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 2022-08-01 to 2026-08-01.)

Article	Citations
Pseudo-global strategy-based visual comfort assessment considering attention mechanism	133
SS-CMT: a label independent cross-modal transferable adversarial video attack with sparse strategy	98
Face and voice cross-modal association with learning convex feature embedding	70
DiffRA: universal restorative adversarial attack based on diffusion model	70
TreeSegNet: multi-scale query-based instance segmentation with frequency-aware and gated feature enhancement	57
Dual-branch spectral–spatial feature extraction network for multispectral image compression	56
A research for sound event localization and detection based on local–global adaptive fusion and temporal importance network	53
FedMAB: adaptive multimodal federated learning with multi-armed bandits	50
A visual question answering model based on image captioning	47
Unsupervised deep metric learning algorithm for crop disease images based on knowledge distillation networks	45
On-line monitoring of structural performance of scraper conveyor driven by digital twin	44
Multi-view Isolated sign language recognition based on cross-view and multi-level transformer	44
Model-based portrait video compression with spatial constraint and adaptive pose processing	43
JAMD-Net: image splicing forgery detection based on JPEG compression artifacts and multi-dilated channel refinement fusion	39
Segmentation-aware image super-resolution with generative adversarial networks	36
CHCoT-MSLU: a coupled hierarchical chain-of-thought prompt learning model for multi-intent spoken language understanding	34
Real emotion seeker: recalibrating annotation for facial expression recognition	33
Towards domain adaptation underwater image enhancement and restoration	32
Fast latent-feature augmentation for cross-domain face forgery detection	32
SFRA: spatial fusion regression augmentation network for facial landmark detection	32
A comparative study of color quantization methods using various image quality assessment indices	31
Feature fusion and optimization integrated refined deep residual network for diabetic retinopathy severity classification using fundus image	31
360° video quality assessment based on saliency-guided viewport extraction	31
LEA-depth: a lightweight self-supervised monocular depth estimation with attention fusion and edge-aware distillation	30
GVA: guided visual attention approach for automatic image caption generation	30

The segmented UEC Food-100 dataset with benchmark experiment on food detection	30
Mamba-driven context-aware tracking with dual prompts	27
GCGV: a dual-branch hybrid network integrating graph attention, CNNs, and vision transformers for enhanced hyperspectral image classification	27