Terkko Navigator / International journal of computer vision

Selective Wavelet Attention Learning for Single Image Deraining

Comparison of Full-Reference Image Quality Models for Optimization of Image Processing Systems

Unified Quality Assessment of in-the-Wild Videos with Mixed Datasets Training

Complete Singularity Analysis for the Perspective-Four-Point Problem

Incremental Rotation Averaging

Label-Free Robustness Estimation of Object Detection CNNs for Autonomous Driving Applications

Benchmarking Low-Light Image Enhancement and Beyond

A Shape Transformation-based Dataset Augmentation Framework for Pedestrian Detection

Excitation Dropout: Encouraging Plasticity in Deep Neural Networks

Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation

Beyond Brightening Low-light Images

The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection

Evaluation of Inpainting and Augmentation for Censored Image Queries

AutoDet: Pyramid Network Architecture Search for Object Detection

Learning to Reconstruct HDR Images from Events, with Applications to Depth and Flow Prediction

Hierarchical Visual-Textual Knowledge Distillation for Life-Long Correlation Learning

Adding Knowledge to Unsupervised Algorithms for the Recognition of Intent

Separating Content from Style Using Adversarial Learning for Recognizing Text in the Wild

A Benchmark and Evaluation of Non-Rigid Structure from Motion

Learning Extremal Representations with Deep Archetypal Analysis

MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking

Reference Pose Generation for Long-term Visual Localization via Learned Features and View Synthesis

Unsupervised Deep Representation Learning for Real-Time Tracking

Face Image Reflection Removal

Guest Editorial: Generative Adversarial Networks for Computer Vision

A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains

Volume Sweeping: Learning Photoconsistency for Multi-View Shape Reconstruction

J $$\hat{\text {A}}$$ A ^ A-Net: Joint Facial Action Unit Detection and Face Alignment Via Adaptive Attention

Beyond Covariance: SICE and Kernel Based Visual Feature Representation

A Camera Model for Line-Scan Cameras with Telecentric Lenses

Unsupervised Domain Adaptation in the Wild via Disentangling Representation Learning

Densifying Supervision for Fine-Grained Visual Comparisons

Image Matching from Handcrafted to Deep Features: A Survey

View Transfer on Human Skeleton Pose: Automatically Disentangle the View-Variant and View-Invariant Information for Pose Representation Learning

Multi-task Compositional Network for Visual Relationship Detection

Semantically Tied Paired Cycle Consistency for Any-Shot Sketch-Based Image Retrieval

Zero-Shot Object Detection: Joint Recognition and Localization of Novel Concepts

Video Based Face Recognition by Using Discriminatively Learned Convex Models

Rooted Spanning Superpixels

Long-Short Temporal–Spatial Clues Excited Network for Robust Person Re-identification

Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images

RoCGAN: Robust Conditional GAN

Label Embedding: A Frugal Baseline for Text Recognition