Pattern Recognition Letters

Papers
(The TQCC of Pattern Recognition Letters is 8. 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 2022-08-01 to 2026-08-01.)
ArticleCitations
Function-based labels for complementary recommendation: Definition, annotation, and LLM-as-a-Judge236
Robust clustering algorithm: The use of soft trimming approach173
EasyFuse: Easy-to-learn visible and infrared image fusion framework based on unpaired set85
Single-/Multi-Source Domain Adaptation via domain separation: A simple but effective method78
Quantized DiT with hadamard transformation: A technical report73
Adaptive recursive channel selection for robust decoding of motor imagery EEG signal in patients with intracerebral hemorrhage70
Guiding multimodal LLMs for efficient visual place recognition65
An analytic study on clustering driven self-supervised speaker verification58
A micro Reinforcement Learning architecture for Intrusion Detection Systems56
VWENet: Volumetric wavelet and mixture-of-experts network for 3D medical image segmentation53
Cross-attention based dual-similarity network for few-shot learning53
Multi-dataset fusion for multi-task learning on face attribute recognition53
Fake News Detection using Hashtag Context50
Thermal crowd counting by distilling multi-modal knowledge47
Detection of visual pursuits using 1D convolutional neural networks47
Extending the kinematic theory of rapid movements with new primitives43
Dual quaternion ambisonics array for six-degree-of-freedom acoustic representation43
FCL-ViT: Task-aware attention tuning for Continual Learning42
Lightweight moment-residual-coherent patterns for image recognition41
Innovative multi-modal approaches to Alzheimer’s disease detection: Transformer hybrid model and adaptive MLP-Mixer41
Rethinking 3D cost aggregation in stereo matching41
GenR: Generative latent inversion for blind face restoration41
Achieving high performance on sketch-based image retrieval without real sketches for training40
AMGB: Trajectory prediction using attention-based mechanism GCN-BiLSTM in IOV40
OSS-OCL: Occlusion Scenario Simulation and Occluded-edge Concentrated Learning for pedestrian detection39
Entropy calibrated prototype embedding for transductive few-shot learning37
SYNAuG: Exploiting synthetic data for data imbalance problems37
Semantic-aware self-supervised depth estimation for stereo 3D detection36
Clustering criteria: What defines a good cluster?36
CrossFormer: Cross-guided attention for multi-modal object detection34
Conditional Stable Diffusion for Distortion Correction and Image Rectification34
DLR: Adversarial examples detection and label recovery for deep neural networks34
Entire-detail motion dual-branch network for micro-expression recognition34
GFMRC: A machine reading comprehension model for named entity recognition34
Editorial Board34
Underwater image color correction via global-local collaborative strategy34
VMamba-Crowd: Bridging multi-scale features from Visual Mamba for weakly-supervised crowd counting34
Distilling EEG representations via capsules for affective computing34
Inter-separability and intra-concentration to enhance stochastic neural network adversarial robustness33
Reflections of an ancient document processor32
Special section: Best papers of the 14th Mexican conference on pattern recognition (MCPR) 202232
The diversified-equal loss for image translation tasks32
Efficient graph edit distance computation using isomorphic vertices30
Stochastic first-order learning for large-scale flexibly tied Gaussian mixture models30
Index for assessment of stationarity in spatiotemporal climatic signals29
Skeleton-based estimation of interaction readiness via spatio-temporal graph convolution29
An improved lightweight two-dimensional human pose estimation network29
Learning to resolve uncertainties for large-scale face recognition29
DM-SR: Diffusion-based multimodal semantic restoration within semantic communication systems29
HDRfeat: A feature-rich network for high dynamic range image reconstruction28
Hiding data hiding28
Probability propagation for faster and efficient point cloud segmentation using a neural network28
Adaptive dynamic networks for object detection in aerial images28
Dual-stream correlation exploration for face anti-Spoofing28
Fusion Regression27
FoodMem: Near real-time and precise food video segmentation27
Similarity activation map for co-salient object detection27
A novel ensemble model with two-stage learning for joint dialog act recognition and sentiment classification26
Multi-period interaction networks for time series forecasting26
Single image super-resolution using Wasserstein generative adversarial network with gradient penalty25
Edge aware adaptive fusion network for video salient object detection25
Self-supervised multi-echo point cloud denoising in snowfall25
Manifold information through neighbor embedding projection for image retrieval25
Attribute disentanglement with gradient reversal for interactive fashion retrieval25
Editorial Board25
Enhancing visual adversarial transferability via affine transformation of intermediate-level perturbations25
