Pattern Recognition

Papers
(The TQCC of Pattern Recognition is 17. 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 2021-04-01 to 2025-04-01.)
ArticleCitations
Semi-supervised extensions of multi-task tree ensembles406
Superpixel-based multi-scale multi-instance learning for hyperspectral image classification313
Information-diffused graph tracking with linear complexity300
Discriminative atoms embedding relation dual network for classification of choroidal neovascularization in OCT images253
Self-Training-Transductive-Learning Broad Learning System (STTL-BLS): A model for effective and efficient image classification236
Back-to-Bones: Rediscovering the role of backbones in domain generalization218
CORE: Learning consistent ordinal representations with convex optimization for image ordinal estimation207
Heterophily-aware graph attention network201
From anomaly detection to open set recognition: Bridging the gap194
EEG-ConvTransformer for single-trial EEG-based visual stimulus classification191
Deep image prior based defense against adversarial examples182
ScribbleNet: Efficient interactive annotation of urban city scenes for semantic segmentation180
Intensity mixture and band-adaptive detail fusion for pansharpening178
3D hand pose estimation from a single RGB image by weighting the occlusion and classification177
Cross-modal co-feedback cellular automata for RGB-T saliency detection166
Weakly-supervised semantic segmentation with saliency and incremental supervision updating164
Learning Foreground Information Bottleneck for few-shot semantic segmentation163
Graph Convolutional Network with elastic topology160
Independent vector analysis: Model, applications, challenges159
Deep tree-ensembles for multi-output prediction155
Low-complexity arrays of contour signatures for exact shape retrieval151
Learning efficient, explainable and discriminative representations for pulmonary nodules classification149
Complex common spatial patterns on time-frequency decomposed EEG for brain-computer interface137
ReViT: Enhancing vision transformers feature diversity with attention residual connections136
Self-Supervised Leaf Segmentation under Complex Lighting Conditions131
Hyper-sausage coverage function neuron model and learning algorithm for image classification131
Overcoming weaknesses of density peak clustering using a data-dependent similarity measure130
A novel interval dual convolutional neural network method for interval-valued stock price prediction128
Supervised penalty-based aggregation applied to motor-imagery based brain-computer-interface128
Mix-ViT: Mixing attentive vision transformer for ultra-fine-grained visual categorization127
PLFace: Progressive Learning for Face Recognition with Mask Bias124
Deep and wide nonnegative matrix factorization with embedded regularization122
Robust deep fuzzy K-means clustering for image data119
Conditional information gain networks as sparse mixture of experts118
Discrete embedding for attributed graphs116
Characters as graphs: Interpretable handwritten Chinese character recognition via Pyramid Graph Transformer111
Beyond OCR + VQA: Towards end-to-end reading and reasoning for robust and accurate textvqa111
Cross-Modal Transformer for RGB-D semantic segmentation of production workshop objects111
Hypergraph matching via game-theoretic hypergraph clustering111
Biological eagle eye-based method for change detection in water scenes110
Factorized multi-Graph matching107
Detection confidence driven multi-object tracking to recover reliable tracks from unreliable detections107
Reconstruction of fragmented trajectories of collective motion using Hadamard deep autoencoders104
DGFormer: Dynamic graph transformer for 3D human pose estimation104
Finding compact and well-separated clusters: Clustering using silhouette coefficients104
CS-net: Conv-simpleformer network for agricultural image segmentation104
Scale-selective and noise-robust extended local binary pattern for texture classification102
GripNet: Graph information propagation on supergraph for heterogeneous graphs102
MUNet: Motion uncertainty-aware semi-supervised video object segmentation101
A uniform transformer-based structure for feature fusion and enhancement for RGB-D saliency detection100
Online and offline streaming feature selection methods with bat algorithm for redundancy analysis99
Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices98
Query efficient black-box adversarial attack on deep neural networks98
RPI-CapsuleGAN: Predicting RNA-protein interactions through an interpretable generative adversarial capsule network95
Fairness in face presentation attack detection94
A survey on deep learning-based image forgery detection93
Self-distillation and self-supervision for partial label learning93
Two phase cooperative learning for supervised dimensionality reduction91
A non-regularization self-supervised Retinex approach to low-light image enhancement with parameterized illumination estimation91
A restarted large-scale spectral clustering with self-guiding and block diagonal representation90
