OOIR: Observatory of International Research

Papers

(The H4-Index of International Journal of Computer Vision is 52. 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 2021-09-01 to 2025-09-01.)

Article	Citations
Learning Accurate Performance Predictors for Ultrafast Automated Model Compression	1612
Dissecting Out-of-Distribution Detection and Open-Set Recognition: A Critical Analysis of Methods and Benchmarks	1175
Guest Editorial: Special Issue on Open-World Visual Recognition	1171
Instance-Aware Scene Layout Forecasting	489
Exploring the Semi-Supervised Video Object Segmentation Problem from a Cyclic Perspective	400
Physical Representation Learning and Parameter Identification from Video Using Differentiable Physics	293
GenKL: An Iterative Framework for Resolving Label Ambiguity and Label Non-conformity in Web Images Via a New Generalized KL Divergence	249
Common Pole–Polar Properties of Central Catadioptric Sphere and Line Images Used for Camera Calibration	236
Correction: Multi-source-free Domain Adaptive Object Detection	210
Learning Text-to-Video Retrieval from Image Captioning	208
Learning Discriminative Features for Visual Tracking via Scenario Decoupling	187
MoDA: Modeling Deformable 3D Objects from Casual Videos	161
Conditional Temporal Variational AutoEncoder for Action Video Prediction	160
From Open Set to Closed Set: Supervised Spatial Divide-and-Conquer for Object Counting	148
Guest Editorial: Special Issue on Large-Scale Generative Models for Content Creation and Manipulation	142
Bootstrapping Vision-Language Models for Frequency-Centric Self-Supervised Remote Physiological Measurement	140
Are Vision Transformers Robust to Spurious Correlations?	137
BioDrone: A Bionic Drone-Based Single Object Tracking Benchmark for Robust Vision	129
PanAf20K: A Large Video Dataset for Wild Ape Detection and Behaviour Recognition	125
Learning with Enriched Inductive Biases for Vision-Language Models	119
RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion	117
View Birdification in the Crowd: Ground-Plane Localization from Perceived Movements	113
AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach	111
Learning Extensible Series-Parallel Lookup Tables for Efficient Image Super-Resolution	105
Image Synthesis Under Limited Data: A Survey and Taxonomy	103

FastComposer: Tuning-Free Multi-subject Image Generation with Localized Attention	102
Delving Deeper into Anti-Aliasing in ConvNets	98
EAN: Event Adaptive Network for Enhanced Action Recognition	95
OpenMonkeyChallenge: Dataset and Benchmark Challenges for Pose Estimation of Non-human Primates	94
Deep Image Deblurring: A Survey	92
SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channels	92
A Minimal Solution for Image-Based Sphere Estimation	85
Instance-dependent Label Distribution Estimation for Learning with Label Noise	85
Correction: SOTVerse: A User-Defined Task Space of Single Object Tracking	84
NAFT and SynthStab: A RAFT-Based Network and a Synthetic Dataset for Digital Video Stabilization	81
VideoQA in the Era of LLMs: An Empirical Study	72
Learning to Generalize Heterogeneous Representation for Cross-Modality Image Synthesis via Multiple Domain Interventions	70
UMSCS: A Novel Unpaired Multimodal Image Segmentation Method Via Cross-Modality Generative and Semi-supervised Learning	68
Relating View Directions of Complementary-View Mobile Cameras via the Human Shadow	67
Project to Adapt: Domain Adaptation for Depth Completion from Noisy and Sparse Sensor Data	65
ICEv2: Interpretability, Comprehensiveness, and Explainability in Vision Transformer	63
Bi-calibration Networks for Weakly-Supervised Video Representation Learning	61
Semantic-Based Implicit Feature Transform for Few-Shot Classification	61
Feature Hallucination for Self-supervised Action Recognition	61
Sfnet: Faster and Accurate Semantic Segmentation Via Semantic Flow	60
Lightweight and Progressively-Scalable Networks for Semantic Segmentation	60
Diagram Perception Networks for Textbook Question Answering via Joint Optimization	59
Weakly Supervised Training of Universal Visual Concepts for Multi-domain Semantic Segmentation	56
A Realism Metric for Generated LiDAR Point Clouds	54
Skeleton Ground Truth Extraction: Methodology, Annotation Tool and Benchmarks	54
Free-view Face Relighting Using a Hybrid Parametric Neural Model on a SMALL-OLAT Dataset	53
Exploiting Inter-Sample Affinity for Knowability-Aware Universal Domain Adaptation	53
Guest Editorial: Special Issue on the British Machine Vision Conference 2022	52