OOIR: Observatory of International Research

Papers

(The H4-Index of Machine Learning is 28. 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 2021-03-01 to 2025-03-01.)

Article	Citations
Lifted model checking for relational MDPs	799
SA-LfV: self-annotated labeling from videos for object detection	225
Learning multi-axis representation in frequency domain for medical image segmentation	171
PerfoRank: cluster-based performance ranking for improved performance evaluation and estimation in professional cycling	105
Credal ensembling in multi-class classification	96
Resolving power: a general approach to compare the distinguishing ability of threshold-free evaluation metrics	92
Misclassification bounds for PAC-Bayesian sparse deep learning	79
Dealing with the unevenness: deeper insights in graph-based attack and defense	77
Speeding up neural network robustness verification via algorithm configuration and an optimised mixed integer linear programming solver portfolio	67
Semi-supervised Latent Block Model with pairwise constraints	64
Moreau-Yoshida variational transport: a general framework for solving regularized distributional optimization problems	58
Correction to: Deep negative correlation classification	57
Assessing machine learning and data imputation approaches to handle the issue of data sparsity in sports forecasting	53
De-biased two-sample U-statistics with application to conditional distribution testing	48
Adapting performance metrics for ordinal classification to interval scale: length matters	45
Maximum causal entropy inverse constrained reinforcement learning	44
Explanatory machine learning for sequential human teaching	39
PAC-learning with approximate predictors	39
Bayesian optimization with approximate set kernels	38
Reachable sets of classifiers and regression models: (non-)robustness analysis and robust training	36
Are LSTMs good few-shot learners?	36
Multi-objective multi-armed bandit with lexicographically ordered and satisficing objectives	35
Multiclass optimal classification trees with SVM-splits	35
No regret sample selection with noisy labels	32
GS2P: a generative pre-trained learning to rank model with over-parameterization for web-scale search	32

Modelling spatiotemporal dynamics from Earth observation data with neural differential equations	30
Machine learning in corporate credit rating assessment using the expanded audit report	30
Recursive tree grammar autoencoders	28