OOIR: Observatory of International Research

Papers

(The H4-Index of Multimedia Systems is 26. 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 2022-05-01 to 2026-05-01.)

Article	Citations
Pseudo-global strategy-based visual comfort assessment considering attention mechanism	161
SS-CMT: a label independent cross-modal transferable adversarial video attack with sparse strategy	122
DiffRA: universal restorative adversarial attack based on diffusion model	93
SFFN-YOLO for small object detection in aerial images	81
On-line monitoring of structural performance of scraper conveyor driven by digital twin	74
Dual convolutional neural network with attention for image blind denoising	60
TreeSegNet: multi-scale query-based instance segmentation with frequency-aware and gated feature enhancement	59
Fast latent-feature augmentation for cross-domain face forgery detection	54
Face and voice cross-modal association with learning convex feature embedding	52
CAPNet: tomato leaf disease detection network based on adaptive feature fusion and convolutional enhancement	52
BENet: bi-directional enhanced network for image captioning	51
Deep Learning-based forgery detection and localization for compressed images using a hybrid optimization model	46
Multi-level sentiment-aware clustering for denoising in multimodal sentiment analysis with ASR errors	45
A variational causal inference-based method for recognizing object state changes in videos	42
Feature fusion and optimization integrated refined deep residual network for diabetic retinopathy severity classification using fundus image	40
Design and realization of pulse-controlled multi-memristor Hopfield neural networks and their applications in information encryption	39
LMFE-RDD: a road damage detector with a lightweight multi-feature extraction network	38
Improving text-image cross-modal retrieval with contrastive loss	34
Segmentation-aware image super-resolution with generative adversarial networks	32
JAMD-Net: image splicing forgery detection based on JPEG compression artifacts and multi-dilated channel refinement fusion	31
Generalizing sentence-level lipreading to unseen speakers: a two-stream end-to-end approach	30
CHCoT-MSLU: a coupled hierarchical chain-of-thought prompt learning model for multi-intent spoken language understanding	29
The segmented UEC Food-100 dataset with benchmark experiment on food detection	29
Real emotion seeker: recalibrating annotation for facial expression recognition	29
A visual question answering model based on image captioning	28

Correction: STASiamRPN: visual tracking based on spatiotemporal and attention	27
Automatic lymph node segmentation using deep parallel squeeze & excitation and attention Unet	26