OOIR: Observatory of International Research

Papers

(The H4-Index of Pattern Recognition is 78. 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 2021-04-01 to 2025-04-01.)

Article	Citations
Semi-supervised extensions of multi-task tree ensembles	406
Superpixel-based multi-scale multi-instance learning for hyperspectral image classification	313
Information-diffused graph tracking with linear complexity	300
Discriminative atoms embedding relation dual network for classification of choroidal neovascularization in OCT images	253
Self-Training-Transductive-Learning Broad Learning System (STTL-BLS): A model for effective and efficient image classification	236
Back-to-Bones: Rediscovering the role of backbones in domain generalization	218
CORE: Learning consistent ordinal representations with convex optimization for image ordinal estimation	207
Heterophily-aware graph attention network	201
From anomaly detection to open set recognition: Bridging the gap	194
EEG-ConvTransformer for single-trial EEG-based visual stimulus classification	191
Deep image prior based defense against adversarial examples	182
ScribbleNet: Efficient interactive annotation of urban city scenes for semantic segmentation	180
Intensity mixture and band-adaptive detail fusion for pansharpening	178
3D hand pose estimation from a single RGB image by weighting the occlusion and classification	177
Cross-modal co-feedback cellular automata for RGB-T saliency detection	166
Weakly-supervised semantic segmentation with saliency and incremental supervision updating	164
Learning Foreground Information Bottleneck for few-shot semantic segmentation	163
Graph Convolutional Network with elastic topology	160
Independent vector analysis: Model, applications, challenges	159
Deep tree-ensembles for multi-output prediction	155
Low-complexity arrays of contour signatures for exact shape retrieval	151
Learning efficient, explainable and discriminative representations for pulmonary nodules classification	149
Complex common spatial patterns on time-frequency decomposed EEG for brain-computer interface	137
ReViT: Enhancing vision transformers feature diversity with attention residual connections	136
Hyper-sausage coverage function neuron model and learning algorithm for image classification	131

Self-Supervised Leaf Segmentation under Complex Lighting Conditions	131
Overcoming weaknesses of density peak clustering using a data-dependent similarity measure	130
Supervised penalty-based aggregation applied to motor-imagery based brain-computer-interface	128
A novel interval dual convolutional neural network method for interval-valued stock price prediction	128
Mix-ViT: Mixing attentive vision transformer for ultra-fine-grained visual categorization	127
PLFace: Progressive Learning for Face Recognition with Mask Bias	124
Deep and wide nonnegative matrix factorization with embedded regularization	122
Robust deep fuzzy K-means clustering for image data	119
Conditional information gain networks as sparse mixture of experts	118
Discrete embedding for attributed graphs	116
Hypergraph matching via game-theoretic hypergraph clustering	111
Characters as graphs: Interpretable handwritten Chinese character recognition via Pyramid Graph Transformer	111
Beyond OCR + VQA: Towards end-to-end reading and reasoning for robust and accurate textvqa	111
Cross-Modal Transformer for RGB-D semantic segmentation of production workshop objects	111
Biological eagle eye-based method for change detection in water scenes	110
Detection confidence driven multi-object tracking to recover reliable tracks from unreliable detections	107
Factorized multi-Graph matching	107
CS-net: Conv-simpleformer network for agricultural image segmentation	104
Reconstruction of fragmented trajectories of collective motion using Hadamard deep autoencoders	104
DGFormer: Dynamic graph transformer for 3D human pose estimation	104
Finding compact and well-separated clusters: Clustering using silhouette coefficients	104
GripNet: Graph information propagation on supergraph for heterogeneous graphs	102
Scale-selective and noise-robust extended local binary pattern for texture classification	102
MUNet: Motion uncertainty-aware semi-supervised video object segmentation	101
A uniform transformer-based structure for feature fusion and enhancement for RGB-D saliency detection	100
Online and offline streaming feature selection methods with bat algorithm for redundancy analysis	99
Environmental Sound Classiﬁcation on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices	98
Query efficient black-box adversarial attack on deep neural networks	98
RPI-CapsuleGAN: Predicting RNA-protein interactions through an interpretable generative adversarial capsule network	95
Fairness in face presentation attack detection	94
Self-distillation and self-supervision for partial label learning	93
A survey on deep learning-based image forgery detection	93
Two phase cooperative learning for supervised dimensionality reduction	91
A non-regularization self-supervised Retinex approach to low-light image enhancement with parameterized illumination estimation	91
A restarted large-scale spectral clustering with self-guiding and block diagonal representation	90
Advancements in point cloud data augmentation for deep learning: A survey	87
Unsupervised person re-identification with multi-label learning guided self-paced clustering	87
Dynamic feature fusion with spatial-temporal context for robust object tracking	86
Improving deep learning on point cloud by maximizing mutual information across layers	85
Heterogeneous network representation learning based on role feature extraction	85
Adaptive spatial-temporal surrounding-aware correlation filter tracking via ensemble learning	85
3D hand pose and shape estimation from RGB images for keypoint-based hand gesture recognition	84
Covered Style Mining via Generative Adversarial Networks for Face Anti-spoofing	84
3D human pose estimation with single image and inertial measurement unit (IMU) sequence	84
Feature-semantic augmentation network for few-shot open-set recognition	83
Phase Randomization: A data augmentation for domain adaptation in human action recognition	82
Attentional prototype inference for few-shot segmentation	82
Refining a k-nearest neighbor graph for a computationally efficient spectral clustering	81
Multi-View correlation distillation for incremental object detection	81
Detecting pulmonary diseases using deep features in X-ray images	80

DIODE: Dilatable Incremental Object Detection	80
Attention‐guided evolutionary attack with elastic‐net regularization on face recognition	80
Graph-based stock correlation and prediction for high-frequency trading systems	80
Graph regularization multidimensional projection	78
An encoded histogram of ridge bifurcations and contours for fingerprint presentation attack detection	78
FoCL: Feature-oriented continual learning for generative models	78
Security and privacy enhanced smartphone-based gait authentication with random representation learning and digital lockers	78
Support subsets estimation for support vector machines retraining	78
A consistent and flexible framework for deep matrix factorizations	78