Pattern Recognition

Papers
(The TQCC of Pattern Recognition is 16. 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 2021-03-01 to 2025-03-01.)
ArticleCitations
Semi-supervised extensions of multi-task tree ensembles378
Superpixel-based multi-scale multi-instance learning for hyperspectral image classification215
Information-diffused graph tracking with linear complexity214
ReViT: Enhancing vision transformers feature diversity with attention residual connections212
Discriminative atoms embedding relation dual network for classification of choroidal neovascularization in OCT images211
Self-Training-Transductive-Learning Broad Learning System (STTL-BLS): A model for effective and efficient image classification206
Back-to-Bones: Rediscovering the role of backbones in domain generalization181
CORE: Learning consistent ordinal representations with convex optimization for image ordinal estimation178
Cross-level Feature Aggregation Network for Polyp Segmentation176
Heterophily-aware graph attention network176
A multi-center study of ultrasound images using a fully automated segmentation architecture170
From anomaly detection to open set recognition: Bridging the gap169
EEG-ConvTransformer for single-trial EEG-based visual stimulus classification163
Deep image prior based defense against adversarial examples159
SARS-Net: COVID-19 detection from chest x-rays by combining graph convolutional network and convolutional neural network157
ScribbleNet: Efficient interactive annotation of urban city scenes for semantic segmentation155
Divide well to merge better: A novel clustering algorithm151
Independent vector analysis: Model, applications, challenges149
Deep tree-ensembles for multi-output prediction148
Low-complexity arrays of contour signatures for exact shape retrieval143
Deep learning-driven diagnosis: A multi-task approach for segmenting stroke and Bell's palsy138
Deep and wide nonnegative matrix factorization with embedded regularization132
DynamicKD: An effective knowledge distillation via dynamic entropy correction-based distillation for gap optimizing128
Robust deep fuzzy K-means clustering for image data126
Conditional information gain networks as sparse mixture of experts125
Characters as graphs: Interpretable handwritten Chinese character recognition via Pyramid Graph Transformer121
Discrete embedding for attributed graphs121
Beyond OCR + VQA: Towards end-to-end reading and reasoning for robust and accurate textvqa117
Hypergraph matching via game-theoretic hypergraph clustering116
AUCO ResNet: an end-to-end network for Covid-19 pre-screening from cough and breath115
Cross-Modal Transformer for RGB-D semantic segmentation of production workshop objects114
UAVformer: A Composite Transformer Network for Urban Scene Segmentation of UAV Images113
Biological eagle eye-based method for change detection in water scenes112
Complex common spatial patterns on time-frequency decomposed EEG for brain-computer interface111
Heterogeneous network representation learning based on role feature extraction107
The trace kernel bandwidth criterion for support vector data description101
ANCES: A novel method to repair attribute noise in classification problems100
Distribution alignment for cross-device palmprint recognition100
3D human pose estimation with single image and inertial measurement unit (IMU) sequence99
3D hand pose and shape estimation from RGB images for keypoint-based hand gesture recognition99
Improving deep learning on point cloud by maximizing mutual information across layers97
Covered Style Mining via Generative Adversarial Networks for Face Anti-spoofing96
RA-YOLOX: Re-parameterization align decoupled head and novel label assignment scheme based on YOLOX96
Feature-semantic augmentation network for few-shot open-set recognition95
Phase Randomization: A data augmentation for domain adaptation in human action recognition93
Learning Foreground Information Bottleneck for few-shot semantic segmentation92
Attentional prototype inference for few-shot segmentation92
Image-to-video person re-identification using three-dimensional semantic appearance alignment and cross-modal interactive learning91
Adaptive spatial-temporal surrounding-aware correlation filter tracking via ensemble learning89
Transformed domain convolutional neural network for Alzheimer's disease diagnosis using structural MRI86
Heterogeneous representation learning and matching for few-shot relation prediction86
An accurate stereo matching method based on color segments and edges85
Refining a k-nearest neighbor graph for a computationally efficient spectral clustering85
Multi-View correlation distillation for incremental object detection85
Meta-learning for dynamic tuning of active learning on stream classification84
Residual shape adaptive dense-nested Unet: Redesign the long lateral skip connections for metal surface tiny defect inspection84
DIODE: Dilatable Incremental Object Detection84
Support subsets estimation for support vector machines retraining83
Graph regularization multidimensional projection83
FoCL: Feature-oriented continual learning for generative models83
