OOIR: Observatory of International Research

Papers

(The H4-Index of Image and Vision Computing is 36. 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
ADVC: Adversarial dense video captioning with unsupervised pretraining	462
Alignment and fusion for adaptive domain nighttime semantic segmentation	207
Few-shot-based video generation via multimodal fusion and Fourier Spliter	198
Feature decoupling and interaction network for defending against adversarial examples	129
Modeling content-attribute preference for personalized image esthetics assessment	128
GLMambaNet: Mamba-based decoder with local detail enhancement for semantic segmentation of remote sensing imagery	107
Efficient ultra-lightweight convolutional attention network for embedded identity document recognition system	97
Accurate and efficient salient object detection via position prior attention	94
Multi-information guided camouflaged object detection	87
G-TRACE: Grouped temporal recalibration for video object segmentation	80
BF3D: Bi-directional fusion 3D detector with semantic sampling and geometric mapping	78
Learning diverse and deep clues for person reidentification	67
Lightweight multi-scale global attention enhancement network for image super-resolution	67
DMNet: Image dehazing via Dual-Domain Modulation	64
Active domain adaptation for semantic segmentation via dynamically balancing domainness and uncertainty	64
Window normalization: Enhancing point cloud understanding by unifying inconsistent point densities	62
Background debiased class incremental learning for video action recognition	61
AI-powered trustable and explainable fall detection system using transfer learning	59
RGB-T tracking by modality difference reduction and feature re-selection	59
ABC: Aligning binary centers for single-stage monocular 3D object detection	53
Hourglass cascaded recurrent stereo matching network	52
DeepArUco++: Improved detection of square fiducial markers in challenging lighting conditions	48
GAN-BodyPose: Real-time 3D human body pose data key point detection and quality assessment assisted by generative adversarial network	48
HPD-Depth: High performance decoding network for self-supervised monocular depth estimation	46
UCPNet: An Ultra-Lightweight Cross-Perception Network for Real-Time Semantic Segmentation	44

Privacy-preserving explainable AI enable federated learning-based denoising fingerprint recognition model	43
CODNet: Context-based object detection network for multimodal image captioning and virtual question answering	42
Single stage architecture for improved accuracy real-time object detection on mobile devices	42
MAFUNet: Mamba with adaptive fusion UNet for medical image segmentation	41
SRMA-KD: Structured relational multi-scale attention knowledge distillation for effective lightweight cardiac image segmentation	39
PST-Mamba: Spatio-temporal selective state fusion for effective point cloud video understanding with state space models	39
Few-shot classification with multisemantic information fusion network	38
Synthetic lidar point cloud generation using deep generative models for improved driving scene object recognition	38
CAGS: Open-vocabulary 3D scene understanding with context-aware Gaussian splatting	38
Recent advances in deterministic human motion prediction: A review	36
SAGNet: Synergistic Attention-Graph Network For video salient object detection	36
Two-stream transformer tracking with messengers	36
Burst image super-resolution via multi-cross attention encoding and multi-scan state-space decoding	36