OOIR: Observatory of International Research

Papers

(The H4-Index of Pattern Recognition is 64. The table below lists those papers that are above that threshold based on CrossRef citation counts [max. 500 papers]. The publications cover those that have been published in the past four years, i.e., from 2019-09-01 to 2023-09-01.)

Article	Citations
U2-Net: Going deeper with nested U-structure for salient object detection	600
Improving person re-identification by attribute and identity learning	370
Underwater scene prior inspired deep underwater image and video enhancement	339
How much can k-means be improved by using better initialization and repeats?	222
Binary neural networks: A survey	216
Unsupervised domain adaptive re-identification: Theory and practice	191
Sensor-based and vision-based human activity recognition: A comprehensive survey	186
A model-based gait recognition method with body pose and human prior knowledge	183
RGB-T object tracking: Benchmark and baseline	173
Understanding adversarial attacks on deep learning based medical image analysis systems	156
Manifold regularized discriminative feature selection for multi-label learning	148
Knowledge base graph embedding module design for Visual question answering model	140
A cross-domain collaborative filtering algorithm with expanding user and item features via the latent factor space of auxiliary domains	138
Dynamic graph convolutional networks	136
Deep-Person: Learning discriminative deep features for person Re-Identification	132
AlignedReID++: Dynamically matching local information for person re-identification	129
Hypergraph convolution and hypergraph attention	128
Cross-modality deep feature learning for brain tumor segmentation	126
Reconstruction by inpainting for visual anomaly detection	121
MetaCOVID: A Siamese neural network framework with contrastive loss for n-shot diagnosis of COVID-19 patients	114
Deep support vector machine for hyperspectral image classification	114
Automatic COVID-19 lung infected region segmentation and measurement using CT-scans images	111
Explainable deep learning for efficient and robust pattern recognition: A survey of recent developments	111
Auto-weighted multi-view clustering via deep matrix decomposition	109
Feature selection using bare-bones particle swarm optimization with mutual information	101

Hierarchical dense recursive network for image super-resolution	101
Automatically discriminating and localizing COVID-19 from community-acquired pneumonia on chest X-rays	98
LCU-Net: A novel low-cost U-Net for environmental microorganism image segmentation	97
Handling incomplete heterogeneous data using VAEs	93
A review of methods for imbalanced multi-label classification	91
Random vector functional link neural network based ensemble deep learning	91
Deep co-training for semi-supervised image segmentation	91
Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks	89
Learning visual relationship and context-aware attention for image captioning	84
A CenterNet++ model for ship detection in SAR images	83
Uncertainty estimation for stereo matching based on evidential deep learning	83
SegLink++: Detecting Dense and Arbitrary-shaped Scene Text by Instance-aware Component Grouping	82
Spatio-temporal deformable 3D ConvNets with attention for action recognition	81
Distinguishing two types of labels for multi-label feature selection	81
Momentum contrastive learning for few-shot COVID-19 diagnosis from chest CT images	80
Multistage attention network for image inpainting	80
Radial-Based Undersampling for imbalanced data classification	79
BLOCK-DBSCAN: Fast clustering for large scale data	79
A reduced universum twin support vector machine for class imbalance learning	78
Visual place recognition: A survey from deep learning perspective	78
Pruning by explaining: A novel criterion for deep neural network pruning	78
Edge computing enabled video segmentation for real-time traffic monitoring in internet of vehicles	78
Exploring uncertainty in pseudo-label guided unsupervised domain adaptation	77
A comprehensive study on gait biometrics using a joint CNN-based method	77
Structured graph learning for clustering and semi-supervised classification	76
Image denoising using complex-valued deep CNN	76
Point attention network for semantic segmentation of 3D point clouds	73
A review of lane detection methods based on deep learning	73
Multi-view subspace clustering via simultaneously learning the representation tensor and affinity matrix	72
GasHis-Transformer: A multi-scale visual transformer approach for gastric histopathological image detection	71
Deep neural networks-based relevant latent representation learning for hyperspectral image classification	71
Heterogeneous oblique random forest	70
Neighborhood linear discriminant analysis	70
AutoPruner: An end-to-end trainable filter pruning method for efficient deep model inference	70
TPM: Multiple object tracking with tracklet-plane matching	69
MDFN: Multi-scale deep feature learning network for object detection	68
CAGNet: Content-Aware Guidance for Salient Object Detection	68
Action Transformer: A self-attention model for short-time pose-based human action recognition	66
Synergistic learning of lung lobe segmentation and hierarchical multi-instance classification for automated severity assessment of COVID-19 in CT images	66
A comprehensive survey of multi-view video summarization	64