GA3N: Generative adversarial AutoAugment network83
An encoded histogram of ridge bifurcations and contours for fingerprint presentation attack detection81
A consistent and flexible framework for deep matrix factorizations80
Security and privacy enhanced smartphone-based gait authentication with random representation learning and digital lockers79
Editorial Board78
Fast algorithms for incremental and decremental semi-supervised discriminant analysis78
Efficient COVID-19 testing via contextual model based compressive sensing77
A near effective and efficient model in recognition77
YOLO-Anti: YOLO-based counterattack model for unseen congested object detection77
Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristic76
Mitigating the effect of dataset shift in clustering75
Editorial Board75
Sequence patterns and HMM profiles to predict proteome wide zinc finger motifs73
3D hand pose estimation from a single RGB image by weighting the occlusion and classification73
Learning interlaced sparse Sinkhorn matching network for video super-resolution73
A new image decomposition approach using pixel-wise analysis sparsity model72
Hierarchical distillation learning for scalable person search71
Split ‘n’ merge net: A dynamic masking network for multi-task attention71
Hyper-feature aggregation and relaxed distillation for class incremental learning70
Instance exploitation for learning temporary concepts from sparsely labeled drifting data streams70
Editorial Board70
Single-particle reconstruction in cryo-EM based on three-dimensional weighted nuclear norm minimization69
Factorized multi-Graph matching69
SEMv2: Table separation line detection based on instance segmentation69
Editorial Board69
Editorial Board69
DeepActsNet: A deep ensemble framework combining features from face, hands, and body for action recognition68
Retraction Notice67
Editorial Board66
Joint discriminative feature learning for multimodal finger recognition66
Holistic word descriptor for lexicon reduction in handwritten arabic documents65
Unsupervised video anomaly detection via normalizing flows with implicit latent features65
Editorial Board65
Effective action recognition with embedded key point shifts65
Robust detectors of rotationally symmetric shapes based on novel semi-shape signatures64
Blitz-SLAM: A semantic SLAM in dynamic environments64
Flexible model weighting for one-dependence estimators based on point-wise independence analysis63
Knowledge-aware deep framework for collaborative skin lesion segmentation and melanoma recognition63
Online and offline streaming feature selection methods with bat algorithm for redundancy analysis62
Robust multi-scale weighting-based edge-smoothing filter for single image dehazing61
Segmentation of Handwritten Arabic Graphemes Using a Directed Convolutional Neural Network and Mathematical Morphology Operations60
Motion-guided spatiotemporal multitask feature discrimination for self-supervised video representation learning60
Generalization capacity of multi-class SVM based on Markovian resampling60
G2-SCANN: Gaussian-kernel graph-based SLD clustering algorithm with natural neighbourhood60
Learning graph edit distance by graph neural networks60
A safe screening rule with bi-level optimization of ν support vect60
Interpretable medical deep framework by logits-constraint attention guiding graph-based multi-scale fusion for Alzheimer’s disease analysis60
Hierarchical multimodal transformers for Multipage DocVQA59
Progressive downsampling and adaptive guidance networks for dynamic scene deblurring59
Visual-to-EEG cross-modal knowledge distillation for continuous emotion recognition59
An enhanced vision transformer with wavelet position embedding for histopathological image classification58
Efficient image analysis with triple attention vision transformer57
Granularity-aware distillation and structure modeling region proposal network for fine-grained image classification57
Cloud based scalable object recognition from video streams using orientation fusion and convolutional neural networks56
Counterfactual explanation based on gradual construction for deep networks56
TriSig: Evaluating the statistical significance of triclusters56
Graph-based stock correlation and prediction for high-frequency trading systems56
Deep reinforcement learning with credit assignment for combinatorial optimization56
Dimension-aware attention for efficient mobile networks56
RESKM: A General Framework to Accelerate Large-Scale Spectral Clustering56
Dense center-direction regression for object counting and localization with point supervision56
An illumination-guided dual attention vision transformer for low-light image enhancement55
Efficient large-scale scene representation with a hybrid of high-resolution grid and plane features55
DCFusion: Difference correlation-driven fusion mechanism of infrared and visible images55
VPA-Net: A visual perception assistance network for 3d lidar semantic segmentation55
Federated Incremental Learning algorithm based on Topological Data Analysis54
IIS-FVIQA: Finger Vein Image Quality Assessment with intra-class and inter-class similarity54
