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 2022-08-01 to 2026-08-01.)

Article	Citations
Function-based labels for complementary recommendation: Definition, annotation, and LLM-as-a-Judge	236
Robust clustering algorithm: The use of soft trimming approach	173
EasyFuse: Easy-to-learn visible and infrared image fusion framework based on unpaired set	85
Single-/Multi-Source Domain Adaptation via domain separation: A simple but effective method	78
Quantized DiT with hadamard transformation: A technical report	73
Adaptive recursive channel selection for robust decoding of motor imagery EEG signal in patients with intracerebral hemorrhage	70
Guiding multimodal LLMs for efficient visual place recognition	65
An analytic study on clustering driven self-supervised speaker verification	58
A micro Reinforcement Learning architecture for Intrusion Detection Systems	56
Multi-dataset fusion for multi-task learning on face attribute recognition	53
VWENet: Volumetric wavelet and mixture-of-experts network for 3D medical image segmentation	53
Cross-attention based dual-similarity network for few-shot learning	53
Fake News Detection using Hashtag Context	50
Detection of visual pursuits using 1D convolutional neural networks	47
Thermal crowd counting by distilling multi-modal knowledge	47
Dual quaternion ambisonics array for six-degree-of-freedom acoustic representation	43
Extending the kinematic theory of rapid movements with new primitives	43
FCL-ViT: Task-aware attention tuning for Continual Learning	42
Lightweight moment-residual-coherent patterns for image recognition	41
Innovative multi-modal approaches to Alzheimer’s disease detection: Transformer hybrid model and adaptive MLP-Mixer	41
Rethinking 3D cost aggregation in stereo matching	41
GenR: Generative latent inversion for blind face restoration	41
Achieving high performance on sketch-based image retrieval without real sketches for training	40
AMGB: Trajectory prediction using attention-based mechanism GCN-BiLSTM in IOV	40
OSS-OCL: Occlusion Scenario Simulation and Occluded-edge Concentrated Learning for pedestrian detection	39

Entropy calibrated prototype embedding for transductive few-shot learning	37
SYNAuG: Exploiting synthetic data for data imbalance problems	37
Clustering criteria: What defines a good cluster?	36
Semantic-aware self-supervised depth estimation for stereo 3D detection	36
Underwater image color correction via global-local collaborative strategy	34
VMamba-Crowd: Bridging multi-scale features from Visual Mamba for weakly-supervised crowd counting	34
Distilling EEG representations via capsules for affective computing	34
CrossFormer: Cross-guided attention for multi-modal object detection	34
Conditional Stable Diffusion for Distortion Correction and Image Rectification	34
DLR: Adversarial examples detection and label recovery for deep neural networks	34
Entire-detail motion dual-branch network for micro-expression recognition	34
GFMRC: A machine reading comprehension model for named entity recognition	34
Editorial Board	34