Computer Vision Systems 14th International Conference, ICVS 2023, Vienna, Austria, September 27–29, 2023, Proceedings

This volume LNCS 14253 constitutes the refereed proceedings of the 14th International Conference, ICVS 2023, in Vienna, Austria, in September 2023..  

The 37 full papers presented were carefully reviewed and selected from 74 submissions. The conference focuses on Humans and Hands; Medical and Health Care; Farming and Forestry; Automation and Manufacturing; Mobile Robotics and Autonomous Systems;  and Performance and Robustness.

Humans and Hands.- Tracking and Identification of Ice Hockey Players.- Dedicated Encoding-streams based Spatio-Temporal framework for dynamic person-independent facial expression recognition.- Hands, Objects, Action! Egocentric 2D Hand-based Action Recognition.- WiFi CSI-Based Long-Range Through-Wall Human Activity Recognition with the ESP32.- PseudoDepth-SLR: Generating Depth Data for Sign Language Recognition.- Slovo: Russian Sign Language Dataset.- Non-contact Heart Rate Monitoring: A Comparative Study of Computer Vision and Radar Approaches.- Medical and Health Care.- CFAB: An Online Data Augmentation to Alleviate the Spuriousness of Classification on Medical Ultrasound Images.- Towards an Unsupervised GrowCut Algorithm for Mammography Segmentation.- DeepLabV3+ Ensemble for Diagnosis of Cardiac Transplant Rejection.- Farming and Forestry.- Of Mice and Pose: 2D Mouse Pose Estimation from Unlabelled Data and Synthetic Prior.- SIFT-guided Saliency-based Augmentation for Weed Detection in Grassland Images:Fusing Classic Computer Vision with Deep Learning.- Key Point-based Orientation Estimation of Strawberries for Robotic Fruit Picking.- Residual Cascade CNN for Detection of Spatially Relevant Objects in Agriculture: The Grape-Stem Paradigm.- Improving Knot Prediction in Wood Logs with Longitudinal Feature Propagation.- Automation and Manufacturing.- Semi-Siamese Network for Robust Change Detection Across Different Domains with Applications to 3D Printing.- Spatial resolution metric for optimal viewpoints generation in visual inspection planning.- A deep learning-based object detection framework for automatic asphalt pavement patch detection using laser profiling images.- A Flexible Approach to PCB Characterization for Recycling.- SynthRetailProduct3D (SyRePro3D): A Pipeline for Synthesis of 3D Retail Product Models with Domain Specific Details based on Package Class Templates.- Small, but important: Traffic light proposals for detecting small traffic lights and beyond.- MATWI: a Multimodal Automatic Tool Wear Inspection dataset and baseline algorithms.- Mixing Domains for Smartly Picking and Using Limited Datasets in Industrial Object Detection.- Mobile Robotics and Autonomous Systems.- Dynamic Vision-based Satellite Detection: A Time-based Encoding Approach with Spiking Neural Networks.- A Hardware-aware Sampling Parameter Search for Efficient Probabilistic Object Detection.- Towards Food Handling Robots for Automated Meal Preparation in Healthcare Facilities.- TrackAgent: 6D Object Tracking via Reinforcement Learning.- Improving Generalization of Synthetically Trained Sonar Image Descriptors for Underwater Place Recognition.- A uniform distribution of landmarks for efficient map compression.- A Novel Approach: Fourier Series Parameterization and Support Vector Machine Regression for 2D Laser SLAM with Closed Shape Features.- Performance and Robustness.- Performance and Failure Cause Estimation for Machine Learning Systems in the Wild.- Data-Free Model Extraction Attacks in the Context of Object Detection.- xAI-CycleGAN, a Cycle-Consistent Generative Assistive Network.- Improving 3D Inline Computational Imaging of Textureless Objects using Pattern Illumination.- Integrating Visual and Semantic Similarity Using Hierarchies for Image Retrieval.- BEVSeg: Geometry and Data-Driven based Multi-View Segmentation in Bird's-Eye-View.- Descriptive Attributes for Language-based Object Keypoint Detection.