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 2022-05-01 to 2026-05-01.)

Article	Citations
Looking beyond input frames: Self-supervised adaptation for video super-resolution	535
SpatioTemporal focus for skeleton-based action recognition	488
Distribution alignment for cross-device palmprint recognition	396
PSCFormer: A lightweight hybrid network for gas identification in electronic nose system	371
Self-supervised video object segmentation via pseudo label rectification	349
Spectral Contrastive Clustering	347
Multi-head graph contrastive learning with hop augmentation for node classification	335
Cascaded learning with transformer for simultaneous eye landmark, eye state and gaze estimation	327
DA-GAN: Dual-attention generative adversarial networks for real-world exquisite makeup transfer	295
RESKM: A General Framework to Accelerate Large-Scale Spectral Clustering	289
Synthetic unknown class learning for learning unknowns	246
Fuzzy clustering algorithm with locality preserving based on anchor graph	240
Mamba-Stereo: Mamba Regularization for Stereo matching	229
Adversarial spectral perturbation for single-domain generalized object detection	216
Occlusion-guided multi-modal fusion for vehicle-infrastructure cooperative 3D object detection	204
Bi-Attention enhanced representation learning for image-text matching	185
Gradual interaction network for stereo matching	180
Mix-ViT: Mixing attentive vision transformer for ultra-fine-grained visual categorization	174
Adapt only once: Fast unsupervised person re-identification via relevance-aware guidance	172
Progressive downsampling and adaptive guidance networks for dynamic scene deblurring	170
Editorial Board	169
FastOPM—A practical method for partial match of time series	166
Generalization capacity of multi-class SVM based on Markovian resampling	165
Mutual Domain Adaptation	165
Robust deep fuzzy K-means clustering for image data	157

Trunk-branch contrastive network with multi-view deformable aggregation for multi-view action recognition	156
A cross-network node classification method in open-set scenario	154
Unsupervised learning non-uniform face enhancement under physics-guided model of illumination decoupling	144
Striving for understanding: Deconstructing neural networks in side-channel analysis	140
Kinship verification using multi-level dictionary pair learning for multiple resolution images	139
Thermal to Visual Person Re-Identification Using Collaborative Metric Learning Based on Maximum Margin Matrix Factorization	129
Leveraging tensor kernels to reduce objective function mismatch in deep clustering	129
A modified interval type-2 Takagi-Sugeno fuzzy neural network and its convergence analysis	125
Phase Randomization: A data augmentation for domain adaptation in human action recognition	125
Pathological graph self-supervised learning for clear-cell renal cell carcinoma survival prediction	124
The MERIT dataset: Modelling and efficiently rendering interpretable transcripts	121
Robust multilayer bootstrap networks in ensemble for unsupervised representation learning and clustering	120
Multi-task meta label correction for time series prediction	119
Beyond mask: Rethinking guidance types in few-shot segmentation	119
Unsupervised update summarization of news events	119
Scaled robust linear embedding with adaptive neighbors preserving	116
MA-Neck: Mutual attention-based feature enhancement for lightweight object detection	115
Neural Normalized Cut: A differential and generalizable approach for spectral clustering	114
A dense light field reconstruction algorithm for four-dimensional optical flow constraint equation	112
Dynamic feature fusion with spatial-temporal context for robust object tracking	108
Deep graph matching meets mixed-integer linear programming: Relax or not ?	108
One-pass online learning under evolving feature data streams: A non-parametric model	107
Extrinsic kernel ridge regression classifier for Kendall’s planar shape space	104
Spectral approximation of Gaussian random graph Laplacians and applications to pattern recognition	104
Deep and wide nonnegative matrix factorization with embedded regularization	104
Intensity mixture and band-adaptive detail fusion for pansharpening	102
Sequence patterns and HMM profiles to predict proteome wide zinc finger motifs	100
W-EICMFusion: A fusion network for infrared and visible images utilising WOA hyperparameter optimisation	100
Implicit face model: Depth super-resolution for 3D face recognition	99
DCFusion: Difference correlation-driven fusion mechanism of infrared and visible images	98
GriT-DBSCAN: A spatial clustering algorithm for very large databases	98
State transition difference prediction for deep reinforcement learning	98
Spectral compression transformer with line pose graph for monocular 3D human pose estimation	98
MSG-CLIP: Enhancing CLIP’s ability to learn fine-grained structural associations through multi-modal scene graph alignment	97
Text-guided weakly supervised framework for dynamic facial expression recognition	97
Cross-modal co-feedback cellular automata for RGB-T saliency detection	96
End-to-end susceptibility-induced distortion correction for diffusion MRI with unsupervised deep learning	94
Support subsets estimation for support vector machines retraining	93
DC-AD: A Divide-and-Conquer Method for Few-Shot Anomaly Detection	93
Locally adaptive one-class classifier fusion with dynamic ℓ	92
A neighborhood-based method for mining and fusing positive and negative false samples	91
Pseudo-labeling with keyword refining for few-supervised video captioning	91
Cross-Modality Interactive Attention Network for AI-generated image quality assessment	90
Consistency-driven feature scoring and regularization network for visible–infrared person re-identification	90
Privileged multi-task learning for attribute-aware aesthetic assessment	89
Improving the Facial Expression Recognition and Its Interpretability via Generating Expression Pattern-map	89
Frequency-domain multi-scale graph learning with information-theoretic constraint for spatio-temporal prediction	88
Temporal consistent multi-view perception for robust embodied manipulation	87
Two phase cooperative learning for supervised dimensionality reduction	87
Attention-assisted multilevel fusion framework for generalized iris presentation attack detection	86

Adaptive integration of textual context and visual embeddings for underrepresented vision classification	86
Hypergraph-driven landmark detection foundation model on echocardiography for cardiac function quantification	86
Training-free subject-enhanced attention guidance for compositional text-to-image generation	85
Improving lesion segmentation in medical images by global and regional feature compensation	84
Density peaks clustering algorithm integrating manifold distance and mutual nearest neighbors	83
GraphProbe: Knowledge Probing for Graph Representation Learning	82
STAR-Net: an interpretable model-aided network for remote sensing image denoising	81