OOIR: Observatory of International Research

Papers

(The H4-Index of Visual Computer 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 2022-06-01 to 2026-06-01.)

Article	Citations
Robust object recognition via context-driven reliability assessment	132
Adaptively weighted discrete Laplacian for inverse rendering	100
Learning shape abstraction by cropping positive cuboid primitives with negative ones	89
Edge-priority-extraction network using re-parameterization for real-time super-resolution	83
Enhancing green screen matting with group normalization and perceptual loss for color overflow and complex edges	63
V$$^2$$MLP: an accurate and simple multi-view MLP network for fine-grained 3D shape recognition	58
Deep learning in chronic wound segmentation: a comprehensive review and meta-analysis	54
Multi-modal co-attention relation networks for visual question answering	54
Joint attribute soft-sharing and contextual local: a multi-level features learning network for person re-identification	52
Feature decomposition and structural learning for multi-diverse and multi-view data clustering	48
Enhanced Temporal Representation and Spatial Alignment for High-Fidelity Talking Video Generation	48
Adaptive box-level supervision with superpixel shape guidance for ultrasound image segmentation	47
Monocular human depth estimation with 3D motion flow and surface normals	45
Camera calibration for the surround-view system: a benchmark and dataset	45
TaiChiGPT: complex sports action generation based on large language models	44
Image encryption algorithm based on cross-scrambling and rapid-mode diffusion	43
SCAKD: a knowledge distillation framework based on spatial-corner attention for infrared and visible image fusion	43
Self-knowledge distillation through ensemble model averaging: a novel approach for image classification	41
A multi-target cow face detection model in complex scenes	41
Developing an augmented reality framework with embedded objects and adaptive optical models for advanced lighting simulation	40
PoseNorm-PCN: pose-normalized human point cloud completion from a single front view	40
Lightweight subpixel sampling network for image super-resolution	39
MoCoSys: human motion correction based on deep learning coupled with 3D+t Laplacian motion representation	38
MAPD: multi-receptive field and attention mechanism for multispectral pedestrian detection	38
AttentionDIP: attention-based deep image prior model to restore satellite and aerial images from gamma distributed speckle interference	37

Virtual object sizes for efficient and convenient mid-air manipulation	37
Using transfer learning to determine the type of mathematical fractals image of Islamic geometric patterns	34
Enhanced optical flow estimation via multiscale kernel selection and super-resolution integration	34
ER: Extract-regress network for precise 3D reconstruction of interacting hands from monocular images	33
Uncertainty-guided time–frequency feature enhancement for emotion-aware speech-driven 3D facial animation	32
A two-stage model for spatial downscaling of daily precipitation data	31
Road crack detection using pixel classification and intensity-based distinctive fuzzy C-means clustering	31
Nighttime driver behavior prediction using taillight signal recognition via CNN-SVM classifier	31