OOIR: Observatory of International Research

Papers

(The H4-Index of Neural Networks is 62. 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 2021-11-01 to 2025-11-01.)

Article	Citations
Editorial Board	350
Efficient multi-view fusion and flexible adaptation to view missing in cardiovascular system signals	329
Corrigendum to “Noise-resistant predefined-time convergent ZNN models for dynamic least squares and multi-agent systems” [Neural Networks 187 (2025) 107412]	309
KEMoS: A knowledge-enhanced multi-modal summarizing framework for Chinese online meetings	223
Deep prior embedding method for Electrical Impedance Tomography	207
MsDUNE: A multi-scale masked temporal fusion framework for speaker-independent lipreading via Dirichlet uncertainty estimation	174
Aspect sentiment learning for Aspect-Level Sentiment Classification	170
EAAR: Efficient and Accurate Action Recognition model with enhanced spatio-temporal perception	153
Automated tactics planning for cyber attack and defense based on large language model agents	128
Nonlinear feature selection for support vector quantile regression	125
GeoScatt-GNN: A Geometric Scattering Transform-Based Graph Neural Network Model for Ames Mutagenicity Prediction	122
Distributed multi-timescale algorithm for nonconvex optimization problem: A control perspective	122
DPGCL: Dual pass filtering based graph contrastive learning	122
ShadowGAN-Former: Reweighting self-attention based on mask for shadow removal	121
Achieving small-batch accuracy with large-batch scalability via Hessian-aware learning rate adjustment	114
Spatial–temporal recurrent reinforcement learning for autonomous ships	112
Chaos and multi-layer attractors in asymmetric neural networks coupled with discrete fractional memristor	109
Boosting adversarial robustness via self-paced adversarial training	108
Universality of reservoir systems with recurrent neural networks	108
Early stopping by correlating online indicators in neural networks	104
Salience Interest Option: Temporal abstraction with salience interest functions	103
Learning dynamic graph representations through timespan view contrasts	99
Unified analysis on multistablity of fraction-order multidimensional-valued memristive neural networks	98
Prescribed performance adaptive neural event-triggered control for switched nonlinear cyber–physical systems under deception attacks	96
SNR: Symbolic network-based rectifiable learning framework for symbolic regression	93

Attention-based random forest and contamination model	92
MTKSVCR: A novel multi-task multi-class support vector machine with safe acceleration rule	90
GEPAF: A non-monotonic generalized activation function in neural network for improving prediction with diverse data distributions characteristics	90
Backdoor attacks on unsupervised graph representation learning	87
Facilitating interaction between partial differential equation-based dynamics and unknown dynamics for regional wind speed prediction	86
Enhancing space–time video super-resolution via spatial–temporal feature interaction	86
Bio-inspired affordance learning for 6-DoF robotic grasping: A transformer-based global feature encoding approach	84
INN/ENNS/JNNS - Membership Applic. Form	83
Learning shared template representation with augmented feature for multi-object pose estimation	83
Deep graph representation learning for influence maximization with accelerated inference	82
CURRENT EVENTS	82
Central loss guides coordinated Transformer for reliable anatomical landmark detection	81
Modeling multi-scale uncertainty with evidence integration for reliable polyp segmentation	79
Sign potential-driven multiplicative optimization for robust deep reinforcement learning	77
Fixed-time synchronization of proportional delay memristive complex-valued competitive neural networks	76
Graph anomaly detection based on hybrid node representation learning	75
RoMAT: Role-based multi-agent transformer for generalizable heterogeneous cooperation	75
Fixed/Preassigned-time synchronization of quaternion-valued neural networks via pure power-law control	74
Multi-loss, feature fusion and improved top-two-voting ensemble for facial expression recognition in the wild	74
Flexibly regularized mixture models and application to image segmentation	74
Dynamic planning in hierarchical active inference	74
NN/ENNS/JNNS - Membership Applic. Form	73
Performance estimation for the memristor-based computing-in-memory implementation of extremely factorized network for real-time and low-power semantic segmentation	73
Towards global neural network abstractions with locally-exact reconstruction	71
DMPP: Differentiable multi-pruner and predictor for neural network pruning	71
Editorial Board	70
Graph convolutional network with tree-guided anisotropic message passing	69
Neural operators for robust output regulation of hyperbolic PDEs	69
Editorial Board	68
A recurrent Hopfield network for estimating meso-scale effective connectivity in MEG	67
Event-triggered H∞	66
RASP: Regularization-based Amplitude Saliency Pruning	65
Reinforced mixture learning	65
Explainable hybrid word representations for sentiment analysis of financial news	65
Predictive accuracy of CNN for cortical oscillatory activity in an acute rat model of parkinsonism	63
Partial label learning: Taxonomy, analysis and outlook	63
Deep semi-supervised learning via dynamic anchor graph embedding in latent space	63
On the Kolmogorov neural networks	62