GAF-Net: A new automated segmentation method based on multiscale feature fusion and feedback module24
Breaking the limits: Synergizing LLM-generated feedback and neighborhood selection for misinformation detection24
FGFDL: Frame grouping and feature dissimilarity learning for reverse video recognition24
Optimized Deep Isolation Forest24
Example forgetting and rehearsal in continual learning24
Spike-TBR: A noise resilient neuromorphic event representation24
New advances in body composition assessment with ShapedNet: A single image deep regression approach23
Real-time identification of eye fixations and saccades using radial basis function networks and Markov chains23
TMO-Det: Deep tone-mapping optimized with and for object detection23
GlueHardener: Correspondence enhancement with geometric constraints for visual odometry23
Offline handwritten signature verification under a stream context with partially labeled data23
Exploring percolation features with polynomial algorithms for classifying Covid-19 in chest X-ray images23
Graph Neural Networks for 3D facial morphology: Assessing the effectiveness of anthropometric and automated landmark detection23
N-QGNv2: Predicting the optimum quadtree representation of a depth map from a monocular camera22
Continual learning for adaptive social network identification22
CGNN: Caption-assisted graph neural network for image-text retrieval21
On the robustness of self-supervised representations for multi-view object classification21
Diverse video captioning through latent variable expansion21
Analysis of systems’ performance in natural language processing competitions21
A more reliable local-global-guided network for correspondence pruning20
Summarized knowledge guidance for single-frame temporal action localization20
Learning on sample-efficient and label-efficient multi-view cardiac data with graph transformer20
Deep active learning: A reality check20
Visual grounding of remote sensing images with multi-dimensional semantic-guidance20
Generation of super-resolution for medical image via a self-prior guided Mamba network with edge-aware constraint20
Classification of emotions using EEG activity associated with different areas of the brain20
Deep graph neural network architecture enhanced by self-attention aggregation mechanism20
Dual Feature Enhancement Graph Clustering Network19
Transformer vision-language tracking via proxy token guided cross-modal fusion19
Tadmo: A tabular distance measure with move operations19
Multimodal AI-enhanced ship detection for mapping fishing vessels and informing on suspicious activities19
ProFeat: Unsupervised image clustering via progressive feature refinement19
Kernel-based convolution expansion for facial expression recognition19
SHCNet: A semi-supervised hypergraph convolutional networks based on relevant feature selection for hyperspectral image classification19
Cross-project defect prediction based on G-LSTM model19
Improving out-of-domain generalization in Multiple Sclerosis detection and segmentation using Random Convolutions19
AF-CANet: Augmentation-free, curriculum-guided attention UNet framework for few-shot document layout analysis18
Zero-shot ear cross-dataset transfer for person recognition on mobile devices18
Convolutional Spiking Neural Networks targeting learning and inference in highly imbalanced datasets18
A lightness-aware loss for low-light image enhancement18
A novel ensemble approach for crop disease detection by leveraging customized EfficientNets and interpretability18
Memory-based Transformer with shorter window and longer horizon for multivariate time series forecasting18
Improving the matching of deformable objects by learning to detect keypoints17
Fast approximate maximum common subgraph computation17
Use estimated signal and noise to adjust step size for image restoration17
Transforming gradient-based techniques into interpretable methods17
Adversarial training of LSTM-ED based anomaly detection for complex time-series in cyber-physical-social systems17
Coarse to fine image matching by mining matchable regions and geometric cues17
Multicriteria decision support employing adaptive prediction in a tensor-based feature representation17
Neural network based cognitive approaches from face perception with human performance benchmark17
Enhancing precipitation detection: A multi-sensor approach using conditional GANs and recurrent networks17
Data augmentation in time series forecasting through inverted framework17
Deep neural network with deformable convolution and side window convolution for image denoising17
Attentive ExFeat based deep generative adversarial network for noise robust face super-resolution17
RobustPrompt: Learning to defend against adversarial attacks with adaptive visual prompts17
Decoding attention from the visual cortex: fMRI-based prediction of human saliency maps17
Learning to chase: Adaptive audio-visual navigation for moving sounds in complex environments17
Attention Mechanism Based Mixture of Gaussian Processes16
PAT: Pixel-wise Adaptive Training for long-tailed segmentation16
Dark channel map and union training strategy for object detection in foggy scenes16
