Table of Contents

• Self-supervised Learning from Semantically Imprecise DataClemens-Alexander Brust, Björn Barz, Joachim Denzler. 27-35 [doi]
• Animal Fiber Identification under the Open Set ConditionOliver Rippel, Sergen Gülçelik, Khosrow Rahimi, Juliana Kurniadi, Andreas Herrmann, Dorit Merhof. 36-47 [doi]
• Who Did It? Identifying Foul Subjects and Objects in Broadcast Soccer VideosChunbo Song, Christopher Rasmussen. 48-54 [doi]
• CGT: Consistency Guided Training in Semi-Supervised LearningNesreen Hasan, Farzin Ghorban, Jörg Velten, Anton Kummert. 55-64 [doi]
• Unidentified Floating Object Detection in Maritime EnvironmentDarshan Venkatrayappa, Agnès Desolneux, Jean-Michel Hubert, Josselin Manceau. 65-74 [doi]
• Milking CowMask for Semi-supervised Image ClassificationGeoff French, Avital Oliver, Tim Salimans. 75-84 [doi]
• Anomaly Detection for Industrial Inspection using Convolutional Autoencoder and Deep Feature-based One-class ClassificationJamal Saeedi, Alessandro Giusti. 85-96 [doi]
• 3D Detection of Vehicles from 2D Images in Traffic SurveillanceMatthijs H. Zwemer, D. Scholte, Rob G. J. Wijnhoven, Peter H. N. de With. 97-106 [doi]
• Iterative 3D Deformable Registration from Single-view RGB Images using Differentiable RenderingArul Selvam Periyasamy, Max Schwarz, Sven Behnke. 107-116 [doi]
• SieveNet: Estimating the Particle Size Distribution of Kernel Fragments in Whole Plant Corn SilageChristoffer Bøgelund Rasmussen, Kristian Kirk, Thomas B. Moeslund. 117-124 [doi]
• GAN-based Face Mask Removal using Facial Landmarks and Pixel Errors in Masked RegionHitoshi Yoshihashi, Naoto Ienaga, Maki Sugimoto. 125-133 [doi]
• Fine-grained Action Recognition using Attribute VectorsSravani Yenduri, Nazil Perveen, Vishnu Chalavadi, C. Krishna Mohan. 134-143 [doi]
• Hear Me out: Fusional Approaches for Audio Augmented Temporal Action LocalizationAnurag Bagchi, Jazib Mahmood, Dolton Fernandes, Ravi Kiran Sarvadevabhatla. 144-154 [doi]
• SemSegDepth: A Combined Model for Semantic Segmentation and Depth CompletionJuan Pablo Lagos, Esa Rahtu. 155-165 [doi]
• On the Cross-dataset Generalization in License Plate RecognitionRayson Laroca, Everton V. Cardoso, Diego Rafael Lucio, Valter Estevam, David Menotti. 166-178 [doi]
• Leveraging Local Domains for Image-to-Image TranslationAnthony Dell'Eva, Fabio Pizzati, Massimo Bertozzi, Raoul de Charette. 179-189 [doi]
• CAM-SegNet: A Context-Aware Dense Material Segmentation Network for Sparsely Labelled DatasetsYuwen Heng, Yihong Wu, Srinandan Dasmahapatra, Hansung Kim. 190-201 [doi]
• The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and LocalizationPaul Bergmann, Xin Jin, David Sattlegger, Carsten Steger. 202-213 [doi]
• Improving the Sample-complexity of Deep Classification Networks with Invariant IntegrationMatthias Rath 0001, Alexandru Paul Condurache. 214-225 [doi]
• Segregational Soft Dynamic Time Warping and Its Application to Action PredictionVictoria Manousaki, Antonis A. Argyros. 226-235 [doi]
