OOIR: Observatory of International Research

Papers

(The H4-Index of Pattern Recognition is 82. 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 2022-06-01 to 2026-06-01.)

Article	Citations
Progressive downsampling and adaptive guidance networks for dynamic scene deblurring	554
Editorial Board	498
FastOPM—A practical method for partial match of time series	406
Mutual Domain Adaptation	380
Deep graph matching meets mixed-integer linear programming: Relax or not ?	371
Multi-task meta label correction for time series prediction	364
One-pass online learning under evolving feature data streams: A non-parametric model	351
Dynamic feature fusion with spatial-temporal context for robust object tracking	350
Neural Normalized Cut: A differential and generalizable approach for spectral clustering	302
Scaled robust linear embedding with adaptive neighbors preserving	299
Robust deep fuzzy K-means clustering for image data	254
Generalization capacity of multi-class SVM based on Markovian resampling	246
Support subsets estimation for support vector machines retraining	232
Looking beyond input frames: Self-supervised adaptation for video super-resolution	221
Identifying the key frames: An attention-aware sampling method for action recognition	219
Robust multilayer bootstrap networks in ensemble for unsupervised representation learning and clustering	188
The MERIT dataset: Modelling and efficiently rendering interpretable transcripts	187
Pathological graph self-supervised learning for clear-cell renal cell carcinoma survival prediction	180
Synthetic unknown class learning for learning unknowns	175
Mix-ViT: Mixing attentive vision transformer for ultra-fine-grained visual categorization	174
Bi-Attention enhanced representation learning for image-text matching	172
Adapt only once: Fast unsupervised person re-identification via relevance-aware guidance	170
DC-AD: A Divide-and-Conquer Method for Few-Shot Anomaly Detection	169
DCFusion: Difference correlation-driven fusion mechanism of infrared and visible images	169
Sequence patterns and HMM profiles to predict proteome wide zinc finger motifs	161

Implicit face model: Depth super-resolution for 3D face recognition	161
Unsupervised learning non-uniform face enhancement under physics-guided model of illumination decoupling	158
Spectral approximation of Gaussian random graph Laplacians and applications to pattern recognition	154
Cross-modal co-feedback cellular automata for RGB-T saliency detection	143
End-to-end susceptibility-induced distortion correction for diffusion MRI with unsupervised deep learning	141
MSG-CLIP: Enhancing CLIP’s ability to learn fine-grained structural associations through multi-modal scene graph alignment	131
Text-guided weakly supervised framework for dynamic facial expression recognition	131
Enhanced visual prompt meets low-light saliency detection	130
Density peaks clustering algorithm integrating manifold distance and mutual nearest neighbors	129
GraphProbe: Knowledge Probing for Graph Representation Learning	128
Two phase cooperative learning for supervised dimensionality reduction	125
Spectral compression transformer with line pose graph for monocular 3D human pose estimation	123
Phase Randomization: A data augmentation for domain adaptation in human action recognition	122
Consistency-driven feature scoring and regularization network for visible–infrared person re-identification	120
A modified interval type-2 Takagi-Sugeno fuzzy neural network and its convergence analysis	120
Extrinsic kernel ridge regression classifier for Kendall’s planar shape space	118
LDM-Morph: Latent diffusion model guided deformable image registration	117
Cross-Modality Interactive Attention Network for AI-generated image quality assessment	117
Pseudo-labeling with keyword refining for few-supervised video captioning	112
Leveraging tensor kernels to reduce objective function mismatch in deep clustering	112
Kinship verification using multi-level dictionary pair learning for multiple resolution images	112
Striving for understanding: Deconstructing neural networks in side-channel analysis	111
Thermal to Visual Person Re-Identification Using Collaborative Metric Learning Based on Maximum Margin Matrix Factorization	108
STAR-Net: an interpretable model-aided network for remote sensing image denoising	108
Improving lesion segmentation in medical images by global and regional feature compensation	108
Improving the Facial Expression Recognition and Its Interpretability via Generating Expression Pattern-map	106
Adaptive integration of textual context and visual embeddings for underrepresented vision classification	105
A cross-network node classification method in open-set scenario	104
Hypergraph-driven landmark detection foundation model on echocardiography for cardiac function quantification	104
Intensity mixture and band-adaptive detail fusion for pansharpening	103
MTS2Graph: Interpretable multivariate time series classification with temporal evolving graphs	101
W-EICMFusion: A fusion network for infrared and visible images utilising WOA hyperparameter optimisation	100
Occlusion-guided multi-modal fusion for vehicle-infrastructure cooperative 3D object detection	100
Beyond mask: Rethinking guidance types in few-shot segmentation	99
Kernel-aware dynamic convolution for dense prediction	99
Domain aware post training quantization for vision transformers in deployment	99
RESKM: A General Framework to Accelerate Large-Scale Spectral Clustering	97
Robust Table Detection and Structure Recognition from Heterogeneous Document Images	97
PSCFormer: A lightweight hybrid network for gas identification in electronic nose system	96
Deep and wide nonnegative matrix factorization with embedded regularization	95
A bijective inference network for interpretable identification of RNA N	93
A neighborhood-based method for mining and fusing positive and negative false samples	93
Distribution alignment for cross-device palmprint recognition	93
eX-ViT: A Novel explainable vision transformer for weakly supervised semantic segmentation	92
ANNE: Adaptive Nearest Neighbours and Eigenvector-based sample selection for robust learning with noisy labels	91
Trunk-branch contrastive network with multi-view deformable aggregation for multi-view action recognition	90
DynamicKD: An effective knowledge distillation via dynamic entropy correction-based distillation for gap optimizing	89
Frequency-domain multi-scale graph learning with information-theoretic constraint for spatio-temporal prediction	89
Spectral Contrastive Clustering	88
GriT-DBSCAN: A spatial clustering algorithm for very large databases	87

Unsupervised person re-identification via multi-domain joint learning	87
DM-GAN: CNN hybrid vits for training GANs under limited data	85
Privileged multi-task learning for attribute-aware aesthetic assessment	85
Adaptive proximal regularization for image smoothing	85
Unsupervised update summarization of news events	85
Inter-Attribute awareness for pedestrian attribute recognition	84
A Sampling-Based Density Peaks Clustering Algorithm for Large-Scale Data	82