OOIR: Observatory of International Research

Papers

(The H4-Index of Applied Intelligence is 47. 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
More effective and efficient exploration via more refined gradient information	275
Exploiting semantic-level affinities with a mask-guided network for temporal action proposal in videos	226
Transformer networks with adaptive inference for scene graph generation	196
Unsupervised 2D dimensionality reduction by jointly learning structural and temporal correlation	171
Revision of prioritized $$\mathcal {E}\mathcal {L}$$ ontologies	150
High-density pedestrian detection algorithm based on deep information fusion	145
Aggregating knowledge-aware graph neural network and adaptive relational attention for recommendation	136
A novel cognitive diagnosis system with attention residual mechanism and broad learning	133
HLC: hierarchically-aware label correlation for hierarchical text classification	130
Spatio-temporal attention-based hybrid deep network for time series prediction of industrial process	123
INNES: An intelligent network penetration testing model based on deep reinforcement learning	121
Data augmented large language models for medical record generation	117
Deep Learning Architecture for Computer Vision-based Structural Defect Detection	109
Symmetric perception and ordinal regression for detecting scoliosis natural image	108
Retraction Note: A survey of group decision making methods in Healthcare Industry 4.0: bibliometrics, applications, and directions	99
Semantic-consistent learning for one-shot joint entity and relation extraction	96
Membership score machine for highly nonlinear classification for small data	94
Recursive least squares method for training and pruning convolutional neural networks	89
SenAttack: adversarial attack method based on perturbation sensitivity and perceptual color distance	82
An evolutionary framework for automatic security guards deployment in large public spaces	82
Diffeomorphic matching with multiscale kernels based on sparse parameterization for cross-view target detection	80
Stochastic-simulation-based multi-attribute group decision-making method under uncertain environment and the application	80
Detecting log anomaly using subword attention encoder and probabilistic feature selection	72
Broadcast news story segmentation using sticky hierarchical dirichlet process	69
A parametric segmented multifactorial evolutionary algorithm based on a three-phase analysis	69

Evolutionary many-objective satisfiability solver for configuring software product lines	68
Joint model- and immunohistochemistry-driven few-shot learning scheme for breast cancer segmentation on 4D DCE-MRI	65
MsDA: Multi-scale domain adaptation dehazing network	64
MFU-Net: a deep multimodal fusion network for breast cancer segmentation with dual-layer spectral detector CT	64
Question difficulty estimation via enhanced directional modality association transformer	62
NkEL: nearest k-labelsets ensemble for multi-label learning	62
Dictionary learning for unsupervised feature selection via dual sparse regression	61
An efficient pruning and fine-tuning method for deep spiking neural network	60
Solving the cooperative scheduling problem of muck transport under time-segment restriction in an entire region	59
Visual enhanced hierarchical network for sentence-based video thumbnail generation	58
Improving weakly supervised phrase grounding via visual representation contextualization with contrastive learning	58
Graph neural networks with selective attention and path reasoning for document-level relation extraction	57
Semantic-aware matrix factorization hashing with intra- and inter-modality fusion for image-text retrieval	56
LCLD: A lightweight vanishing point detector with contrast-learning-based intermediate supervision module	53
Integrated self-supervised label propagation for label imbalanced sets	51
FGO-Net: Feature and Gaussian Optimization Network for visual saliency prediction	50
MSDM: multi-space diffusion with dynamic loss weight	50
Behavior sessions and time-aware for multi-target sequential recommendation	49
Enhancing real-time and day-ahead load forecasting accuracy with deep learning and weighed ensemble approach	49
A large-scale multiobjective evolutionary algorithm with overlapping decomposition and adaptive reference point selection	49
A multi-class partial hinge loss for partial label learning	48
A semantic visual SLAM towards object selection and tracking optimization	47
An incremental rare association rule mining approach with a life cycle tree structure considering time-sensitive data	47
Automated classification of remote sensing satellite images using deep learning based vision transformer	47