This book constitutes the refereed proceedings of the 13th International Conference on Computer Vision Systems, ICVS 2021, held in September 2021. Due to COVID-19 pandemic the conference was held virtually.
The 20 papers presented were carefully reviewed and selected from 29 submissions. cover a broad spectrum of issues falling under the wider scope of computer vision in real-world applications, including among others, vision systems for robotics, autonomous vehicles, agriculture and medicine. In this volume, the papers are organized into the sections: attention systems; classification and detection; semantic interpretation; video and motion analysis; computer vision systems in agriculture.
Inhaltsverzeichnis
Attention Systems. - Thermal Image Super-Resolution Using Second-Order Channel Attention with Varying Receptive Fields. - MARL: Multimodal Attentional Representation Learning for Disease Prediction. - Object Localization with Attribute Preference based on Top-Down Attention. - See the silence: improving visual-only voice activity detection by optical flow and RGB fusion. - Classification and Detection. - Score to Learn: a Comparative Analysis of Scoring Functions for Active Learning in Robotics. - Enhancing the performance of image classification through features automatically learned from depth-maps. - Object Detection on TPU Accelerated Embedded Devices. - Tackling Inter-Class Similarity and Intra-Class Variance for Microscopic Image-based Classification. - Semantic Interpretation. - Measuring the Sim2Real gap in 3D Object classification for different 3D data representation. - Spatially-Constrained Semantic Segmentation with Topological aps and Visual mbeddings. - Knowledge-enabled generation of semantically annotated image sequences of manipulation activities from VR demonstrations. - Make It Easier: An Empirical Simplification of a Deep 3D Segmentation Network for Human Body Parts. - Video and Motion Analysis. - Video Popularity Prediction through Fusing Early Viewership with Video Content. - Action Prediction during Human-Object Interaction based on DTW and Early Fusion of Human and Object Representations. - GridTrack: Detection and Tracking of Multiple Objects in Dynamic Occupancy Grids. - An Efficient Video Desnowing and Deraining Method with a Novel Variant Dataset. - Computer Vision Systems in Agriculture. - Robust Counting of Soft Fruit through Occlusions with Re-identification. - Non-destructive Soft Fruit Mass and Volume Estimation for Phenotyping in Horticulture. - Learning Image-based Contaminant Detection in Wool Fleece from Noisy Annotations. - Active Learning for Crop-Weed Discrimination by Image Classification from Convolutional Neural Network s Feature Pyramid Levels.