• Vehicle Pair Activity Classification using QTC and Long Short Term Memory Neural NetworkRahulan Radhakrishnan, Alaa AlZoubi. 236-247 [doi]
• ETL: Efficient Transfer Learning for Face TasksThrupthi Ann John, Isha Dua, Vineeth N. Balasubramanian, C. V. Jawahar. 248-257 [doi]
• Reinforced Damage Minimization in Critical Events for Self-driving VehiclesFrancesco Merola, Fabrizio Falchi, Claudio Gennaro, Marco Di Benedetto 0001. 258-266 [doi]
• Evolutional Normal Maps: 3D Face Representations for 2D-3D Face Recognition, Face Modelling and Data AugmentationMichael Danner, Thomas Weber, Patrik Huber 0001, Muhammad Awais 0001, Matthias Rätsch, Josef Kittler. 267-274 [doi]
• Bispectral Pedestrian Detection Augmented with Saliency Maps using TransformerMohamed Amine Marnissi, Ikram Hattab, Hajer Fradi, Anis Sahbani, Najoua Essoukri Ben Amara. 275-284 [doi]
• Weakly-supervised Localization of Multiple Objects in Images using Cosine LossBjörn Barz, Joachim Denzler. 287-296 [doi]
• DeepPupil Net: Deep Residual Network for Precise Pupil Center LocalizationNikolaos Poulopoulos, Emmanouil Z. Psarakis. 297-304 [doi]
• High Resolution Mask R-CNN-based Damage Detection on Titanium Nitride Coated Milling Tools for Condition Monitoring by using a New Illumination TechniqueMühenad Bilal, Sunil Kancharana, Christian Mayer, Daniel Pfaller, Leonid Koval, Markus Bregulla, Rafal Cupek, Adam Ziebinski. 305-314 [doi]
• Neural Network Pruning based on Filter Importance Values Approximated with Monte Carlo Gradient EstimationCsanád Sándor, Szabolcs Pável, Lehel Csató. 315-322 [doi]
• The MIS Check-Dam Dataset for Object Detection and Instance Segmentation TasksChintan Tundia, Rajiv Kumar, Om P. Damani, G. Sivakumar. 323-330 [doi]
• Oil Spill Detection and Visualization from UAV Images using Convolutional Neural NetworksValério Nogueira, Roberto J. M. Cavalcante, João A. G. R. Almeida, Tiago P. M. Fé, Ana C. M. Malhado, Thales Vieira, Krerley Oliveira. 331-338 [doi]
• Generating Proposals from Corners in RPN to Detect Bees in Dense ScenesYassine Kriouile, Corinne Ancourt, Katarzyna Wegrzyn-Wolska, Lamine Bougueroua. 339-350 [doi]
• Feature Extraction using Downsampling for Person Re-identification with Low-resolution ImagesMasashi Nishiyama, Takuya Endo, Yoshio Iwai. 351-358 [doi]
• Applying Center Loss to Multidimensional Feature Space in Deep Neural Networks for Open-set RecognitionDaiju Kanaoka, Yuichiro Tanaka, Hakaru Tamukoh. 359-365 [doi]
• Automated Human Movement Segmentation by Means of Human Pose Estimation in RGB-D Videos for Climbing Motion AnalysisRaul Beltrán Beltrán, Julia Richter, Ulrich Heinkel. 366-373 [doi]
• A General Two-branch Decoder Architecture for Improving Encoder-decoder Image Segmentation ModelsSijie Hu, Fabien Bonardi, Samia Bouchafa, Désiré Sidibé. 374-381 [doi]
• Automated Damage Inspection of Power Transmission Towers from UAV ImagesAleixo Cambeiro Barreiro, Clemens Seibold, Anna Hilsmann, Peter Eisert. 382-389 [doi]
• Monocular Estimation of Translation, Pose and 3D Shape on Detected Objects using a Convolutional AutoencoderIvar Persson, Martin Ahrnbom, Mikael G. Nilsson. 390-396 [doi]
