OOIR: Observatory of International Research

Papers

(The H4-Index of Neural Networks is 65. 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 2022-05-01 to 2026-05-01.)

Article	Citations
Editorial Board	448
Editorial Board	260
Editorial Board	259
Reinforced mixture learning	187
Aspect sentiment learning for Aspect-Level Sentiment Classification	180
EAAR: Efficient and Accurate Action Recognition model with enhanced spatio-temporal perception	170
Dynamic planning in hierarchical active inference	153
Variational autoencoder for distributional learning via quantile function estimation	140
Boosting adversarial robustness via self-paced adversarial training	140
Distributed multi-timescale algorithm for nonconvex optimization problem: A control perspective	138
Enhancing space–time video super-resolution via spatial–temporal feature interaction	130
Deep prior embedding method for Electrical Impedance Tomography	130
Recurrent stochastic configuration networks with block increments	130
Learning shared template representation with augmented feature for multi-object pose estimation	120
Backdoor samples detection based on perturbation discrepancy consistency in pre-trained language models	114
Corrigendum to “Noise-resistant predefined-time convergent ZNN models for dynamic least squares and multi-agent systems” [Neural Networks 187 (2025) 107412]	111
Efficient multi-view fusion and flexible adaptation to view missing in cardiovascular system signals	109
Partial label learning: Taxonomy, analysis and outlook	107
Unified analysis on multistablity of fraction-order multidimensional-valued memristive neural networks	106
Backdoor attacks on unsupervised graph representation learning	104
Early stopping by correlating online indicators in neural networks	104
Graph anomaly detection based on hybrid node representation learning	103
Uncertainty-Aware Graph Contrastive Fusion Network for multimodal physiological signal emotion recognition	103
Automated tactics planning for cyber attack and defense based on large language model agents	102
Neural operators for robust output regulation of hyperbolic PDEs	101

Closed-loop Correction Reprogramming for Fine-grained Visual Prompting	98
Differential Feature Guidance and Compressed Cost Volume for Large Disparity Stereo Network	96
SNR: Symbolic network-based rectifiable learning framework for symbolic regression	93
RoMAT: Role-based multi-agent transformer for generalizable heterogeneous cooperation	92
Chaos and multi-layer attractors in asymmetric neural networks coupled with discrete fractional memristor	92
Oblique and rotation double random forest	90
Fixed-time synchronization of proportional delay memristive complex-valued competitive neural networks	88
Explainable hybrid word representations for sentiment analysis of financial news	88
Dual-balancing for multi-task learning	87
Spatial–temporal recurrent reinforcement learning for autonomous ships	87
INN/ENNS/JNNS - Membership Applic. Form	85
Multi-loss, feature fusion and improved top-two-voting ensemble for facial expression recognition in the wild	83
3D face-model reconstruction from a single image: A feature aggregation approach using hierarchical transformer with weak supervision	82
CURRENT EVENTS	79
Reinforcement learning with formation energy feedback for material diffusion models	79
TRKM: Twin restricted kernel machines for classification and regression	79
DPGCL: Dual pass filtering based graph contrastive learning	78
MTKSVCR: A novel multi-task multi-class support vector machine with safe acceleration rule	78
Bio-inspired affordance learning for 6-DoF robotic grasping: A transformer-based global feature encoding approach	78
ShadowGAN-Former: Reweighting self-attention based on mask for shadow removal	78
Nonlinear feature selection for support vector quantile regression	75
Towards global neural network abstractions with locally-exact reconstruction	75
Sign potential-driven multiplicative optimization for robust deep reinforcement learning	75
Graph convolutional network with tree-guided anisotropic message passing	75
RASP: Regularization-based Amplitude Saliency Pruning	74
Metamon-GS: Enhancing representability with variance-guided densification and light encoding	73
Prescribed performance adaptive neural event-triggered control for switched nonlinear cyber–physical systems under deception attacks	72
A recurrent Hopfield network for estimating meso-scale effective connectivity in MEG	71
MsDUNE: A multi-scale masked temporal fusion framework for speaker-independent lipreading via Dirichlet uncertainty estimation	71
Learning dynamic graph representations through timespan view contrasts	71
Regression-based multisource conditional domain adaptation for policy outcome prediction	70
A DINO-based progressive semantic enhanced infrared and visible image fusion network	70
GeoScatt-GNN: A geometric scattering transform-based graph neural network model for Ames mutagenicity prediction	69
Adams-based hierarchical features fusion network for image dehazing	69
Graph-level contrastive learning with self-aware and cross-sample topology augmentation for brain disorder diagnosis using rs-fMRI	69
VLExpan: A visual-enhanced LLM framework with inductive and deductive policies for entity set expansion	68
Flexibly regularized mixture models and application to image segmentation	67
Facilitating interaction between partial differential equation-based dynamics and unknown dynamics for regional wind speed prediction	67
Salience Interest Option: Temporal abstraction with salience interest functions	65
Event-triggered H∞	65