OOIR: Observatory of International Research

Papers

(The H4-Index of Image and Vision Computing is 32. 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 2021-11-01 to 2025-11-01.)

Article	Citations
Active domain adaptation for semantic segmentation via dynamically balancing domainness and uncertainty	266
Alignment and fusion for adaptive domain nighttime semantic segmentation	173
Cross-scale global attention feature pyramid network for person search	146
Single stage architecture for improved accuracy real-time object detection on mobile devices	123
Few-shot classification with multisemantic information fusion network	109
Modeling content-attribute preference for personalized image esthetics assessment	101
Feature decoupling and interaction network for defending against adversarial examples	97
Learning diverse and deep clues for person reidentification	87
Editorial Board	78
ABC: Aligning binary centers for single-stage monocular 3D object detection	77
Hourglass cascaded recurrent stereo matching network	67
CODNet: Context-based object detection network for multimodal image captioning and virtual question answering	64
BF3D: Bi-directional fusion 3D detector with semantic sampling and geometric mapping	63
Accurate and efficient salient object detection via position prior attention	60
Synthetic lidar point cloud generation using deep generative models for improved driving scene object recognition	55
FMD-Yolo: An efficient face mask detection method for COVID-19 prevention and control in public	49
GLMambaNet: Mamba-based decoder with local detail enhancement for semantic segmentation of remote sensing imagery	44
G-TRACE: Grouped temporal recalibration for video object segmentation	44
HPD-Depth: High performance decoding network for self-supervised monocular depth estimation	43
SRMA-KD: Structured relational multi-scale attention knowledge distillation for effective lightweight cardiac image segmentation	41
Background debiased class incremental learning for video action recognition	41
ADVC: Adversarial dense video captioning with unsupervised pretraining	37
Learning an augmentation strategy for sparse datasets	36
PU-GACNet: Graph Attention Convolution Network for Point Cloud Upsampling	35
MAFUNet: Mamba with adaptive fusion UNet for medical image segmentation	34

Multi-information guided camouflaged object detection	34
GAN-BodyPose: Real-time 3D human body pose data key point detection and quality assessment assisted by generative adversarial network	34
AI-powered trustable and explainable fall detection system using transfer learning	34
DMNet: Image dehazing via Dual-Domain Modulation	33
DeepArUco++: Improved detection of square fiducial markers in challenging lighting conditions	32
RGB-T tracking by modality difference reduction and feature re-selection	32
Deep learning with adaptive convolutions for classification of retinal diseases via optical coherence tomography	32
PST-Mamba: Spatio-temporal selective state fusion for effective point cloud video understanding with state space models	32
Lightweight multi-scale global attention enhancement network for image super-resolution	32
1D kernel distillation network for efficient image super-resolution	32
Privacy-preserving explainable AI enable federated learning-based denoising fingerprint recognition model	32