• Tennis Strokes Recognition from Generated Stick Figure Video OverlaysBoris Bacic, Ishara Bandara. 397-404 [doi]
• PodNet: Ensemble-based Classification of Podocytopathy on Kidney Glomerular ImagesGeorge Oliveira Barros, David Campos Wanderley, Luciano Oliveira Rebouças, Washington L. C. dos-Santos, Angelo A. Duarte, Flavio de Barros Vidal. 405-412 [doi]
• Detecting Patches on Road Pavement Images Acquired with 3D Laser Sensors using Object Detection and Deep LearningSyed Ibrahim Hassan, Dympna O'Sullivan, Susan McKeever, David Power, Ray McGowan, Kieran Feighan. 413-420 [doi]
• Weakly Supervised Segmentation of Histopathology Images: An Insight in Feature Maps Ability for Learning Models InterpretationYanbo Feng, Adel Hafiane, Hélène Laurent. 421-427 [doi]
• Multitask Metamodel for Keypoint Visibility Prediction in Human Pose EstimationRomain Guesdon, Carlos Fernando Crispim Junior, Laure Tougne. 428-436 [doi]
• Evaluation of Long-term Deep Visual Place RecognitionFarid Alijani, Jukka Peltomäki, Jussi Puura, Heikki Huttunen, Joni-Kristian Kämäräinen, Esa Rahtu. 437-447 [doi]
• Human Activity Recognition: A Spatio-temporal Image Encoding of 3D Skeleton Data for Online Action DetectionNassim Mokhtari, Alexis Nédélec, Pierre De Loor. 448-455 [doi]
• Deep Set Conditioned Latent Representations for Action RecognitionAkash Singh, Tom De Schepper, Kevin Mets, Peter Hellinckx, José Oramas, Steven Latré. 456-466 [doi]
• Streamlining Action Recognition in Autonomous Shared Vehicles with an Audiovisual Cascade StrategyJoão Ribeiro Pinto, Pedro Carvalho, Carolina Pinto, Afonso Sousa, Leonardo Capozzi, Jaime S. Cardoso 0001. 467-474 [doi]
• Video-based Behavior Understanding of Children for Objective Diagnosis of AutismAbid Ali, Farhood Negin, Susanne Thümmler, François Brémond. 475-484 [doi]
• Buildings Extraction from Historical Topographic Maps via a Deep Convolution Neural NetworkChristos Xydas, Anastasios L. Kesidis, Kleomenis Kalogeropoulos, Andreas Tsatsaris. 485-492 [doi]
• Subclass-based Undersampling for Class-imbalanced Image ClassificationDaniel Lehmann 0005, Marc Ebner. 493-500 [doi]
• Multimodal Personality Recognition using Cross-attention Transformer and Behaviour EncodingTanay Agrawal, Dhruv Agarwal 0002, Michal Balazia, Neelabh Sinha, François Brémond. 501-508 [doi]
• Improving Semantic Image Segmentation via Label Fusion in Semantically Textured MeshesFlorian Fervers, Timo Breuer, Gregor Stachowiak, Sebastian Bullinger, Christoph Bodensteiner, Michael Arens. 509-516 [doi]
• Honeybee Re-identification in Video: New Datasets and Impact of Self-supervisionJeffrey Chan, Hector Carrión, Rémi Mégret, Jose L. Agosto-Rivera, Tugrul Giray. 517-525 [doi]
• Describing Image Focused in Cognitive and Visual Details for Visually Impaired People: An Approach to Generating Inclusive ParagraphsDaniel Louzada Fernandes, Marcos H. F. Ribeiro, Fabio Ribeiro Cerqueira, Michel Melo Silva. 526-534 [doi]