FSE: Continual Learning for Named Entity Recognition by Fast-Slow Experts16
Clustering-inspired channel selection method for weakly supervised object localization16
VTHSC-MIR: Vision Transformer Hashing with Supervised Contrastive learning based medical image retrieval16
Hyperspectral image classification using feature-weighted fusion with Kolmogorov-Arnold network and graph attention network16
Cross-erasure enhanced network for occluded person re-identification16
Aggregated masked autoencoding for offline reinforcement learning16
Editorial Board16
CAMFND: Cross-modal adaptive-aware learning for multimodal fake news detection16
Locality-aware subgraphs for inductive link prediction in knowledge graphs16
Geometric insights into focal loss: Reducing curvature for enhanced model calibration16
GCAESeg: Grouped Channel Attention Enhanced network for thyroid nodule segmentation in ultrasound images15
Special section: CIARP-2415
CSF: Closed-mask-guided semantic fusion method for semantic perception of unknown scenes15
Style transformation super-resolution GAN for extremely small infrared target image15
MCFP: A multi-target 3D perception method with weak dependence on 2D detectors15
Corrigendum to “Keyword weight optimization using gradient strategies in event focused web crawling” Pattern recognition letters volume 142 (2021) pages 3-1015
Comparing filter and wrapper approaches for feature selection in handwritten character recognition15
Panoramic brain network analyzer: A residual graph network with attention mechanism for autism spectrum disorder diagnosis15
Improving radial lens distortion correction with multi-task learning15
NAS For efficient mobile eyebrow biometrics15
Group commonality graph: Multimodal pedestrian trajectory prediction via deep group features15
Metadata, wavelet, and time aware diffusion models for satellite image super resolution15
Weight Saliency search with Semantic Constraint for Neural Machine Translation attacks15
CLIPRefiner: Enhancing realism and detail in free-hand sketches through semantically-aware optimization15
3D ear reconstruction with Neural-Powell optimized SOP and curvature guidance15
DuaFace: Data uncertainty in angular based loss for face recognition15
Global-local graph neural networks for node-classification15
Automatic dottization of Arabic text (Rasms) using deep recurrent neural networks14
Learning a robust RGB-Thermal detector for extreme modality imbalance14
Segment Anything Model for detecting salient objects with accurate prompting and Ladder Directional Perception14
An overhead-free region-based JPEG framework for task-driven image compression14
On why and how statistical significance criteria can guide multivariate time series motif analysis14
An efficient ensemble explainable AI (XAI) approach for morphed face detection14
Transductive t-SNE (tt-SNE) for classification and data visualization14
Interpretable answer retrieval based on heterogeneous network embedding14
Kreĭn twin support vector machines for imbalanced data classification14
Dense multiscale inference network for lightweight salient object detection of strip steel surface defects14
InDeepFake: A novel multimodal multilingual indian deepfake video dataset14
DRSGen: Diagnostic-region-guided single-domain generalization for thyroid nodule segmentation14
HLCN: A Hypergraph Laplace Contrastive Network for enhanced multimodal sentiment analysis14
Graph neural collaborative filtering with medical content-aware pre-training for treatment pattern recommendation14
SAMIRO: Spatial Attention Mutual Information Regularization with a pre-trained model as Oracle for lane detection14
TCDI-Net: Early fake news detection network via topical context enhancement and cross-modal deep interaction14
Introduction to the special issue on “Computer vision solutions for part-based image analysis and classification (CV_PARTIAL)”13
Multi-low resource languages in palm leaf manuscript recognition: Syllable-based augmentation and error analysis13
Discriminative projection fuzzy K-Means with adaptive neighbors13
Enhancing surface normal estimation with cross-modal attention RGB-D fusion and adversarial Schrödinger bridge13
Dead pixel test using effective receptive field13
MIF: Multi-source information fusion for few-shot classification with CLIP13
Editorial for special section ‘ICPR 2020’13
Multifractal characterization and recognition of animal behavior based on deep wavelet transform13
A Bayesian network combiner for multimodal handwriting analysis in Alzheimer’s disease detection13
Improving Parkinson’s disease recognition through voice analysis using deep learning13
Uncertainty quantification metrics for deep regression13
DAT: A robust Discriminant Analysis-based Test of unimodality for unknown input distributions13
PSA-Det3D: Pillar set abstraction for 3D object detection13
Information theoretic clustering of the human pangenome minigraph13
Assessing demographic bias in brain age prediction models using multiple deep learning paradigms12
A Jackknife-Inspired Deep Learning Approach to Subject-Independent Classification of EEG12
Editorial Board12