MBQuant: A novel multi-branch topology method for arbitrary bit-width network quantization53
TBConvL-Net: A hybrid deep learning architecture for robust medical image segmentation53
Density change consistency clustering from density extreme53
Leveraging tensor kernels to reduce objective function mismatch in deep clustering52
GriT-DBSCAN: A spatial clustering algorithm for very large databases52
LGNet: Local and global point dependency network for 3D object detection52
A cross-network node classification method in open-set scenario52
A Cross-Lingual Summarization method based on cross-lingual Fact-relationship Graph Generation52
Thermal to Visual Person Re-Identification Using Collaborative Metric Learning Based on Maximum Margin Matrix Factorization51
Knowledge transfer evolutionary search for lightweight neural architecture with dynamic inference51
Determining the trustworthiness of DNNs in classification tasks using generalized feature-based confidence metric51
Compositional Zero-Shot Learning using Multi-Branch Graph Convolution and Cross-layer Knowledge Sharing51
MoRE: Multi-output residual embedding for multi-label classification51
Robust Table Detection and Structure Recognition from Heterogeneous Document Images51
Twin SVM for conditional probability estimation in binary and multiclass classification51
Encoder–decoder cycle for visual question answering based on perception-action cycle51
YOLOPX: Anchor-free multi-task learning network for panoptic driving perception50
WSDS-GAN: A weak-strong dual supervised learning method for underwater image enhancement50
A bi-level formulation for multiple kernel learning via self-paced training50
Fairness in face presentation attack detection50
Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices50
Switching clusters’ synchronization for discrete space-time complex dynamical networks via boundary feedback controls50
Improving the Facial Expression Recognition and Its Interpretability via Generating Expression Pattern-map49
Person re-identification: A retrospective on domain specific open challenges and future trends49
Density peaks clustering based on balance density and connectivity49
Editorial Board49
Evolving meta-correlation classes for binary similarity49
Kinship verification using multi-level dictionary pair learning for multiple resolution images49
SDUNet: Road extraction via spatial enhanced and densely connected UNet49
Automatic medical image interpretation: State of the art and future directions48
Exploring transformers for behavioural biometrics: A case study in gait recognition48
Meta-seg: A survey of meta-learning for image segmentation48
PLFace: Progressive Learning for Face Recognition with Mask Bias48
A novel interval dual convolutional neural network method for interval-valued stock price prediction47
Dense extreme inception network for edge detection47
Rain-component-aware capsule-GAN for single image de-raining47
A Dual Self-Attention mechanism for vehicle re-Identification47
GGD-GAN: Gradient-Guided dual-Branch adversarial networks for relic sketch generation47
Inter-Attribute awareness for pedestrian attribute recognition47
eX-ViT: A Novel explainable vision transformer for weakly supervised semantic segmentation47
Joint learning of latent subspace and structured graph for multi-view clustering46
Cascaded learning with transformer for simultaneous eye landmark, eye state and gaze estimation46
Deep graph matching meets mixed-integer linear programming: Relax or not ?46
Robformer: A robust decomposition transformer for long-term time series forecasting46
GHOST: Graph-based higher-order similarity transformation for classification46
Do deep neural networks contribute to multivariate time series anomaly detection?46
FastOPM—A practical method for partial match of time series46
AMMD: Attentive maximum mean discrepancy for few-shot image classification46
GripNet: Graph information propagation on supergraph for heterogeneous graphs46
Clustering experience replay for the effective exploitation in reinforcement learning45
Distributional barycenter problem through data-driven flows45
Identifying the key frames: An attention-aware sampling method for action recognition45
Multi-scale multi-hierarchy attention convolutional neural network for fetal brain extraction44
Temporal sparse adversarial attack on sequence-based gait recognition44
JSL3d: Joint subspace learning with implicit structure supervision for 3D pose estimation44
Learning pseudo labels for semi-and-weakly supervised semantic segmentation44
Feature selections based on two-type overlap degrees and three-view granulation measures for 44
LongReMix: Robust learning with high confidence samples in a noisy label environment44
Scale-selective and noise-robust extended local binary pattern for texture classification44
Weakly Supervised Instance Segmentation via Category-aware Centerness Learning with Localization Supervision43
A restarted large-scale spectral clustering with self-guiding and block diagonal representation43
Cluster prototype earth mover’s distance adapters and alignment-guided prompt learning for vision–language models43
