Abstract is missing.
- Thermal Image Super-Resolution Using Second-Order Channel Attention with Varying Receptive FieldsNolan B. Gutierrez, William J. Beksi. 3-13 [doi]
- MARL: Multimodal Attentional Representation Learning for Disease PredictionAli Hamdi, Amr Aboeleneen, Khaled B. Shaban. 14-27 [doi]
- Object Localization with Attribute Preference Based on Top-Down AttentionSoubarna Banik, Mikko Lauri, Alois C. Knoll, Simone Frintrop. 28-40 [doi]
- See the Silence: Improving Visual-Only Voice Activity Detection by Optical Flow and RGB FusionDanu Caus, Guillaume Carbajal, Timo Gerkmann, Simone Frintrop. 41-51 [doi]
- Score to Learn: A Comparative Analysis of Scoring Functions for Active Learning in RoboticsRiccardo Grigoletto, Elisa Maiettini, Lorenzo Natale. 55-67 [doi]
- Enhancing the Performance of Image Classification Through Features Automatically Learned from Depth-MapsGeorge Ciubotariu, Vlad-Ioan Tomescu, Gabriela Czibula. 68-81 [doi]
- Object Detection on TPU Accelerated Embedded DevicesBertalan Kovács, Anders D. Henriksen, Jonathan Dyssel Stets, Lazaros Nalpantidis. 82-92 [doi]
- Tackling Inter-class Similarity and Intra-class Variance for Microscopic Image-Based ClassificationAishwarya Venkataramanan, Martin Laviale, Cécile Figus, Philippe Usseglio-Polatera, Cédric Pradalier. 93-103 [doi]
- Measuring the Sim2Real Gap in 3D Object Classification for Different 3D Data RepresentationJean-Baptiste Weibel, Rainer Rohrböck, Markus Vincze. 107-116 [doi]
- Spatially-Constrained Semantic Segmentation with Topological Maps and Visual EmbeddingsChristina Theodoridou, Andreas Kargakos, Ioannis Kostavelis, Dimitrios Giakoumis, Dimitrios Tzovaras. 117-129 [doi]
- Knowledge-Enabled Generation of Semantically Annotated Image Sequences of Manipulation Activities from VR DemonstrationsAndrei Haidu, Xiaoyue Zhang, Michael Beetz. 130-143 [doi]
- Make It Easier: An Empirical Simplification of a Deep 3D Segmentation Network for Human Body PartsMatteo Terreran, Daniele Evangelista, Jacopo Lazzaro, Alberto Pretto. 144-156 [doi]
- Video Popularity Prediction Through Fusing Early Viewership with Video ContentAlexandros Vrochidis, Nikolaos Dimitriou, Stelios Krinidis, Savvas Panagiotidis, Stathis Parcharidis, Dimitrios Tzovaras. 159-168 [doi]
- Action Prediction During Human-Object Interaction Based on DTW and Early Fusion of Human and Object RepresentationsVictoria Manousaki, Konstantinos E. Papoutsakis, Antonis A. Argyros. 169-179 [doi]
- GridTrack: Detection and Tracking of Multiple Objects in Dynamic Occupancy GridsÖzgür Erkent, David Sierra González, Anshul Paigwar, Christian Laugier. 180-194 [doi]
- An Efficient Video Desnowing and Deraining Method with a Novel Variant DatasetArezoo Sadeghzadeh, Md Baharul Islam, Reza Zaker. 195-208 [doi]
- Robust Counting of Soft Fruit Through Occlusions with Re-identificationRaymond Kirk, Michael Mangan, Grzegorz Cielniak. 211-222 [doi]
- Non-destructive Soft Fruit Mass and Volume Estimation for Phenotyping in HorticultureRaymond Kirk, Michael Mangan, Grzegorz Cielniak. 223-233 [doi]
- Learning Image-Based Contaminant Detection in Wool Fleece from Noisy AnnotationsTimothy Patten, Alen Alempijevic, Robert Fitch. 234-244 [doi]
- Active Learning for Crop-Weed Discrimination by Image Classification from Convolutional Neural Network's Feature Pyramid LevelsUsman A. Zahidi, Grzegorz Cielniak. 245-257 [doi]