Unsupervised person re-identification with multi-label learning guided self-paced clustering87
Advancements in point cloud data augmentation for deep learning: A survey87
Dynamic feature fusion with spatial-temporal context for robust object tracking86
Heterogeneous network representation learning based on role feature extraction85
Adaptive spatial-temporal surrounding-aware correlation filter tracking via ensemble learning85
Improving deep learning on point cloud by maximizing mutual information across layers85
Covered Style Mining via Generative Adversarial Networks for Face Anti-spoofing84
3D human pose estimation with single image and inertial measurement unit (IMU) sequence84
3D hand pose and shape estimation from RGB images for keypoint-based hand gesture recognition84
Feature-semantic augmentation network for few-shot open-set recognition83
Phase Randomization: A data augmentation for domain adaptation in human action recognition82
Attentional prototype inference for few-shot segmentation82
Multi-View correlation distillation for incremental object detection81
Refining a k-nearest neighbor graph for a computationally efficient spectral clustering81
DIODE: Dilatable Incremental Object Detection80
Attention‐guided evolutionary attack with elastic‐net regularization on face recognition80
Graph-based stock correlation and prediction for high-frequency trading systems80
Detecting pulmonary diseases using deep features in X-ray images80
Security and privacy enhanced smartphone-based gait authentication with random representation learning and digital lockers78
Support subsets estimation for support vector machines retraining78
A consistent and flexible framework for deep matrix factorizations78
Graph regularization multidimensional projection78
An encoded histogram of ridge bifurcations and contours for fingerprint presentation attack detection78
FoCL: Feature-oriented continual learning for generative models78
Fast algorithms for incremental and decremental semi-supervised discriminant analysis77
Editorial Board76
YOLO-Anti: YOLO-based counterattack model for unseen congested object detection76
Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristic75
A near effective and efficient model in recognition75
Efficient COVID-19 testing via contextual model based compressive sensing75
Mitigating the effect of dataset shift in clustering74
Learning interlaced sparse Sinkhorn matching network for video super-resolution74
Editorial Board74
A new image decomposition approach using pixel-wise analysis sparsity model74
Split ‘n’ merge net: A dynamic masking network for multi-task attention73
Editorial Board72
Hierarchical distillation learning for scalable person search72
Hyper-feature aggregation and relaxed distillation for class incremental learning71
Instance exploitation for learning temporary concepts from sparsely labeled drifting data streams71
Editorial Board70
Single-particle reconstruction in cryo-EM based on three-dimensional weighted nuclear norm minimization70
SEMv2: Table separation line detection based on instance segmentation69
DeepActsNet: A deep ensemble framework combining features from face, hands, and body for action recognition69
Editorial Board69
Retraction Notice68
Editorial Board68
Holistic word descriptor for lexicon reduction in handwritten arabic documents67
AUCO ResNet: an end-to-end network for Covid-19 pre-screening from cough and breath67
Effective action recognition with embedded key point shifts66
Unsupervised Domain Adaptation via Deep Conditional Adaptation Network66
Discriminative feature alignment: Improving transferability of unsupervised domain adaptation by Gaussian-guided latent alignment64
Unsupervised video anomaly detection via normalizing flows with implicit latent features63
High-order manifold regularized multi-view subspace clustering with robust affinity matrices and weighted TNN63
Robust multi-scale weighting-based edge-smoothing filter for single image dehazing62
Multi-dimensional clustering through fusion of high-order similarities62
Flexible model weighting for one-dependence estimators based on point-wise independence analysis62
Robust detectors of rotationally symmetric shapes based on novel semi-shape signatures62
Segmentation of Handwritten Arabic Graphemes Using a Directed Convolutional Neural Network and Mathematical Morphology Operations61
G2-SCANN: Gaussian-kernel graph-based SLD clustering algorithm with natural neighbourhood61
A safe screening rule with bi-level optimization of ν support vect61
Learning graph edit distance by graph neural networks60
Generalization capacity of multi-class SVM based on Markovian resampling60
Motion-guided spatiotemporal multitask feature discrimination for self-supervised video representation learning60
Hierarchical multimodal transformers for Multipage DocVQA59
Cloud based scalable object recognition from video streams using orientation fusion and convolutional neural networks59
Progressive downsampling and adaptive guidance networks for dynamic scene deblurring59
Efficient image analysis with triple attention vision transformer59
