OOIR: Observatory of International Research

Papers

(The H4-Index of Pattern Recognition is 81. 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 2021-08-01 to 2025-08-01.)

Article	Citations
Editorial Board	384
Retraction Notice	357
Cross-modal co-feedback cellular automata for RGB-T saliency detection	289
Effective action recognition with embedded key point shifts	288
Holistic word descriptor for lexicon reduction in handwritten arabic documents	258
Progressive downsampling and adaptive guidance networks for dynamic scene deblurring	257
Robust multilayer bootstrap networks in ensemble for unsupervised representation learning and clustering	241
FastOPM—A practical method for partial match of time series	205
Two phase cooperative learning for supervised dimensionality reduction	205
Deep graph matching meets mixed-integer linear programming: Relax or not ?	199
Privileged multi-task learning for attribute-aware aesthetic assessment	187
Looking beyond input frames: Self-supervised adaptation for video super-resolution	187
DA-GAN: Dual-attention generative adversarial networks for real-world exquisite makeup transfer	175
Sketches by MoSSaRT: Representative selection from manifolds with gross sparse corruptions	174
Generalization capacity of multi-class SVM based on Markovian resampling	171
Occlusion-guided multi-modal fusion for vehicle-infrastructure cooperative 3D object detection	160
Adapt only once: Fast unsupervised person re-identification via relevance-aware guidance	142
Thermal to Visual Person Re-Identification Using Collaborative Metric Learning Based on Maximum Margin Matrix Factorization	142
Unsupervised update summarization of news events	140
Self-supervised video object segmentation via pseudo label rectification	140
Distribution alignment for cross-device palmprint recognition	139
Gradual interaction network for stereo matching	139
Multi-task meta label correction for time series prediction	138
DCFusion: Difference correlation-driven fusion mechanism of infrared and visible images	137
Temporal sparse adversarial attack on sequence-based gait recognition	136

Neural Normalized Cut: A differential and generalizable approach for spectral clustering	135
Mutual Domain Adaptation	135
Spectral approximation of Gaussian random graph Laplacians and applications to pattern recognition	133
A modified interval type-2 Takagi-Sugeno fuzzy neural network and its convergence analysis	132
A dense light field reconstruction algorithm for four-dimensional optical flow constraint equation	132
Unsupervised learning non-uniform face enhancement under physics-guided model of illumination decoupling	130
Implicit face model: Depth super-resolution for 3D face recognition	130
Balanced seed selection for K-means clustering with determinantal point process	129
A bijective inference network for interpretable identification of RNA N	127
Sequence patterns and HMM profiles to predict proteome wide zinc finger motifs	126
Improving the Facial Expression Recognition and Its Interpretability via Generating Expression Pattern-map	125
Support subsets estimation for support vector machines retraining	120
Training-free Subject-Enhanced Attention Guidance for Compositional Text-to-image Generation	120
ANNE: Adaptive Nearest Neighbours and Eigenvector-based sample selection for robust learning with noisy labels	119
Enhanced visible–infrared person re-identification based on cross-attention multiscale residual vision transformer	119
Leveraging tensor kernels to reduce objective function mismatch in deep clustering	118
Deep reinforcement learning with credit assignment for combinatorial optimization	118
A Dual Self-Attention mechanism for vehicle re-Identification	116
Robust deep fuzzy K-means clustering for image data	116
A Sampling-Based Density Peaks Clustering Algorithm for Large-Scale Data	116
Bounded exponential loss function based AdaBoost ensemble of OCSVMs	116
Deep and wide nonnegative matrix factorization with embedded regularization	115
Explainable AI in human motion: A comprehensive approach to analysis, modeling, and generation	115
Knowledge memorization and generation for action recognition in still images	114
Temporal Consistent Multi-View Perception for Robust Embodied Manipulation	113
Mix-ViT: Mixing attentive vision transformer for ultra-fine-grained visual categorization	112
Pseudo-labeling with keyword refining for few-supervised video captioning	108
Robust Table Detection and Structure Recognition from Heterogeneous Document Images	103
DM-GAN: CNN hybrid vits for training GANs under limited data	102
RESKM: A General Framework to Accelerate Large-Scale Spectral Clustering	98
Dynamic selection for reconstructing instance-dependent noisy labels	95
SpatioTemporal focus for skeleton-based action recognition	94
Striving for understanding: Deconstructing neural networks in side-channel analysis	94
MTS2Graph: Interpretable multivariate time series classification with temporal evolving graphs	94
A neighborhood-based method for mining and fusing positive and negative false samples	94
Bi-Attention enhanced representation learning for image-text matching	92
Consistency-driven feature scoring and regularization network for visible–infrared person re-identification	92
A cross-network node classification method in open-set scenario	92
An entity-weights-based convolutional neural network for large-sale complex knowledge embedding	92
Phase Randomization: A data augmentation for domain adaptation in human action recognition	92
DynamicKD: An effective knowledge distillation via dynamic entropy correction-based distillation for gap optimizing	91
Kinship verification using multi-level dictionary pair learning for multiple resolution images	91
Extrinsic kernel ridge regression classifier for Kendall’s planar shape space	90
Dynamic weighted knowledge distillation for brain tumor segmentation	89
Intensity mixture and band-adaptive detail fusion for pansharpening	89
FoCL: Feature-oriented continual learning for generative models	89
Dynamic feature fusion with spatial-temporal context for robust object tracking	89
Distance-aware network for physical-world object distribution estimation and counting	88
eX-ViT: A Novel explainable vision transformer for weakly supervised semantic segmentation	85
DC-AD: A Divide-and-Conquer Method for Few-Shot Anomaly Detection	85

CORE: Learning consistent ordinal representations with convex optimization for image ordinal estimation	84
MSAN: Multiscale self-attention network for pansharpening	83
SARS-Net: COVID-19 detection from chest x-rays by combining graph convolutional network and convolutional neural network	83
GriT-DBSCAN: A spatial clustering algorithm for very large databases	82
Inter-Attribute awareness for pedestrian attribute recognition	82
Head pose estimation using deep neural networks and 3D point clouds	81
BiconNet: An edge-preserved connectivity-based approach for salient object detection	81
Cascaded learning with transformer for simultaneous eye landmark, eye state and gaze estimation	81
Switching clusters’ synchronization for discrete space-time complex dynamical networks via boundary feedback controls	81