Hand-object information embedded dexterous grasping generation12
ABAE: Auxiliary Balanced AutoEncoder for class-imbalanced semi-supervised learning12
Channel-spatial knowledge distillation for efficient semantic segmentation12
Reducing redundancy in the bottleneck representation of autoencoders12
KeyEncoder: A secure and usable EEG-based cryptographic key generation mechanism12
Camera-independent color constancy by scene semantics12
An improved entity recognition approach to cyber-social knowledge provision of intellectual property using a CRF-LSTM model12
Distributed edge-event-triggered consensus of multi-agent system under DoS attack12
Prototype distance ratio sampling for generalised few shot object detection12
Multi-scale self-attention-based feature enhancement for detection of targets with small image sizes12
Voxel and deep learning based depth complementation for transparent objects12
Robust time series explanations via information-theoretic temporal structural priors12
Mind the data: Evaluating data quality sensitivity in medical LLMs12
Data-agnostic Face Image Synthesis Detection using Bayesian CNNs12
Explainable few-shot learning with visual explanations on a low resource pneumonia dataset12
Multi-scale self-attention mixup for graph classification12
Adversarial image generation by spatial transformation in perceptual colorspaces12
TRIS: A multimodal and multitask framework for unifying text–image retrieval and referring image segmentation12
Addressing domain discrepancy: A dual-branch collaborative model to unsupervised dehazing12
Non-parametric discretization for probabilistic labeled data12
Feature decomposition-based gaze estimation with auxiliary head pose regression12
Denoising diffusion model with adversarial learning for unsupervised anomaly detection on brain MRI images12
Hierarchical supervisions with two-stream network for Deepfake detection12
Open set classification of untranscribed handwritten text image documents11
Memory-efficient distribution-guided experience sampling for policy consolidation11
Editorial Board11
CTCSANet: An adaptive channel-spatial attention network for abdominal organ segmentation11
Exploiting deep and hand-crafted features for texture image retrieval using class membership11
CustomDepth: Customizing point-wise depth categories for depth completion11
Patterns of vehicle lights: Addressing complexities of camera-based vehicle light datasets and metrics11
Tri-modal causal learning for forecasting EV charging demand11
Multi-head second-order pooling for graph transformer networks11
Local Selective Vision Transformer for Depth Estimation Using a Compound Eye Camera11
An explainable super-resolution visual method for micro-crack image detection11
Federated learning with 1 regularization11
A closed-form solution for conditional multidimensional scaling11
An asymmetric heuristic for trained ternary quantization based on the statistics of the weights: An application to medical signal classification11
Social domain integrated semantic self-discovery method for recommendation11
Information extraction in handwritten historical logbooks11
MVSSC: Meta-reinforcement learning based visual indoor navigation using multi-view semantic spatial context11
SPOT: An efficient training-free task similarity quantification method for continual learning11
Mask-guided cycle-GAN for specular highlight removal11
SqCLIRIL: Spoken query cross-lingual information retrieval in Indian languages11
STaTS: Structure-aware temporal sequence summarization via statistical window merging11
Image outpainting guided by prior structure information11
EPRVFL: A fast and scalable model for real-time fake news detection11
Autoencoders with exponential deviation loss for weakly supervised anomaly detection11
Editorial Board11
Artistic neural style transfer using CycleGAN and FABEMD by adaptive information selection11
HARWE: A multi-modal large-scale dataset for context-aware human activity recognition in smart working environments11
ADFNeT: Adaptive decomposition and fusion for color constancy11
Less is more: A minimalist approach to robust GAN-generated face detection11
Object detection in drone video based on recurrent motion attention11
DSR-Diff: Depth map super-resolution with diffusion model11
Attribute alignment networks for generalized zero-shot learning10
A method for evaluating deep generative models of images for hallucinations in high-order spatial context10
Editorial Board10
Multi-Prototypes representation learning for contrastive clustering10
Object – PSF: A unified representation framework for end-to-end panoptic segmentation forecasting10
Multi-Modal masked autoencoder and parallel Mamba for 3D brain tumor segmentation10
Time-aware and task-transferable adversarial attack for perception of autonomous vehicles10
Collaborative feature alignment with global–local fusion for fine-grained sketch-based image retrieval10
RHRAF: Residual hypergraph refinement with adaptive fusion for open-set facial expression image retrieval10
Multi-scale convolutional networks for traffic forecasting with spatial-temporal attention10
0.47824692726135