VPA-Net: A visual perception assistance network for 3d lidar semantic segmentation58
Counterfactual explanation based on gradual construction for deep networks58
Dimension-aware attention for efficient mobile networks58
Efficient large-scale scene representation with a hybrid of high-resolution grid and plane features57
DCFusion: Difference correlation-driven fusion mechanism of infrared and visible images57
An illumination-guided dual attention vision transformer for low-light image enhancement57
LGNet: Local and global point dependency network for 3D object detection56
Federated Incremental Learning algorithm based on Topological Data Analysis56
A cross-network node classification method in open-set scenario56
A Cross-Lingual Summarization method based on cross-lingual Fact-relationship Graph Generation56
Leveraging tensor kernels to reduce objective function mismatch in deep clustering56
MBQuant: A novel multi-branch topology method for arbitrary bit-width network quantization56
Compositional Zero-Shot Learning using Multi-Branch Graph Convolution and Cross-layer Knowledge Sharing55
Determining the trustworthiness of DNNs in classification tasks using generalized feature-based confidence metric55
Twin SVM for conditional probability estimation in binary and multiclass classification55
Knowledge transfer evolutionary search for lightweight neural architecture with dynamic inference55
Encoder–decoder cycle for visual question answering based on perception-action cycle55
Thermal to Visual Person Re-Identification Using Collaborative Metric Learning Based on Maximum Margin Matrix Factorization55
Dense extreme inception network for edge detection54
A bi-level formulation for multiple kernel learning via self-paced training54
MoRE: Multi-output residual embedding for multi-label classification54
Frequency learning attention networks based on deep learning for automatic modulation classification in wireless communication54
Adaptive, Hybrid Feature Selection (AHFS)54
WSDS-GAN: A weak-strong dual supervised learning method for underwater image enhancement54
Multi-scale spatial-spectral fusion based on multi-input fusion calculation and coordinate attention for hyperspectral image classification53
Improving the Facial Expression Recognition and Its Interpretability via Generating Expression Pattern-map53
Deep learning-driven diagnosis: A multi-task approach for segmenting stroke and Bell's palsy53
Knowledge base graph embedding module design for Visual question answering model53
Automatic medical image interpretation: State of the art and future directions52
Kinship verification using multi-level dictionary pair learning for multiple resolution images52
Density peaks clustering based on balance density and connectivity52
Editorial Board52
Evolving meta-correlation classes for binary similarity52
Rain-component-aware capsule-GAN for single image de-raining51
GHOST: Graph-based higher-order similarity transformation for classification51
eX-ViT: A Novel explainable vision transformer for weakly supervised semantic segmentation51
FastOPM—A practical method for partial match of time series51
GGD-GAN: Gradient-Guided dual-Branch adversarial networks for relic sketch generation51
Robformer: A robust decomposition transformer for long-term time series forecasting51
Distributional barycenter problem through data-driven flows50
Feature selections based on two-type overlap degrees and three-view granulation measures for 50
Clustering experience replay for the effective exploitation in reinforcement learning50
JSL3d: Joint subspace learning with implicit structure supervision for 3D pose estimation50
Cluster prototype earth mover’s distance adapters and alignment-guided prompt learning for vision–language models50
AMMD: Attentive maximum mean discrepancy for few-shot image classification50
Deep graph matching meets mixed-integer linear programming: Relax or not ?50
Multi-scale multi-hierarchy attention convolutional neural network for fetal brain extraction50
Prototype learning based generic multiple object tracking via point-to-box supervision49
High-frequency and low-frequency dual-channel graph attention network49
Shadow-aware decomposed transformer network for shadow detection and removal49
Kernel-guided injection deep network for blind fusion of multispectral and panchromatic images49
The familiarity hypothesis: Explaining the behavior of deep open set methods49
DM-GAN: CNN hybrid vits for training GANs under limited data49
Discovering an inference recipe for weakly-supervised object localization48
Dynamic selection for reconstructing instance-dependent noisy labels48
A large cross-modal video retrieval dataset with reading comprehension48
A dense light field reconstruction algorithm for four-dimensional optical flow constraint equation48
Privileged multi-task learning for attribute-aware aesthetic assessment48
Answering knowledge-based visual questions via the exploration of Question Purpose48
Dynamic weighted knowledge distillation for brain tumor segmentation48
Progressive expansion for semi-supervised bi-modal salient object detection47
