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 2021-09-01 to 2025-09-01.)

Article	Citations
More effective and efficient exploration via more refined gradient information	288
Exploiting semantic-level affinities with a mask-guided network for temporal action proposal in videos	243
Transformer networks with adaptive inference for scene graph generation	204
Revision of prioritized $$\mathcal {E}\mathcal {L}$$ ontologies	163
High-density pedestrian detection algorithm based on deep information fusion	151
HLC: hierarchically-aware label correlation for hierarchical text classification	144
Aggregating knowledge-aware graph neural network and adaptive relational attention for recommendation	137
A novel cognitive diagnosis system with attention residual mechanism and broad learning	136
Spatio-temporal attention-based hybrid deep network for time series prediction of industrial process	127
INNES: An intelligent network penetration testing model based on deep reinforcement learning	121
Data augmented large language models for medical record generation	114
Resolution-sensitive self-supervised monocular absolute depth estimation	111
Deep Learning Architecture for Computer Vision-based Structural Defect Detection	99
FeMIP: detector-free feature matching for multimodal images with policy gradient	99
Group channel pruning and spatial attention distilling for object detection	95
Semantic-consistent learning for one-shot joint entity and relation extraction	87
Membership score machine for highly nonlinear classification for small data	87
Retraction Note: A survey of group decision making methods in Healthcare Industry 4.0: bibliometrics, applications, and directions	87
Recursive least squares method for training and pruning convolutional neural networks	82
An evolutionary framework for automatic security guards deployment in large public spaces	74
SenAttack: adversarial attack method based on perturbation sensitivity and perceptual color distance	74
Diffeomorphic matching with multiscale kernels based on sparse parameterization for cross-view target detection	70
Stochastic-simulation-based multi-attribute group decision-making method under uncertain environment and the application	69
Broadcast news story segmentation using sticky hierarchical dirichlet process	65
Detecting log anomaly using subword attention encoder and probabilistic feature selection	65

A parametric segmented multifactorial evolutionary algorithm based on a three-phase analysis	64
Evolutionary many-objective satisfiability solver for configuring software product lines	64
MsDA: Multi-scale domain adaptation dehazing network	63
Joint model- and immunohistochemistry-driven few-shot learning scheme for breast cancer segmentation on 4D DCE-MRI	63
NkEL: nearest k-labelsets ensemble for multi-label learning	62
Question difficulty estimation via enhanced directional modality association transformer	61
Dictionary learning for unsupervised feature selection via dual sparse regression	60
An efficient pruning and fine-tuning method for deep spiking neural network	59
Improving weakly supervised phrase grounding via visual representation contextualization with contrastive learning	57
Solving the cooperative scheduling problem of muck transport under time-segment restriction in an entire region	57
Visual enhanced hierarchical network for sentence-based video thumbnail generation	57
Graph neural networks with selective attention and path reasoning for document-level relation extraction	52
Semantic-aware matrix factorization hashing with intra- and inter-modality fusion for image-text retrieval	51
Integrated self-supervised label propagation for label imbalanced sets	51
LCLD: A lightweight vanishing point detector with contrast-learning-based intermediate supervision module	51
FGO-Net: Feature and Gaussian Optimization Network for visual saliency prediction	50
MSDM: multi-space diffusion with dynamic loss weight	50
A new deep learning-based approach for predicting the geothermal heat pump’s thermal power of a real bioclimatic house	49
Enhancing real-time and day-ahead load forecasting accuracy with deep learning and weighed ensemble approach	49
Imitation learning by state-only distribution matching	48
FAGCL: frequency-based augmentation graph contrastive learning for recommendation	48
Probabilistic linguistic hesitant fuzzy multi-attribute decision making for rural revitalization project selection of China	47
HRANet: Hierarchical region-aware network for crowd counting	47