OOIR: Observatory of International Research

Papers

(The H4-Index of Image and Vision Computing is 35. 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
ABC: Aligning binary centers for single-stage monocular 3D object detection	415
Lightweight multi-scale global attention enhancement network for image super-resolution	179
Alignment and fusion for adaptive domain nighttime semantic segmentation	179
DeepArUco++: Improved detection of square fiducial markers in challenging lighting conditions	153
AI-powered trustable and explainable fall detection system using transfer learning	120
BF3D: Bi-directional fusion 3D detector with semantic sampling and geometric mapping	110
SRMA-KD: Structured relational multi-scale attention knowledge distillation for effective lightweight cardiac image segmentation	94
Accurate and efficient salient object detection via position prior attention	86
G-TRACE: Grouped temporal recalibration for video object segmentation	80
Efficient ultra-lightweight convolutional attention network for embedded identity document recognition system	75
CODNet: Context-based object detection network for multimodal image captioning and virtual question answering	72
PST-Mamba: Spatio-temporal selective state fusion for effective point cloud video understanding with state space models	69
ADVC: Adversarial dense video captioning with unsupervised pretraining	67
CAGS: Open-vocabulary 3D scene understanding with context-aware Gaussian splatting	66
GAN-BodyPose: Real-time 3D human body pose data key point detection and quality assessment assisted by generative adversarial network	62
Single stage architecture for improved accuracy real-time object detection on mobile devices	59
MAFUNet: Mamba with adaptive fusion UNet for medical image segmentation	58
Learning diverse and deep clues for person reidentification	52
Active domain adaptation for semantic segmentation via dynamically balancing domainness and uncertainty	52
Privacy-preserving explainable AI enable federated learning-based denoising fingerprint recognition model	49
Synthetic lidar point cloud generation using deep generative models for improved driving scene object recognition	49
HPD-Depth: High performance decoding network for self-supervised monocular depth estimation	47
Feature decoupling and interaction network for defending against adversarial examples	46
Modeling content-attribute preference for personalized image esthetics assessment	45
GLMambaNet: Mamba-based decoder with local detail enhancement for semantic segmentation of remote sensing imagery	42

Background debiased class incremental learning for video action recognition	40
Few-shot-based video generation via multimodal fusion and Fourier Spliter	40
Window normalization: Enhancing point cloud understanding by unifying inconsistent point densities	38
Hourglass cascaded recurrent stereo matching network	37
RGB-T tracking by modality difference reduction and feature re-selection	37
Multi-information guided camouflaged object detection	37
Few-shot classification with multisemantic information fusion network	36
DMNet: Image dehazing via Dual-Domain Modulation	36
SAGNet: Synergistic Attention-Graph Network For video salient object detection	35
Frequency and content dual stream network for image dehazing	35