Dirichlet process mixture of Gaussian process functional regressions and its variational EM algorithm47
Game-theoretic hypergraph matching with density enhancement46
Scalable clustering by aggregating representatives in hierarchical groups46
Split-and-merge model selection of mixtures of Gaussian processes with RJMCMC46
A modified interval type-2 Takagi-Sugeno fuzzy neural network and its convergence analysis46
Human–object interaction detection via recycling of ground-truth annotations46
Polarized reflection removal with dual-stream attention guidance46
MS-TCRNet: Multi-Stage Temporal Convolutional Recurrent Networks for action segmentation using sensor-augmented kinematics46
Unsupervised learning of global factors in deep generative models46
Large motion anime head animation using a cascade pose transform network46
ASF-Net: Robust video deraining via temporal alignment and online adaptive learning45
ZooKT: Task-adaptive knowledge transfer of Model Zoo for few-shot learning45
Occlusion-guided multi-modal fusion for vehicle-infrastructure cooperative 3D object detection45
SparseComm: An Efficient Sparse Communication Framework for Vehicle-Infrastructure Cooperative 3D Detection45
Fast adaptively balanced min-cut clustering45
Local Linear Embedding with Adaptive Neighbors45
Riemannian representation learning for multi-source domain adaptation45
A Sampling-Based Density Peaks Clustering Algorithm for Large-Scale Data45
A coded knowledge distillation framework for image classification based on adaptive JPEG encoding45
MinEnt: Minimum entropy for self-supervised representation learning44
A generalized multi-aspect distance metric for mixed-type data clustering44
Residual network with self-adaptive time step size44
CRCGAN: Toward robust feature extraction in finger vein recognition44
DA-GAN: Dual-attention generative adversarial networks for real-world exquisite makeup transfer44
Asymmetric patch sampling for contrastive learning44
QFAE: Q-Function guided Action Exploration for offline deep reinforcement learning44
RP-Net: A Robust Polar Transformation Network for rotation-invariant face detection44
SNN using color-opponent and attention mechanisms for object recognition43
Boosting transferability of physical attack against detectors by redistributing separable attention43
Dynamic VAEs via semantic-aligned matching for continual zero-shot learning43
Averaging GPS segments competition 201943
Dual-perspective multi-instance embedding learning with adaptive density distribution mining43
Two-stage Rule-induction visual reasoning on RPMs with an application to video prediction43
Semantic aware representation learning for optimizing image retrieval systems in radiology43
A newton interpolation network for smoke semantic segmentation43
ACFNet: An adaptive cross-fusion network for infrared and visible image fusion43
Motion-guided semantic alignment for line art animation colorization43
Hyperspectral image classification via discriminative convolutional neural network with an improved triplet loss42
Semantic-based conditional generative adversarial hashing with pairwise labels42
Pseudo-labeling with keyword refining for few-supervised video captioning42
Embedded feature selection for robust probability learning machines42
Consistency-driven feature scoring and regularization network for visible–infrared person re-identification42
Instant pose extraction based on mask transformer for occluded person re-identification42
Coloring anime line art videos with transformation region enhancement network41
Adversarial pan-sharpening attacks for object detection in remote sensing41
Joint utilization of positive and negative pseudo-labels in semi-supervised facial expression recognition41
Exemplar-free class incremental learning via discriminative and comparable parallel one-class classifiers41
Crossover-Net: Leveraging vertical-horizontal crossover relation for robust medical image segmentation41
Multi-branch feature transformation cross-domain few-shot learning for hyperspectral image classification41
Multi-view visual semantic embedding for cross-modal image–text retrieval41
MvWECM: Multi-view Weighted Evidential C-Means clustering41
TransMatch: Transformer-based correspondence pruning via local and global consensus41
Semantics-enhanced early action detection using dynamic dilated convolution40
Pairwise learning for the partial label ranking problem40
Infrared small target detection via adaptive M-estimator ring top-hat transformation40
Sparsely-labeled source assisted domain adaptation40
Patch loss: A generic multi-scale perceptual loss for single image super-resolution40
Semi-supervised kernel matrix learning using adaptive constraint-based seed propagation40
Fast hard negative mining for deep metric learning40
Saliency detection for underwater moving object with sonar based on motion estimation and multi-trajectory analysis40
Local multi-scale feature aggregation network for real-time image dehazing40
An evidential clustering algorithm by finding belief-peaks and disjoint neighborhoods40
0.13186311721802