OOIR: Observatory of International Research

Papers

(The H4-Index of Multimedia Systems is 27. 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 2021-02-01 to 2025-02-01.)

Article	Citations
Pose-guided feature region-based fusion network for occluded person re-identification	126
Inception-like Large Kernel network for lightweight image super-resolution	94
Segmentation-aware image super-resolution with generative adversarial networks	84
ITrans: generative image inpainting with transformers	73
Development of outdoor swimmers detection system with small object detection method based on deep learning	68
BCMask: a finer leaf instance segmentation with bilayer convolution mask	65
Robust 3D face modeling and tracking from RGB-D images	65
The segmented UEC Food-100 dataset with benchmark experiment on food detection	57
Dental radiology: a convolutional neural network-based approach to detect dental disorders from dental images in a real-time environment	56
An improved contrast enhancement for dark images with non-uniform illumination based on edge preservation	56
Layer-wise enhanced transformer with multi-modal fusion for image caption	56
A gated multi-hierarchical feature fusion network for recognizing steel plate surface defects	55
An overview of deep learning techniques for COVID-19 detection: methods, challenges, and future works	51
Lite general network and MagFace CNN for micro-expression spotting in long videos	48
VMSG: a video caption network based on multimodal semantic grouping and semantic attention	42
Hierarchical cross-modal contextual attention network for visual grounding	40
Improving the application performance of Loki via algorithm optimization	37
Real-walk modelling: deep learning model for user mobility in virtual reality	36
Recent advancements of deep learning in detecting breast cancer: a survey	33
Improving text-image cross-modal retrieval with contrastive loss	32
Objective image fusion evaluation method for target recognition based on target quality factor	30
Implicit neural representation steganography by neuron pruning	28
MSADRCN: meta-learning based joint super-resolution fusion of infrared and visible images	28
LLR-MVSNet: a lightweight network for low-texture scene reconstruction	28
RCENet: an efficient pose estimation network based on regression correction	28

Unsupervised deep metric learning algorithm for crop disease images based on knowledge distillation networks	27
Adaptive B-spline curve fitting with minimal control points using an improved sparrow search algorithm for geometric modeling of aero-engine blades	27