OOIR: Observatory of International Research

Papers

(The H4-Index of Pattern Recognition is 79. 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.)

Article	Citations
Editorial Board	324
Retraction Notice	311
A cross-network node classification method in open-set scenario	267
Cross-modal co-feedback cellular automata for RGB-T saliency detection	246
Effective action recognition with embedded key point shifts	222
Holistic word descriptor for lexicon reduction in handwritten arabic documents	219
Progressive downsampling and adaptive guidance networks for dynamic scene deblurring	207
Distance-aware network for physical-world object distribution estimation and counting	192
Robust multilayer bootstrap networks in ensemble for unsupervised representation learning and clustering	184
A neighborhood-based method for mining and fusing positive and negative false samples	183
FastOPM—A practical method for partial match of time series	183
Two phase cooperative learning for supervised dimensionality reduction	183
Deep graph matching meets mixed-integer linear programming: Relax or not ?	174
Looking beyond input frames: Self-supervised adaptation for video super-resolution	169
Privileged multi-task learning for attribute-aware aesthetic assessment	163
An entity-weights-based convolutional neural network for large-sale complex knowledge embedding	161
Occlusion-guided multi-modal fusion for vehicle-infrastructure cooperative 3D object detection	160
A Sampling-Based Density Peaks Clustering Algorithm for Large-Scale Data	160
Fast adaptively balanced min-cut clustering	149
DA-GAN: Dual-attention generative adversarial networks for real-world exquisite makeup transfer	141
Knowledge memorization and generation for action recognition in still images	138
Synthetic unknown class learning for learning unknowns	138
Sketches by MoSSaRT: Representative selection from manifolds with gross sparse corruptions	135
Phase Randomization: A data augmentation for domain adaptation in human action recognition	134
CORE: Learning consistent ordinal representations with convex optimization for image ordinal estimation	133

DCFusion: Difference correlation-driven fusion mechanism of infrared and visible images	133
Leveraging tensor kernels to reduce objective function mismatch in deep clustering	130
Extrinsic kernel ridge regression classifier for Kendall’s planar shape space	126
Thermal to Visual Person Re-Identification Using Collaborative Metric Learning Based on Maximum Margin Matrix Factorization	125
Kinship verification using multi-level dictionary pair learning for multiple resolution images	124
Hyper-feature aggregation and relaxed distillation for class incremental learning	122
DynamicKD: An effective knowledge distillation via dynamic entropy correction-based distillation for gap optimizing	119
Robust Table Detection and Structure Recognition from Heterogeneous Document Images	117
Sequence patterns and HMM profiles to predict proteome wide zinc finger motifs	116
Cascaded learning with transformer for simultaneous eye landmark, eye state and gaze estimation	113
Mutual Domain Adaptation	113
MTS2Graph: Interpretable multivariate time series classification with temporal evolving graphs	112
Unsupervised update summarization of news events	110
A dense light field reconstruction algorithm for four-dimensional optical flow constraint equation	109
Multi-task meta label correction for time series prediction	109
A modified interval type-2 Takagi-Sugeno fuzzy neural network and its convergence analysis	109
Crossover-Net: Leveraging vertical-horizontal crossover relation for robust medical image segmentation	109
Improving the Facial Expression Recognition and Its Interpretability via Generating Expression Pattern-map	107
An illumination-guided dual attention vision transformer for low-light image enhancement	106
PSCFormer: A lightweight hybrid network for gas identification in electronic nose system	106
Intensity mixture and band-adaptive detail fusion for pansharpening	105
Enhanced visible–infrared person re-identification based on cross-attention multiscale residual vision transformer	105
Switching clusters’ synchronization for discrete space-time complex dynamical networks via boundary feedback controls	104
Support subsets estimation for support vector machines retraining	103
SARS-Net: COVID-19 detection from chest x-rays by combining graph convolutional network and convolutional neural network	102
Identifying the key frames: An attention-aware sampling method for action recognition	101
Bounded exponential loss function based AdaBoost ensemble of OCSVMs	100
Unsupervised person re-identification via multi-domain joint learning	99
DM-GAN: CNN hybrid vits for training GANs under limited data	98
Temporal sparse adversarial attack on sequence-based gait recognition	97
A generalized multi-aspect distance metric for mixed-type data clustering	97
RESKM: A General Framework to Accelerate Large-Scale Spectral Clustering	96
eX-ViT: A Novel explainable vision transformer for weakly supervised semantic segmentation	93
Distribution alignment for cross-device palmprint recognition	92
Deep reinforcement learning with credit assignment for combinatorial optimization	91
Bi-Attention enhanced representation learning for image-text matching	91
Adapt only once: Fast unsupervised person re-identification via relevance-aware guidance	88
Pseudo-labeling with keyword refining for few-supervised video captioning	87
Dynamic selection for reconstructing instance-dependent noisy labels	87
Consistency-driven feature scoring and regularization network for visible–infrared person re-identification	87
GriT-DBSCAN: A spatial clustering algorithm for very large databases	87
Robust deep fuzzy K-means clustering for image data	86
Inter-Attribute awareness for pedestrian attribute recognition	86
BiconNet: An edge-preserved connectivity-based approach for salient object detection	84
Adaptive, Hybrid Feature Selection (AHFS)	84
FoCL: Feature-oriented continual learning for generative models	84
Generalization capacity of multi-class SVM based on Markovian resampling	84
Explainable AI in human motion: A comprehensive approach to analysis, modeling, and generation	84
Head pose estimation using deep neural networks and 3D point clouds	83
TBConvL-Net: A hybrid deep learning architecture for robust medical image segmentation	83

SpatioTemporal focus for skeleton-based action recognition	83
LCU-Net: A novel low-cost U-Net for environmental microorganism image segmentation	83
Dynamic feature fusion with spatial-temporal context for robust object tracking	83
Offline signature verification using a region based deep metric learning network	82
A Dual Self-Attention mechanism for vehicle re-Identification	79
Supervised penalty-based aggregation applied to motor-imagery based brain-computer-interface	79
ANNE: Adaptive Nearest Neighbours and Eigenvector-based sample selection for robust learning with noisy labels	79