OOIR: Observatory of International Research

Papers

(The H4-Index of International Journal of Computer Vision is 48. 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 2021-08-01 to 2025-08-01.)

Article	Citations
Learning Accurate Performance Predictors for Ultrafast Automated Model Compression	1422
A Minimal Solution for Image-Based Sphere Estimation	1140
Dissecting Out-of-Distribution Detection and Open-Set Recognition: A Critical Analysis of Methods and Benchmarks	1128
Guest Editorial: Special Issue on Open-World Visual Recognition	418
Instance-Aware Scene Layout Forecasting	388
Exploring the Semi-Supervised Video Object Segmentation Problem from a Cyclic Perspective	267
Image Synthesis Under Limited Data: A Survey and Taxonomy	225
Physical Representation Learning and Parameter Identification from Video Using Differentiable Physics	225
Instance-dependent Label Distribution Estimation for Learning with Label Noise	198
GenKL: An Iterative Framework for Resolving Label Ambiguity and Label Non-conformity in Web Images Via a New Generalized KL Divergence	188
PanAf20K: A Large Video Dataset for Wild Ape Detection and Behaviour Recognition	158
Common Pole–Polar Properties of Central Catadioptric Sphere and Line Images Used for Camera Calibration	148
Correction: Multi-source-free Domain Adaptive Object Detection	145
Learning Text-to-Video Retrieval from Image Captioning	135
Learning Discriminative Features for Visual Tracking via Scenario Decoupling	134
MoDA: Modeling Deformable 3D Objects from Casual Videos	125
Conditional Temporal Variational AutoEncoder for Action Video Prediction	114
From Open Set to Closed Set: Supervised Spatial Divide-and-Conquer for Object Counting	112
Guest Editorial: Special Issue on Large-Scale Generative Models for Content Creation and Manipulation	111
Learning with Enriched Inductive Biases for Vision-Language Models	110
View Birdification in the Crowd: Ground-Plane Localization from Perceived Movements	109
RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion	109
AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach	105
Learning Extensible Series-Parallel Lookup Tables for Efficient Image Super-Resolution	98
Bootstrapping Vision-Language Models for Frequency-Centric Self-Supervised Remote Physiological Measurement	95

EAN: Event Adaptive Network for Enhanced Action Recognition	93
Are Vision Transformers Robust to Spurious Correlations?	92
SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channels	90
BioDrone: A Bionic Drone-Based Single Object Tracking Benchmark for Robust Vision	90
Deep Image Deblurring: A Survey	90
OpenMonkeyChallenge: Dataset and Benchmark Challenges for Pose Estimation of Non-human Primates	90
FastComposer: Tuning-Free Multi-subject Image Generation with Localized Attention	84
Delving Deeper into Anti-Aliasing in ConvNets	80
Guest Editorial: Special Issue on the Promises and Dangers of Large Vision Models	79
Correction: SOTVerse: A User-Defined Task Space of Single Object Tracking	76
NAFT and SynthStab: A RAFT-Based Network and a Synthetic Dataset for Digital Video Stabilization	69
Lightweight and Progressively-Scalable Networks for Semantic Segmentation	66
UniCanvas: Affordance-Aware Unified Real Image Editing via Customized Text-to-Image Generation	64
VideoQA in the Era of LLMs: An Empirical Study	63
Learning to Generalize Heterogeneous Representation for Cross-Modality Image Synthesis via Multiple Domain Interventions	62
In the Eye of Transformer: Global–Local Correlation for Egocentric Gaze Estimation and Beyond	62
UMSCS: A Novel Unpaired Multimodal Image Segmentation Method Via Cross-Modality Generative and Semi-supervised Learning	60
Relating View Directions of Complementary-View Mobile Cameras via the Human Shadow	57
FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild	57
Project to Adapt: Domain Adaptation for Depth Completion from Noisy and Sparse Sensor Data	54
ICEv2: Interpretability, Comprehensiveness, and Explainability in Vision Transformer	53
Weakly Supervised Training of Universal Visual Concepts for Multi-domain Semantic Segmentation	53
A Realism Metric for Generated LiDAR Point Clouds	50