OOIR: Observatory of International Research

Papers

(The H4-Index of Pattern Recognition is 85. 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.)

Article	Citations
Progressive downsampling and adaptive guidance networks for dynamic scene deblurring	579
Editorial Board	522
FastOPM—A practical method for partial match of time series	448
Multi-task meta label correction for time series prediction	427
Mutual Domain Adaptation	427
One-pass online learning under evolving feature data streams: A non-parametric model	412
Robust deep fuzzy K-means clustering for image data	399
Generalization capacity of multi-class SVM based on Markovian resampling	397
Support subsets estimation for support vector machines retraining	330
Looking beyond input frames: Self-supervised adaptation for video super-resolution	322
The MERIT dataset: Modelling and efficiently rendering interpretable transcripts	284
Pathological graph self-supervised learning for clear-cell renal cell carcinoma survival prediction	266
Bi-Attention enhanced representation learning for image-text matching	243
Sequence patterns and HMM profiles to predict proteome wide zinc finger motifs	237
Spectral approximation of Gaussian random graph Laplacians and applications to pattern recognition	234
End-to-end susceptibility-induced distortion correction for diffusion MRI with unsupervised deep learning	203
Text-guided weakly supervised framework for dynamic facial expression recognition	201
Density peaks clustering algorithm integrating manifold distance and mutual nearest neighbors	187
GraphProbe: Knowledge Probing for Graph Representation Learning	186
Spectral compression transformer with line pose graph for monocular 3D human pose estimation	186
Adaptive proximal regularization for image smoothing	184
Inter-Attribute awareness for pedestrian attribute recognition	182
A Sampling-Based Density Peaks Clustering Algorithm for Large-Scale Data	181
Hyper-feature aggregation and relaxed distillation for class incremental learning	178
CORE: Learning consistent ordinal representations with convex optimization for image ordinal estimation	172

An entity-weights-based convolutional neural network for large-sale complex knowledge embedding	171
Balanced seed selection for K-means clustering with determinantal point process	163
Beyond similarity: Mutual information-guided retrieval for in-context learning in VQA	162
State transition difference prediction for deep reinforcement learning	159
Consistency-driven feature scoring and regularization network for visible–infrared person re-identification	141
A modified interval type-2 Takagi-Sugeno fuzzy neural network and its convergence analysis	140
Kinship verification using multi-level dictionary pair learning for multiple resolution images	134
Extrinsic kernel ridge regression classifier for Kendall’s planar shape space	134
Improving lesion segmentation in medical images by global and regional feature compensation	131
Thermal to Visual Person Re-Identification Using Collaborative Metric Learning Based on Maximum Margin Matrix Factorization	131
Striving for understanding: Deconstructing neural networks in side-channel analysis	131
Adaptive integration of textual context and visual embeddings for underrepresented vision classification	130
Kernel-aware dynamic convolution for dense prediction	128
Hypergraph-driven landmark detection foundation model on echocardiography for cardiac function quantification	128
Beyond mask: Rethinking guidance types in few-shot segmentation	127
Domain aware post training quantization for vision transformers in deployment	127
RESKM: A General Framework to Accelerate Large-Scale Spectral Clustering	125
Frequency-domain multi-scale graph learning with information-theoretic constraint for spatio-temporal prediction	123
Privileged multi-task learning for attribute-aware aesthetic assessment	121
Spectral Contrastive Clustering	121
Unsupervised update summarization of news events	120
Supervised penalty-based aggregation applied to motor-imagery based brain-computer-interface	120
Gradual interaction network for stereo matching	118
RVSA-3D: Voxel-based fully sparse attention 3D object detection for rail transit obstacle perception	118
Two phase cooperative learning for supervised dimensionality reduction	116
Deep and wide nonnegative matrix factorization with embedded regularization	115
Unsupervised learning non-uniform face enhancement under physics-guided model of illumination decoupling	113
Locally adaptive one-class classifier fusion with dynamic ℓp-Norm constraints for robust anomaly detection	113
Temporal consistent multi-view perception for robust embodied manipulation	111
Adversarial spectral perturbation for single-domain generalized object detection	106
Attention-assisted multilevel fusion framework for generalized iris presentation attack detection	106
A Dual Self-Attention mechanism for vehicle re-Identification	104
Mamba-Stereo: Mamba Regularization for Stereo matching	104
A dense light field reconstruction algorithm for four-dimensional optical flow constraint equation	104
Unsupervised person re-identification via multi-domain joint learning	101
Dynamic feature fusion with spatial-temporal context for robust object tracking	100
Identifying the key frames: An attention-aware sampling method for action recognition	100
Neural Normalized Cut: A differential and generalizable approach for spectral clustering	100
GNS2CCL: A graph network semi-supervised concept-cognitive learning model for node classification	99
Enhanced visual prompt meets low-light saliency detection	96
Multidimensional nonlinear transform-based tensor representation for high-dimensional image reconstruction	95
Training-free subject-enhanced attention guidance for compositional text-to-image generation	95
Fast adaptively balanced min-cut clustering	94
Robust multilayer bootstrap networks in ensemble for unsupervised representation learning and clustering	93
Cascaded learning with transformer for simultaneous eye landmark, eye state and gaze estimation	93
Trunk-branch contrastive network with multi-view deformable aggregation for multi-view action recognition	93
Synthetic unknown class learning for learning unknowns	93
Self-supervised video object segmentation via pseudo label rectification	91
DM-GAN: CNN hybrid vits for training GANs under limited data	91
Enhanced visible–infrared person re-identification based on cross-attention multiscale residual vision transformer	91

A cross-network node classification method in open-set scenario	90
From temporal thumbnail to semantics: Debiasing multi-view action recognition	89
Dynamic selection for reconstructing instance-dependent noisy labels	89
Distribution alignment for cross-device palmprint recognition	88
STAR-Net: an interpretable model-aided network for remote sensing image denoising	88
Robust Table Detection and Structure Recognition from Heterogeneous Document Images	88
Cross-modal co-feedback cellular automata for RGB-T saliency detection	88
Distance-aware network for physical-world object distribution estimation and counting	88
A bijective inference network for interpretable identification of RNA N	86
Temporal sparse adversarial attack on sequence-based gait recognition	85
Bounded exponential loss function based AdaBoost ensemble of OCSVMs	85
SpatioTemporal focus for skeleton-based action recognition	85
MTS2Graph: Interpretable multivariate time series classification with temporal evolving graphs	85