OOIR: Observatory of International Research

Papers

(The H4-Index of Pattern Recognition Letters is 37. 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 2022-01-01 to 2026-01-01.)

Article	Citations
OSS-OCL: Occlusion Scenario Simulation and Occluded-edge Concentrated Learning for pedestrian detection	180
Extending the kinematic theory of rapid movements with new primitives	154
Revisiting convexity-preserving signal recovery with the linearly involved GMC penalty	95
HashWalk: An efficient node classification method based on clique-compressed graph embedding	85
Multi-dataset fusion for multi-task learning on face attribute recognition	84
Option compatible reward inverse reinforcement learning	84
Entire-detail motion dual-branch network for micro-expression recognition	75
GFMRC: A machine reading comprehension model for named entity recognition	73
An analytic study on clustering driven self-supervised speaker verification	69
Rethinking 3D cost aggregation in stereo matching	68
Detection of visual pursuits using 1D convolutional neural networks	65
Robust clustering algorithm: The use of soft trimming approach	63
Achieving high performance on sketch-based image retrieval without real sketches for training	63
FCL-ViT: Task-aware attention tuning for Continual Learning	60
SYNAuG: Exploiting synthetic data for data imbalance problems	59
Semantic-aware self-supervised depth estimation for stereo 3D detection	56
Fake News Detection using Hashtag Context	56
EasyFuse: Easy-to-learn visible and infrared image fusion framework based on unpaired set	54
Dual quaternion ambisonics array for six-degree-of-freedom acoustic representation	52
Innovative multi-modal approaches to Alzheimer’s disease detection: Transformer hybrid model and adaptive MLP-Mixer	51
CORE: A knowledge graph entity type prediction method via complex space regression and embedding	49
Cross-attention based dual-similarity network for few-shot learning	49
CrossFormer: Cross-guided attention for multi-modal object detection	46
VMamba-Crowd: Bridging multi-scale features from Visual Mamba for weakly-supervised crowd counting	45
Single-/Multi-Source Domain Adaptation via domain separation: A simple but effective method	44

Pattern detection in the activation space for identifying synthesized content	44
Unsupervised thermal-to-visible domain adaptation method for pedestrian detection	44
AMGB: Trajectory prediction using attention-based mechanism GCN-BiLSTM in IOV	44
A micro Reinforcement Learning architecture for Intrusion Detection Systems	43
Spike-TBR: A noise resilient neuromorphic event representation	42
Conditional Stable Diffusion for Distortion Correction and Image Rectification	41
EEPNet: An efficient and effective convolutional neural network for palmprint recognition	38
Adaptive dynamic networks for object detection in aerial images	38
Self-supervised multi-echo point cloud denoising in snowfall	37
Text-to-image synthesis with self-supervised learning	37
Editorial Board	37
Salient object detection by aggregating contextual information	37