OOIR: Observatory of International Research

Papers

(The H4-Index of Pattern Recognition Letters is 40. 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 2021-10-01 to 2025-10-01.)

Article	Citations
Robust clustering algorithm: The use of soft trimming approach	161
A micro Reinforcement Learning architecture for Intrusion Detection Systems	147
Performing Attack Halting Process with Digital Pattern and Proactive Model Resolving the Security Issues in IoT Based Models	144
HashWalk: An efficient node classification method based on clique-compressed graph embedding	103
An analytic study on clustering driven self-supervised speaker verification	88
Pattern detection in the activation space for identifying synthesized content	82
Multi-dataset fusion for multi-task learning on face attribute recognition	75
Dual quaternion ambisonics array for six-degree-of-freedom acoustic representation	75
AMGB: Trajectory prediction using attention-based mechanism GCN-BiLSTM in IOV	72
Semantic-aware self-supervised depth estimation for stereo 3D detection	72
CrossFormer: Cross-guided attention for multi-modal object detection	71
EasyFuse: Easy-to-learn visible and infrared image fusion framework based on unpaired set	68
Option compatible reward inverse reinforcement learning	67
Rethinking 3D cost aggregation in stereo matching	65
Predicting soluble solids content in “Fuji” apples of different ripening stages based on multiple information fusion	63
Unsupervised thermal-to-visible domain adaptation method for pedestrian detection	61
GFMRC: A machine reading comprehension model for named entity recognition	60
Extending the kinematic theory of rapid movements with new primitives	58
CORE: A knowledge graph entity type prediction method via complex space regression and embedding	57
Revisiting convexity-preserving signal recovery with the linearly involved GMC penalty	54
Single-/Multi-Source Domain Adaptation via domain separation: A simple but effective method	54
Detection of visual pursuits using 1D convolutional neural networks	53
Entire-detail motion dual-branch network for micro-expression recognition	50
OSS-OCL: Occlusion Scenario Simulation and Occluded-edge Concentrated Learning for pedestrian detection	50
Innovative multi-modal approaches to Alzheimer’s disease detection: Transformer hybrid model and adaptive MLP-Mixer	50

Fake News Detection using Hashtag Context	49
Cross-attention based dual-similarity network for few-shot learning	49
Achieving high performance on sketch-based image retrieval without real sketches for training	48
SYNAuG: Exploiting synthetic data for data imbalance problems	47
Multimodal grid features and cell pointers for scene text visual question answering	46
Enhancing visual adversarial transferability via affine transformation of intermediate-level perturbations	46
Conditional Stable Diffusion for Distortion Correction and Image Rectification	44
Fusion Regression	44
Manifold information through neighbor embedding projection for image retrieval	43
Editorial Board	42
GAF-Net: A new automated segmentation method based on multiscale feature fusion and feedback module	42
Quantitative performance evaluation of object detectors in hazy environments	41
FoodMem: Near real-time and precise food video segmentation	41
DLR: Adversarial examples detection and label recovery for deep neural networks	41
Spike-TBR: A noise resilient neuromorphic event representation	40
Inter-separability and intra-concentration to enhance stochastic neural network adversarial robustness	40
Self-supervised multi-echo point cloud denoising in snowfall	40