OOIR: Observatory of International Research

Papers

(The H4-Index of Pattern Recognition Letters is 34. 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
OSS-OCL: Occlusion Scenario Simulation and Occluded-edge Concentrated Learning for pedestrian detection	221
Function-based labels for complementary recommendation: Definition, annotation, and LLM-as-a-Judge	169
Robust clustering algorithm: The use of soft trimming approach	118
Semantic-aware self-supervised depth estimation for stereo 3D detection	93
GFMRC: A machine reading comprehension model for named entity recognition	82
EasyFuse: Easy-to-learn visible and infrared image fusion framework based on unpaired set	79
Single-/Multi-Source Domain Adaptation via domain separation: A simple but effective method	74
Underwater image color correction via global-local collaborative strategy	64
Quantized DiT with hadamard transformation: A technical report	61
Adaptive recursive channel selection for robust decoding of motor imagery EEG signal in patients with intracerebral hemorrhage	61
Guiding multimodal LLMs for efficient visual place recognition	56
Multi-dataset fusion for multi-task learning on face attribute recognition	54
Clustering criteria: What defines a good cluster?	52
Cross-attention based dual-similarity network for few-shot learning	51
Fake News Detection using Hashtag Context	51
Detection of visual pursuits using 1D convolutional neural networks	49
Entropy calibrated prototype embedding for transductive few-shot learning	48
Thermal crowd counting by distilling multi-modal knowledge	47
Dual quaternion ambisonics array for six-degree-of-freedom acoustic representation	45
Extending the kinematic theory of rapid movements with new primitives	45
SYNAuG: Exploiting synthetic data for data imbalance problems	43
Achieving high performance on sketch-based image retrieval without real sketches for training	42
Entire-detail motion dual-branch network for micro-expression recognition	41
Lightweight moment-residual-coherent patterns for image recognition	40
FCL-ViT: Task-aware attention tuning for Continual Learning	40

An analytic study on clustering driven self-supervised speaker verification	39
Innovative multi-modal approaches to Alzheimer’s disease detection: Transformer hybrid model and adaptive MLP-Mixer	39
A micro Reinforcement Learning architecture for Intrusion Detection Systems	39
AMGB: Trajectory prediction using attention-based mechanism GCN-BiLSTM in IOV	37
VWENet: Volumetric wavelet and mixture-of-experts network for 3D medical image segmentation	37
VMamba-Crowd: Bridging multi-scale features from Visual Mamba for weakly-supervised crowd counting	36
Rethinking 3D cost aggregation in stereo matching	35
Conditional Stable Diffusion for Distortion Correction and Image Rectification	34
DLR: Adversarial examples detection and label recovery for deep neural networks	34
CrossFormer: Cross-guided attention for multi-modal object detection	34