OOIR: Observatory of International Research

Papers

(The H4-Index of Neurocomputing is 92. 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
Special Issue SOCO 2021: New trends in soft computing and its application in industrial and environmental problems	1750
Overcoming the Price of Anarchy by Steering with Recommendations	1327
Learning hierarchical image feature for efficient image rectification	1009
fRAKI: k-space deep learning with offline data-universal and online scan-specific priors	940
Editorial Board	664
Motion frequency exploration based force separator for surgical robots interacting with a beating heart	603
PaintDiffusion: Towards text-driven painting variation via collaborative diffusion guidance	417
Optimal deception attacks under energy harvesting constraints for cyber–physical systems	374
Spatiotemporal semantic structural representation learning for image sequence prediction	357
From continuous pre-training to alignment: A comprehensive toolkit for large language models in federated learning	341
Debate divides: Argument relation-based contrastive opinion summarization via multi-task learning for online discussions	319
Kernel clustering with automatic variable weighting for interval data	302
A stochastic optimization technique for hyperparameter tuning in reservoir computing	288
Balanced quantum neural architecture search	286
MDVL-Edit: Mask-assisted highly disentangled text-driven face image editing based on vision-language alignment	265
Neuroadaptive event-triggered tracking control for nonlinear systems with dynamic fault feedback and prescribed time convergence	257
Neural Network Adaptive Observer design for Nonlinear Systems with Partially and Completely Unknown Dynamics Subject to Variable Sampled and Delay Output Measurement	256
Model compression through distillation with cross-layer integrated guidance at word level	241
Acceleration of grokking in learning arithmetic operations via Kolmogorov–Arnold representation	238
Mining confident supervision by prototypes discovering and annotation selection for weakly supervised semantic segmentation	235
Network based on the synergy of knowledge and context for natural language inference	235
Ensemble strategy learning for imperfect information games	234
Editorial Board	221
Adaptive map matching based on dynamic word embeddings for indoor positioning	217
Focus on hierarchical features: Soft-weighted hierarchical features network	216

Estimator-based iterative deviation-free residual generator for fault detection under random access protocol	215
A new robust semi-supervised clustering method based on adaptive credibility estimation and locality preservation	206
A study of growth based morphological development in neural network controlled walkers	204
Adaptive modeling of systems with uncertain dynamics via continuous long-short term memories	202
Class-prior probability estimation using density ratio between unlabeled instances and positively labeled noisy instances	197
AEP: Aligning knowledge graphs via embedding propagation	197
Efficient hyperspectral image segmentation for biosecurity scanning using knowledge distillation from multi-head teacher	195
Cross-modal feature symbiosis for personalized meta-path generation in heterogeneous networks	185
Multi-type spectral spatial feature for hyperspectral image classification	171
A new feature selection method based on importance measures for crude oil return forecasting	166
Sensitivity-propagated dual-frequency graph neural network for multivariate time series forecasting	162
Random forest feature selection for partial label learning	160
Online Q-learning design augmented with fuzzy-adaptive parameter adjustment for wastewater treatment processes	158
RCEAE: A Role Correlation-enhanced Model for Event Argument Extraction	157
Dual-alignment cross-domain few-shot learning with lightweight domain-specific attention for hyperspectral image classification	155
Improved image denoising via self-supervised Weickert operator learning and plug-and-play learned Primal Dual	154
Strategies for time series forecasting with generalized regression neural networks	153
MM-instruct: Generated visual instructions for large multimodal model alignment	151
Intermittent sampled-data synchronization of delayed reaction–diffusion neural networks	148
Improving generalization capability of object detectors via efficient global attention	146
Bidirectional parallel multi-layer multi-scale hybrid network	146
Cluster consensus with first and higher-order antagonistic interaction dynamics	138
Corrigendum to “S2F: Border peeling clustering from cluster skeletons to final clusters”[Neurocomputing 654 (2025), 131324]	137
Cycle pixel difference network for crisp edge detection	137
Data privacy protection health status assessment for rotating machinery with dual-task feature fusion framework	135
Editorial Board	134
Enhancing visual tracking with multi-scale cross-correlation and progressive attention	130
Multi-scale BiTemporal fusion for dynamic facial expression recognition in the wild	128
Decoding pre-movement neural activity from thalamic LFPs for adaptive neurostimulation in tremor patients	126
Spatio-temporal tree attention network for forecasting traffic flow	126
A learnable population filter for dynamic multi-objective optimization	124
The unsupervised sequential bio-tomographic image registration method based on deep wavelet transform and manifold symmetry constraints	123
MNSeg: Mamba-based 3D neuron segmentation integrated with bidirectional attention mechanism and topological loss	121
CRG-HG: A contrastive-regularized generative framework for heterogeneous graph learning	118
Multi-model-based transferable and imperceptible 3D adversarial attack	117
A novel recurrent neural network with robust learning algorithm: Application to modeling of nonlinear complex systems	117
Visual attention-based siamese CNN with SoftmaxFocal loss for laser-induced damage change detection of optical elements	117
PriFLRC: A secure multi-party computation-based privacy-enhanced federated learning scheme resilient to collusion	116
Quantile pattern regression using twin extreme learning machines with smooth pinball loss	116
A fisher score-based multi-instance learning method assisted by mixture of factor analysis	113
Multi-modal data clustering using deep learning: A systematic review	112
SPNet: Semantic preserving network with semantic constraint and non-semantic calibration for color constancy	111
DARTS-AM: robustifying differentiable neural architecture selection with attribution magnitude	110
Learning-based sliding mode control of discrete markov jump systems with actuator faults via action-critic-disturbance neural network approach	110
A comprehensive survey of adversarial defense techniques in the visual domain	109
Retraction notice to “Distilled and filtered deep neural networks for real-time object detection in edge computing” [Neurocomputing 505 (2022) 225–237]	108
Privacy-preserving secure bipartite consensus of stochastic nonlinear multi-agent systems via double dynamic event-triggered control under DoS attacks and markovian switching networks	108
Unveiling distinguishing properties of adversarial examples through neural tangent kernels	108
Optical convolutional neural network with the hybrid training method	107
Continual few-shot relation extraction via multi-task balanced dual-branch network	106

Adversarial training via multi-guidance and historical memory enhancement	104
	102
cpp-AIF: A multi-core C++ implementation of Active Inference for Partially Observable Markov Decision Processes	102
Learning to localize image forgery using end-to-end attention network	101
Blind face restoration: Benchmark datasets and a baseline model	100
The consistency analysis of gradient learning under independent covariate shift	99
Edge Feature Empowered Graph Attention Network for Sum Rate Maximization in Heterogeneous D2D Communication System	99
Adaptive lightweight network construction method for Self-Knowledge Distillation	98
Salient instance segmentation with region and box-level annotations	97
A substructure transfer reinforcement learning method based on metric learning	96
iCGPN: Interaction-centric graph parsing network for human-object interaction detection	95
UdpTrace: Utility-enhanced differential privacy scheme for trajectory data publishing	95
GradCa: Generalizing to unseen domains via gradient calibration	94
Enhancing randomized recurrent neural networks with explainable attribution methods	93
A more compact object detector head network with feature enhancement and relational reasoning	93
LightSpikformer: A compression framework for spiking transformer via low-rank decomposition of tensor networks	93
Multimodal understanding of human values in videos: A benchmark dataset and PLM-based method	93
Graph-constructed adaptive semantic fusion for heterophilic graph contrastive learning	92
BR Net: A novel deep learning model guided by brain region features for decoding single-trial visual EEG signals	92