• Augmented Radar Points Connectivity based on Image Processing Techniques for Object Detection and ClassificationMohamed Sabry, Ahmed Hussein, Amr ElMougy, Slim Abdennadher. 535-542 [doi]
• Using Student Action Recognition to Enhance the Efficiency of Tele-educationEleni Dimitriadou, Andreas Lanitis. 543-549 [doi]
• TVNet: Temporal Voting Network for Action LocalizationHanyuan Wang, Dima Damen, Majid Mirmehdi, Toby Perrett. 550-558 [doi]
• HRI-Gestures: Gesture Recognition for Human-Robot InteractionAvgi Kollakidou, Frederik Haarslev, Çagatay Odabasi, Leon Bodenhagen, Norbert Krüger. 559-566 [doi]
• StructureNet: Deep Context Attention Learning for Structural Component RecognitionAkash Kaothalkar, Bappaditya Mandal, Niladri B. Puhan. 567-573 [doi]
• Pose Guided Feature Learning for 3D Object Tracking on RGB VideosMateusz Majcher, Bogdan Kwolek. 574-581 [doi]
• Fusion of Different Features by Cross Cooperative Learning for Semantic SegmentationRyota Ikedo, Kazuhiro Hotta. 582-589 [doi]
• Detecting Object States vs Detecting Objects: A New Dataset and a Quantitative Experimental StudyFilippos Gouidis, Theodore Patkos, Antonis A. Argyros, Dimitris Plexousakis. 590-600 [doi]
• Skeleton-based Online Sign Language Recognition using Monotonic AttentionNatsuki Takayama, Gibran Benitez-Garcia, Hiroki Takahashi. 601-608 [doi]
• Seeing the Differences in Artistry among Art Fields by using Multi-task LearningRyo Sato, Fumihiko Sakaue, Jun Sato. 609-616 [doi]
• Diversifying Image Synthesis using Data ClassificationYuta Suzuki, Fumihiko Sakaue, Jun Sato. 617-622 [doi]
• Combining Text and Image Knowledge with GANs for Zero-Shot Action Recognition in VideosKaiqiang Huang, Luis Miralles Pechuán, Susan McKeever. 623-631 [doi]
• Exploitation of Noisy Automatic Data Annotation and Its Application to Hand Posture ClassificationGeorgios Lydakis, Iason Oikonomidis, Dimitrios I. Kosmopoulos, Antonis A. Argyros. 632-641 [doi]
• Transfer Learning via Test-time Neural Networks AggregationBruno Casella, Alessio Barbaro Chisari, Sebastiano Battiato, Mario Valerio Giuffrida. 642-649 [doi]
• Evaluation of RGB and LiDAR Combination for Robust Place RecognitionFarid Alijani, Jukka Peltomäki, Jussi Puura, Heikki Huttunen, Joni-Kristian Kämäräinen, Esa Rahtu. 650-658 [doi]
• Using Contrastive Learning and Pseudolabels to Learn Representations for Retail Product Image ClassificationMuktabh Mayank Srivastava. 659-663 [doi]
• Don't Miss the Fine Print! An Enhanced Framework to Extract Text from Low Resolution ImagesPranay Dugar, Aditya Vikram, Anirban Chatterjee, Kunal Banerjee 0001, Vijay Agneeswaran. 664-671 [doi]
• Attention-based Gender Recognition on Masked FacesVincenzo Carletti, Antonio Greco, Alessia Saggese, Mario Vento. 672-678 [doi]
• Class-conditional Importance Weighting for Deep Learning with Noisy LabelsBhalaji Nagarajan, Ricardo Marques, Marcos Mejia, Petia Radeva. 679-686 [doi]
• MOD SLAM: Mixed Method for a More Robust SLAM without Loop ClosingThomas Belos, Pascal Monasse, Eva Dokládalová. 691-701 [doi]
• Event-based Extraction of Navigation Features from Unsupervised Learning of Optic Flow PatternsPaul Fricker, Tushar Chauhan, Christophe Hurter, Benoit R. Cottereau. 702-710 [doi]
