OOIR: Observatory of International Research

Papers

(The H4-Index of Neural Networks is 61. 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
Editorial Board	298
Multi-loss, feature fusion and improved top-two-voting ensemble for facial expression recognition in the wild	283
Efficient multi-view fusion and flexible adaptation to view missing in cardiovascular system signals	281
Towards global neural network abstractions with locally-exact reconstruction	276
Graph convolutional network with tree-guided anisotropic message passing	189
Predictive accuracy of CNN for cortical oscillatory activity in an acute rat model of parkinsonism	173
Reinforced mixture learning	163
Editorial Board	147
NN/ENNS/JNNS - Membership Applic. Form	128
RoMAT: Role-based multi-agent transformer for generalizable heterogeneous cooperation	114
Adams-based hierarchical features fusion network for image dehazing	109
Editorial Board	107
Central loss guides coordinated Transformer for reliable anatomical landmark detection	106
MTKSVCR: A novel multi-task multi-class support vector machine with safe acceleration rule	106
Event-triggered H∞	105
A recurrent Hopfield network for estimating meso-scale effective connectivity in MEG	103
Learning to reweight examples in multi-label classification	101
Uncertainty-Aware Graph Contrastive Fusion Network for multimodal physiological signal emotion recognition	100
SNR: Symbolic network-based rectifiable learning framework for symbolic regression	100
Deep semi-supervised learning via dynamic anchor graph embedding in latent space	99
Nonlinear feature selection for support vector quantile regression	96
Automated Tactics Planning for Cyber Attack and Defense Based on Large Language Model Agents	95
Backdoor attacks on unsupervised graph representation learning	93
Attention-based random forest and contamination model	92
Spatial–temporal recurrent reinforcement learning for autonomous ships	89

Graph anomaly detection based on hybrid node representation learning	87
Dynamic planning in hierarchical active inference	85
Distributed multi-timescale algorithm for nonconvex optimization problem: A control perspective	83
A CNN model embedded with local feature knowledge and its application to time-varying signal classification	83
Boosting adversarial robustness via self-paced adversarial training	83
Achieving small-batch accuracy with large-batch scalability via Hessian-aware learning rate adjustment	81
CURRENT EVENTS	80
Bio-inspired affordance learning for 6-DoF robotic grasping: A transformer-based global feature encoding approach	80
Neural operators for robust output regulation of hyperbolic PDEs	80
Deep graph representation learning for influence maximization with accelerated inference	79
Performance estimation for the memristor-based computing-in-memory implementation of extremely factorized network for real-time and low-power semantic segmentation	78
Learning dynamic graph representations through timespan view contrasts	76
Salience Interest Option: Temporal abstraction with salience interest functions	76
DPGCL: Dual pass filtering based graph contrastive learning	74
DMPP: Differentiable multi-pruner and predictor for neural network pruning	73
Learning shared template representation with augmented feature for multi-object pose estimation	72
Fixed-time synchronization of proportional delay memristive complex-valued competitive neural networks	71
Sign potential-driven multiplicative optimization for robust deep reinforcement learning	71
Universality of reservoir systems with recurrent neural networks	70
Deep prior embedding method for Electrical Impedance Tomography	70
An efficient encoder–decoder model for portrait depth estimation from single images trained on pixel-accurate synthetic data	70
ShadowGAN-Former: Reweighting self-attention based on mask for shadow removal	69
RASP: Regularization-based Amplitude Saliency Pruning	68
Flexibly regularized mixture models and application to image segmentation	67
Enhancing space–time video super-resolution via spatial–temporal feature interaction	66
Unified analysis on multistablity of fraction-order multidimensional-valued memristive neural networks	65
GEPAF: A non-monotonic generalized activation function in neural network for improving prediction with diverse data distributions characteristics	65
Facilitating interaction between partial differential equation-based dynamics and unknown dynamics for regional wind speed prediction	64
Diversity-driven knowledge distillation for financial trading using Deep Reinforcement Learning	64
3D face-model reconstruction from a single image: A feature aggregation approach using hierarchical transformer with weak supervision	62
Explainable hybrid word representations for sentiment analysis of financial news	62
Partial label learning: Taxonomy, analysis and outlook	62
UTRAD: Anomaly detection and localization with U-Transformer	62
Fixed/Preassigned-time synchronization of quaternion-valued neural networks via pure power-law control	62
Early stopping by correlating online indicators in neural networks	61
KEMoS: A knowledge-enhanced multi-modal summarizing framework for Chinese online meetings	61