OOIR: Observatory of International Research

Papers

(The H4-Index of Image and Vision Computing is 31. 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 2021-10-01 to 2025-10-01.)

Article	Citations
Learning diverse and deep clues for person reidentification	234
Active domain adaptation for semantic segmentation via dynamically balancing domainness and uncertainty	171
HPD-Depth: High performance decoding network for self-supervised monocular depth estimation	142
ADVC: Adversarial dense video captioning with unsupervised pretraining	123
Alignment and fusion for adaptive domain nighttime semantic segmentation	107
Modeling content-attribute preference for personalized image esthetics assessment	93
Editorial Board	84
ABC: Aligning binary centers for single-stage monocular 3D object detection	82
Accurate and efficient salient object detection via position prior attention	81
Single stage architecture for improved accuracy real-time object detection on mobile devices	74
FMD-Yolo: An efficient face mask detection method for COVID-19 prevention and control in public	73
Cross-scale global attention feature pyramid network for person search	64
Feature decoupling and interaction network for defending against adversarial examples	63
BF3D: Bi-directional fusion 3D detector with semantic sampling and geometric mapping	63
Hourglass cascaded recurrent stereo matching network	60
G-TRACE: Grouped temporal recalibration for video object segmentation	55
Multi-information guided camouflaged object detection	43
PU-GACNet: Graph Attention Convolution Network for Point Cloud Upsampling	43
Few-shot classification with multisemantic information fusion network	41
Learning an augmentation strategy for sparse datasets	39
DeepArUco++: Improved detection of square fiducial markers in challenging lighting conditions	38
SRMA-KD: Structured relational multi-scale attention knowledge distillation for effective lightweight cardiac image segmentation	36
Background debiased class incremental learning for video action recognition	36
Lightweight multi-scale global attention enhancement network for image super-resolution	35
Synthetic lidar point cloud generation using deep generative models for improved driving scene object recognition	35

AI-powered trustable and explainable fall detection system using transfer learning	34
RGB-T tracking by modality difference reduction and feature re-selection	34
DMNet: Image dehazing via Dual-Domain Modulation	32
MAFUNet: Mamba with adaptive fusion UNet for medical image segmentation	32
Privacy-preserving explainable AI enable federated learning-based denoising fingerprint recognition model	31
GAN-BodyPose: Real-time 3D human body pose data key point detection and quality assessment assisted by generative adversarial network	31
1D kernel distillation network for efficient image super-resolution	31