OOIR: Observatory of International Research

Papers

(The H4-Index of Image and Vision Computing is 34. 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 2022-06-01 to 2026-06-01.)

Article	Citations
PST-Mamba: Spatio-temporal selective state fusion for effective point cloud video understanding with state space models	427
ADVC: Adversarial dense video captioning with unsupervised pretraining	189
CAGS: Open-vocabulary 3D scene understanding with context-aware Gaussian splatting	185
ABC: Aligning binary centers for single-stage monocular 3D object detection	181
Alignment and fusion for adaptive domain nighttime semantic segmentation	121
Few-shot-based video generation via multimodal fusion and Fourier Spliter	116
Feature decoupling and interaction network for defending against adversarial examples	98
Modeling content-attribute preference for personalized image esthetics assessment	87
GLMambaNet: Mamba-based decoder with local detail enhancement for semantic segmentation of remote sensing imagery	84
Efficient ultra-lightweight convolutional attention network for embedded identity document recognition system	77
Accurate and efficient salient object detection via position prior attention	76
Multi-information guided camouflaged object detection	68
G-TRACE: Grouped temporal recalibration for video object segmentation	67
Hourglass cascaded recurrent stereo matching network	66
DMNet: Image dehazing via Dual-Domain Modulation	59
SRMA-KD: Structured relational multi-scale attention knowledge distillation for effective lightweight cardiac image segmentation	59
HPD-Depth: High performance decoding network for self-supervised monocular depth estimation	54
Window normalization: Enhancing point cloud understanding by unifying inconsistent point densities	53
Background debiased class incremental learning for video action recognition	53
Privacy-preserving explainable AI enable federated learning-based denoising fingerprint recognition model	50
MAFUNet: Mamba with adaptive fusion UNet for medical image segmentation	48
RGB-T tracking by modality difference reduction and feature re-selection	48
DeepArUco++: Improved detection of square fiducial markers in challenging lighting conditions	47
BF3D: Bi-directional fusion 3D detector with semantic sampling and geometric mapping	43
AI-powered trustable and explainable fall detection system using transfer learning	43

Lightweight multi-scale global attention enhancement network for image super-resolution	42
Learning diverse and deep clues for person reidentification	41
Active domain adaptation for semantic segmentation via dynamically balancing domainness and uncertainty	40
CODNet: Context-based object detection network for multimodal image captioning and virtual question answering	38
Synthetic lidar point cloud generation using deep generative models for improved driving scene object recognition	38
GAN-BodyPose: Real-time 3D human body pose data key point detection and quality assessment assisted by generative adversarial network	36
Single stage architecture for improved accuracy real-time object detection on mobile devices	36
Few-shot classification with multisemantic information fusion network	35
CMS-net: Edge-aware multimodal MRI feature fusion for brain tumor segmentation	34
CSG-DOF:A Class Structure-Guided Discriminative Optimization Framework for few-shot object detection	34
Burst image super-resolution via multi-cross attention encoding and multi-scan state-space decoding	34
SAGNet: Synergistic Attention-Graph Network For video salient object detection	34