OOIR: Observatory of International Research

Papers

(The H4-Index of Neural Networks is 57. 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 2021-06-01 to 2025-06-01.)

Article	Citations
Editorial Board	351
Multi-loss, feature fusion and improved top-two-voting ensemble for facial expression recognition in the wild	269
A recurrent Hopfield network for estimating meso-scale effective connectivity in MEG	267
Backdoor attacks on unsupervised graph representation learning	265
Efficient multi-view fusion and flexible adaptation to view missing in cardiovascular system signals	256
Towards global neural network abstractions with locally-exact reconstruction	171
Facilitating interaction between partial differential equation-based dynamics and unknown dynamics for regional wind speed prediction	158
Graph convolutional network with tree-guided anisotropic message passing	156
Unified analysis on multistablity of fraction-order multidimensional-valued memristive neural networks	149
Predictive accuracy of CNN for cortical oscillatory activity in an acute rat model of parkinsonism	140
Reinforced mixture learning	108
A fast saddle-point dynamical system approach to robust deep learning	107
Editorial Board	107
Editorial Board	102
NN/ENNS/JNNS - Membership Applic. Form	102
Distributed multi-timescale algorithm for nonconvex optimization problem: A control perspective	99
Enhancing space–time video super-resolution via spatial–temporal feature interaction	98
Deep semi-supervised learning via dynamic anchor graph embedding in latent space	93
RoMAT: Role-based multi-agent transformer for generalizable heterogeneous cooperation	92
Learning to reweight examples in multi-label classification	92
SNR: Symbolic network-based rectifiable learning framework for symbolic regression	90
A CNN model embedded with local feature knowledge and its application to time-varying signal classification	88
Achieving small-batch accuracy with large-batch scalability via Hessian-aware learning rate adjustment	88
Oblique and rotation double random forest	85
Nonlinear feature selection for support vector quantile regression	85

Bio-inspired affordance learning for 6-DoF robotic grasping: A transformer-based global feature encoding approach	83
CURRENT EVENTS	81
Neural operators for robust output regulation of hyperbolic PDEs	81
Partial label learning: Taxonomy, analysis and outlook	79
Deep graph representation learning for influence maximization with accelerated inference	77
GEPAF: A non-monotonic generalized activation function in neural network for improving prediction with diverse data distributions characteristics	77
Spatial–temporal recurrent reinforcement learning for autonomous ships	77
Performance estimation for the memristor-based computing-in-memory implementation of extremely factorized network for real-time and low-power semantic segmentation	75
Salience Interest Option: Temporal abstraction with salience interest functions	74
Learning dynamic graph representations through timespan view contrasts	73
DPGCL: Dual pass filtering based graph contrastive learning	72
KEMoS: A knowledge-enhanced multi-modal summarizing framework for Chinese online meetings	71
DMPP: Differentiable multi-pruner and predictor for neural network pruning	70
H∞	69
Learning shared template representation with augmented feature for multi-object pose estimation	69
Graph anomaly detection based on hybrid node representation learning	69
On the Kolmogorov neural networks	67
MTKSVCR: A novel multi-task multi-class support vector machine with safe acceleration rule	67
Chaos and multi-layer attractors in asymmetric neural networks coupled with discrete fractional memristor	66
Adams-based hierarchical features fusion network for image dehazing	66
UTRAD: Anomaly detection and localization with U-Transformer	66
Boosting adversarial robustness via self-paced adversarial training	65
Prescribed performance adaptive neural event-triggered control for switched nonlinear cyber–physical systems under deception attacks	63
An efficient encoder–decoder model for portrait depth estimation from single images trained on pixel-accurate synthetic data	63
Fixed/Preassigned-time synchronization of quaternion-valued neural networks via pure power-law control	62
ShadowGAN-Former: Reweighting self-attention based on mask for shadow removal	62
3D face-model reconstruction from a single image: A feature aggregation approach using hierarchical transformer with weak supervision	61
Early stopping by correlating online indicators in neural networks	61
Event-triggered H∞	61
RASP: Regularization-based Amplitude Saliency Pruning	60
Explainable hybrid word representations for sentiment analysis of financial news	59
Attention-based random forest and contamination model	58
Dynamic planning in hierarchical active inference	57
Flexibly regularized mixture models and application to image segmentation	57
A survey on modern trainable activation functions	57
Diversity-driven knowledge distillation for financial trading using Deep Reinforcement Learning	57
CURRENT EVENTS	57