The familiarity hypothesis: Explaining the behavior of deep open set methods43
Shadow-aware decomposed transformer network for shadow detection and removal43
Kernel-guided injection deep network for blind fusion of multispectral and panchromatic images43
Prototype learning based generic multiple object tracking via point-to-box supervision43
Uncertainty estimation in HDR imaging with Bayesian neural networks43
Finding compact and well-separated clusters: Clustering using silhouette coefficients43
High-order manifold regularized multi-view subspace clustering with robust affinity matrices and weighted TNN42
A large cross-modal video retrieval dataset with reading comprehension42
Auto-weighted Tensor Schatten p-Norm for Robust Multi-view Graph Clustering42
High-frequency and low-frequency dual-channel graph attention network42
Discovering an inference recipe for weakly-supervised object localization42
ScanMix: Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised Learning42
DM-GAN: CNN hybrid vits for training GANs under limited data42
Detection confidence driven multi-object tracking to recover reliable tracks from unreliable detections42
SpatioTemporal focus for skeleton-based action recognition42
Dynamic weighted knowledge distillation for brain tumor segmentation41
Dynamic selection for reconstructing instance-dependent noisy labels41
Privileged multi-task learning for attribute-aware aesthetic assessment41
EdVAE: Mitigating codebook collapse with evidential discrete variational autoencoders40
Progressive expansion for semi-supervised bi-modal salient object detection40
Dirichlet process mixture of Gaussian process functional regressions and its variational EM algorithm40
Answering knowledge-based visual questions via the exploration of Question Purpose40
Mix-ViT: Mixing attentive vision transformer for ultra-fine-grained visual categorization40
Cross-modal co-feedback cellular automata for RGB-T saliency detection40
A dense light field reconstruction algorithm for four-dimensional optical flow constraint equation40
Multi-stage image denoising with the wavelet transform40
A modified interval type-2 Takagi-Sugeno fuzzy neural network and its convergence analysis40
Fast subspace clustering by learning projective block diagonal representation39
Large motion anime head animation using a cascade pose transform network39
Polarized reflection removal with dual-stream attention guidance39
Game-theoretic hypergraph matching with density enhancement39
Learning generalized visual odometry using position-aware optical flow and geometric bundle adjustment39
Shape robustness in style enhanced cross domain semantic segmentation39
Scalable clustering by aggregating representatives in hierarchical groups39
Unsupervised learning of global factors in deep generative models39
Reconstruction of fragmented trajectories of collective motion using Hadamard deep autoencoders39
Human–object interaction detection via recycling of ground-truth annotations39
Split-and-merge model selection of mixtures of Gaussian processes with RJMCMC39
MS-TCRNet: Multi-Stage Temporal Convolutional Recurrent Networks for action segmentation using sensor-augmented kinematics39
FastUNet: Fast hierarchical multi-patch underwater enhancement network for industrial recirculating aquaculture39
A Sampling-Based Density Peaks Clustering Algorithm for Large-Scale Data38
ASF-Net: Robust video deraining via temporal alignment and online adaptive learning38
Occlusion-guided multi-modal fusion for vehicle-infrastructure cooperative 3D object detection38
A coded knowledge distillation framework for image classification based on adaptive JPEG encoding38
MUNet: Motion uncertainty-aware semi-supervised video object segmentation38
Riemannian representation learning for multi-source domain adaptation38
Fast adaptively balanced min-cut clustering38
RP-Net: A Robust Polar Transformation Network for rotation-invariant face detection38
ZooKT: Task-adaptive knowledge transfer of Model Zoo for few-shot learning38
Local Linear Embedding with Adaptive Neighbors38
SparseComm: An Efficient Sparse Communication Framework for Vehicle-Infrastructure Cooperative 3D Detection38
Frequency learning attention networks based on deep learning for automatic modulation classification in wireless communication38
Overcoming weaknesses of density peak clustering using a data-dependent similarity measure38
DA-GAN: Dual-attention generative adversarial networks for real-world exquisite makeup transfer38
Learning depth via leveraging semantics: Self-supervised monocular depth estimation with both implicit and explicit semantic guidance37
QFAE: Q-Function guided Action Exploration for offline deep reinforcement learning37
CRCGAN: Toward robust feature extraction in finger vein recognition37
A generalized multi-aspect distance metric for mixed-type data clustering37
MinEnt: Minimum entropy for self-supervised representation learning37
SNN using color-opponent and attention mechanisms for object recognition37
Hyper-sausage coverage function neuron model and learning algorithm for image classification37
0.13536596298218