OOIR: Observatory of International Research

Papers

(The H4-Index of International Journal of Computer Vision is 46. 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 2021-02-01 to 2025-02-01.)

Article	Citations
Towards Robust Monocular Depth Estimation: A New Baseline and Benchmark	1603
Spectral Shape Recovery and Analysis Via Data-driven Connections	900
Learning with Enriched Inductive Biases for Vision-Language Models	891
Unsupervised Semantic Segmentation of Urban Scenes via Cross-Modal Distillation	806
Rethinking Generalizability and Discriminability of Self-Supervised Learning from Evolutionary Game Theory Perspective	290
A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking	247
Contextual Object Detection with Multimodal Large Language Models	196
Toward Accurate and Robust Pedestrian Detection via Variational Inference	179
Image Synthesis Under Limited Data: A Survey and Taxonomy	168
Dual-Space Video Person Re-identification	164
A Survey on Adaptive Cameras	160
PL$${}_{1}$$P: Point-Line Minimal Problems under Partial Visibility in Three Views	146
Common Pole–Polar Properties of Central Catadioptric Sphere and Line Images Used for Camera Calibration	142
WATCHER: Wavelet-Guided Texture-Content Hierarchical Relation Learning for Deepfake Detection	142
Dissecting Out-of-Distribution Detection and Open-Set Recognition: A Critical Analysis of Methods and Benchmarks	132
Regional Adversarial Training for Better Robust Generalization	127
Rethinking Out-of-Distribution Detection From a Human-Centric Perspective	97
Efficient High-Quality Vectorized Modeling of Large-Scale Scenes	93
RMS-FlowNet++: Efficient and Robust Multi-scale Scene Flow Estimation for Large-Scale Point Clouds	88
An Empirical Study on Multi-domain Robust Semantic Segmentation	86
Re-ID-leak: Membership Inference Attacks Against Person Re-identification	85
SegViT v2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers	84
DOVE: Learning Deformable 3D Objects by Watching Videos	83
Learning Dynamic Prototypes for Visual Pattern Debiasing	80
Deep Physics-Guided Unrolling Generalization for Compressed Sensing	80

Editor’s Note: Special Issue on BMVC 2021	77
Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Prior	74
Robots Understanding Contextual Information in Human-Centered Environments Using Weakly Supervised Mask Data Distillation	73
EAN: Event Adaptive Network for Enhanced Action Recognition	72
Learning Accurate Performance Predictors for Ultrafast Automated Model Compression	69
Editor’s Note: Special Issue on Computer Vision and Cultural Heritage Preservation	66
Interpreting Face Inference Models Using Hierarchical Network Dissection	65
View Birdification in the Crowd: Ground-Plane Localization from Perceived Movements	61
Renormalization for Initialization of Rolling Shutter Visual-Inertial Odometry	59
Hierarchical Curriculum Learning for No-Reference Image Quality Assessment	58
Dynamic Context Removal: A General Training Strategy for Robust Models on Video Action Predictive Tasks	58
Context-Enhanced Representation Learning for Single Image Deraining	56
From Individual to Whole: Reducing Intra-class Variance by Feature Aggregation	55
Self-supervised Secondary Landmark Detection via 3D Representation Learning	55
Semi-Supervised and Long-Tailed Object Detection with CascadeMatch	55
RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learning	52
Development and Validation of an Unsupervised Feature Learning System for Leukocyte Characterization and Classification: A Multi-Hospital Study	51
Conditional Temporal Variational AutoEncoder for Action Video Prediction	50
The Isowarp: The Template-Based Visual Geometry of Isometric Surfaces	49
An Exploration of Embodied Visual Exploration	48
Visual Object Tracking in First Person Vision	46
Lidar Panoptic Segmentation in an Open World	46
Breaking the Limits of Reliable Prediction via Generated Data	46