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 2021-08-01 to 2025-08-01.)

Article	Citations
Robust domain-adaptive discriminant analysis	145
Revisiting convexity-preserving signal recovery with the linearly involved GMC penalty	138
HashWalk: An efficient node classification method based on clique-compressed graph embedding	136
Semantic-aware self-supervised depth estimation for stereo 3D detection	113
EasyFuse: Easy-to-learn visible and infrared image fusion framework based on unpaired set	95
Multi-dataset fusion for multi-task learning on face attribute recognition	88
A micro Reinforcement Learning architecture for Intrusion Detection Systems	82
Performing Attack Halting Process with Digital Pattern and Proactive Model Resolving the Security Issues in IoT Based Models	79
Innovative multi-modal approaches to Alzheimer’s disease detection: Transformer hybrid model and adaptive MLP-Mixer	73
GFMRC: A machine reading comprehension model for named entity recognition	73
Rethinking 3D cost aggregation in stereo matching	73
Extending the kinematic theory of rapid movements with new primitives	70
Detection of visual pursuits using 1D convolutional neural networks	69
Cross-attention based dual-similarity network for few-shot learning	69
SYNAuG: Exploiting synthetic data for data imbalance problems	67
Fake News Detection using Hashtag Context	64
Achieving high performance on sketch-based image retrieval without real sketches for training	63
Dual quaternion ambisonics array for six-degree-of-freedom acoustic representation	61
Option compatible reward inverse reinforcement learning	59
CrossFormer: Cross-guided attention for multi-modal object detection	56
Predicting soluble solids content in “Fuji” apples of different ripening stages based on multiple information fusion	55
AMGB: Trajectory prediction using attention-based mechanism GCN-BiLSTM in IOV	55
An analytic study on clustering driven self-supervised speaker verification	53
CORE: A knowledge graph entity type prediction method via complex space regression and embedding	53
OSS-OCL: Occlusion Scenario Simulation and Occluded-edge Concentrated Learning for pedestrian detection	50

Entire-detail motion dual-branch network for micro-expression recognition	50
Unsupervised thermal-to-visible domain adaptation method for pedestrian detection	49
Multimodal grid features and cell pointers for scene text visual question answering	48
Single-/Multi-Source Domain Adaptation via domain separation: A simple but effective method	47
Robust clustering algorithm: The use of soft trimming approach	47
Pattern detection in the activation space for identifying synthesized content	47
Effective semi-supervised learning for structured data using Embedding GANs	45
Unconstrained end-to-end text reading with feature rectification	44
A Hybrid Tucker-VQ Tensor Sketch decomposition model for coding and streaming real world light fields using stack of differently focused images	43
Similarity activation map for co-salient object detection	41
Iterative ridge regression using the aggregating algorithm	41
Dual-stream correlation exploration for face anti-Spoofing	41
Inter-separability and intra-concentration to enhance stochastic neural network adversarial robustness	40
Enhancing visual adversarial transferability via affine transformation of intermediate-level perturbations	40
Weighted distances on the truncated hexagonal grid	40