• Scan2Part: Fine-grained and Hierarchical Part-level Understanding of Real-World 3D ScansAlexandr Notchenko, Vladislav Ishimtsev, Alexey Artemov, Vadim Selyutin, Emil Bogomolov, Evgeny Burnaev. 711-722 [doi]
• Classification Performance of RanSaC Algorithms with Automatic Threshold EstimationClément Riu, Vincent Nozick, Pascal Monasse, Joachim Dehais. 723-733 [doi]
• BRDF-based Irradiance Image Estimation to Remove Radiometric Differences for Stereo MatchingKebin Peng, John Quarles, Kevin Desai. 734-744 [doi]
• Combining Local and Global Pose Estimation for Precise Tracking of Similar ObjectsNiklas Gard, Anna Hilsmann, Peter Eisert. 745-756 [doi]
• Pushing the Efficiency of StereoNet: Exploiting Spatial SparsityGeorgios Zampokas, Christos-Savvas Bouganis, Dimitrios Tzovaras. 757-766 [doi]
• 3-D Tennis Ball Trajectory Estimation from Multi-view Videos and Its Parameterization by Parabola FittingKenta Sohara, Yasuyuki Sugaya. 769-776 [doi]
• Seg2Pose: Pose Estimations from Instance Segmentation Masks in One or Multiple Views for Traffic ApplicationsMartin Ahrnbom, Ivar Persson, Mikael G. Nilsson. 777-784 [doi]
• Motion-constrained Road User Tracking for Real-time Traffic AnalysisNyan Bo Bo, Peter Veelaert, Wilfried Philips. 785-792 [doi]
• 3D Object Reconstruction using Stationary RGB CameraJosé Guedes dos Santos Júnior, Gustavo C. R. Lima, Adam H. M. Pinto, Joao Paulo Silva do Monte Lima, Veronica Teichrieb, Jonysberg P. Quintino, Fabio Q. B. da Silva, André L. M. Santos, Helder Pinho. 793-800 [doi]
• Error Evaluation of Semantic VSLAM Algorithms for Smart FarmingAdam Kalisz, Mingjun Sun, Jonas Gedschold, Tim Erich Wegner, Giovanni Del Galdo, Jörn Thielecke. 801-810 [doi]
• Viewpoint-independent Single-view 3D Object Reconstruction using Reinforcement LearningSeiya Ito, Byeongjun Ju, Naoshi Kaneko, Kazuhiko Sumi. 811-819 [doi]
• Generalizable Online 3D Pedestrian Tracking with Multiple CamerasVictor Gouveia de M. Lyra, Isabella de Andrade, João Paulo Lima, Rafael Roberto, Lucas Figueiredo, João Marcelo X. N. Teixeira, Diego Thomas, Hideaki Uchiyama, Veronica Teichrieb. 820-827 [doi]
• LiMoSeg: Real-time Bird's Eye View based LiDAR Motion SegmentationSambit Mohapatra, Mona Hodaei, Senthil Kumar Yogamani, Stefan Milz, Heinrich Gotzig, Martin Simon, Hazem Rashed, Patrick Maeder. 828-835 [doi]
• Evaluating the Impact of Head Motion on Monocular Visual Odometry with Synthetic DataCharles Hamesse, Hiêp Quang Luong, Rob Haelterman. 836-843 [doi]
• An Occlusion Aware Five-view Stereo System and Its Application in Video Post-productionChangan Zhu, Taryn Laurendeau, Chris Joslin. 844-854 [doi]
• Human Pose Estimation through a Novel Multi-view SchemeJorge L. Charco, Ángel D. Sappa, Boris Xavier Vintimilla. 855-862 [doi]
• Visual Tilt Correction for Vehicle-mounted CamerasFiras Kastantin, Levente Hajder. 863-870 [doi]
• Semi-supervised Anomaly Detection for Weakly-annotated VideosKhaled El-Tahan, Marwan Torki. 871-878 [doi]