with Gaussian mixture modeling48
Non-negative Tucker decomposition with graph regularization and smooth constraint for clustering47
Distributional and spatial-temporal robust representation learning for transportation activity recognition47
Expecting individuals’ body reaction to Covid-19 based on statistical Naïve Bayes technique47
Crowd counting from single images using recursive multi-pathway zooming and foreground enhancement47
CGMV-EGR: A multimodal fusion framework for electromyographic gesture recognition47
Doubly contrastive representation learning for federated image recognition47
Dynamic and reliable subtask tracker with general schatten p-norm regularization47
SS ViT: Observing pathologies of multi-layer perceptron weights and re-setting vision transformer47
Low-resolution human pose estimation47
An empirical study of the impact of masks on face recognition47
Deep neural network compression through interpretability-based filter pruning47
Co-regularized optimal high-order graph embedding for multi-view clustering46
Joint Intra-view and Inter-view Enhanced Tensor Low-rank Induced Affinity Graph Learning46
Multi-attention augmented network for single image super-resolution46
Generalized pyramid co-attention with learnable aggregation net for video question answering46
Joint spatial and scale attention network for multi-view facial expression recognition46
A novel hybrid decoding neural network for EEG signal representation46
A review of deep-learning-based super-resolution: From methods to applications46
Real masks and spoof faces: On the masked face presentation attack detection46
WB-LRP: Layer-wise relevance propagation with weight-dependent baseline46
ResPrune: An energy-efficient restorative filter pruning method using stochastic optimization for accelerating CNN46
Hiding multiple images into a single image via joint compressive autoencoders46
Mutual information regularized identity-aware facial expression recognition in compressed video46
TCFAP-Net: Transformer-based Cross-feature Fusion and Adaptive Perception Network for large-scale point cloud semantic segmentation45
A recurrent graph neural network for inductive representation learning on dynamic graphs45
Discriminative feature generation for classification of imbalanced data45
NCL++: Nested Collaborative Learning for long-tailed visual recognition45
PDRLRR: A novel low-rank representation with projection distance regularization via manifold optimization for clustering45
DualAdaptNet: Enhancing Domain Adaptation Regression with Error Accumulation Reduction and Dual-Head Heterogeneous Learning45
Hybrid routing transformer for zero-shot learning45
0.14916706085205