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 2021-12-01 to 2025-12-01.)

Article	Citations
A visual question answering model based on image captioning	127
Unsupervised deep metric learning algorithm for crop disease images based on knowledge distillation networks	92
Pseudo-global strategy-based visual comfort assessment considering attention mechanism	88
SS-CMT: a label independent cross-modal transferable adversarial video attack with sparse strategy	83
A research for sound event localization and detection based on local–global adaptive fusion and temporal importance network	76
Real emotion seeker: recalibrating annotation for facial expression recognition	71
A comparative study of color quantization methods using various image quality assessment indices	70
BENet: bi-directional enhanced network for image captioning	67
Correction: STASiamRPN: visual tracking based on spatiotemporal and attention	58
Towards domain adaptation underwater image enhancement and restoration	49
Dual-branch spectral–spatial feature extraction network for multispectral image compression	47
Face and voice cross-modal association with learning convex feature embedding	43
ConASD: Contrastive Few Shot Learning for Detecting Autism Spectrum Disorder via Eye Tracking Scanpath	42
Feature fusion and optimization integrated refined deep residual network for diabetic retinopathy severity classification using fundus image	41
LMFE-RDD: a road damage detector with a lightweight multi-feature extraction network	41
360° video quality assessment based on saliency-guided viewport extraction	40
SFRA: spatial fusion regression augmentation network for facial landmark detection	39
SEMNet: a simple and efficient MLP-based network for 3D Face point clouds landmarks localization	38
Model-based portrait video compression with spatial constraint and adaptive pose processing	35
Improving text-image cross-modal retrieval with contrastive loss	34
CAPNet: tomato leaf disease detection network based on adaptive feature fusion and convolutional enhancement	30
Segmentation-aware image super-resolution with generative adversarial networks	30
Dual convolutional neural network with attention for image blind denoising	29
SS-YOLOv8: small-size object detection algorithm based on improved YOLOv8 for UAV imagery	29
SFFN-YOLO for small object detection in aerial images	28

CHCoT-MSLU: a coupled hierarchical chain-of-thought prompt learning model for multi-intent spoken language understanding	28
DiffRA: universal restorative adversarial attack based on diffusion model	27