Table of Contents

• Sublabel-Accurate Multilabeling Meets Product Label SpacesZhenzhang Ye, Bjoern Haefner, Yvain Quéau, Thomas Möllenhoff, Daniel Cremers. 3-17 [doi]
• InfoSeg: Unsupervised Semantic Image Segmentation with Mutual Information MaximizationRobert Harb, Patrick Knöbelreiter. 18-32 [doi]
• Sampling-Free Variational Inference for Neural Networks with Multiplicative Activation NoiseJannik Schmitt, Stefan Roth 0001. 33-47 [doi]
• Conditional Adversarial Debiasing: Towards Learning Unbiased Classifiers from Biased DataChristian Reimers, Paul Bodesheim, Jakob Runge, Joachim Denzler. 48-62 [doi]
• Revisiting Consistency Regularization for Semi-supervised LearningYue Fan, Anna Kukleva, Bernt Schiele. 63-78 [doi]
• Learning Robust Models Using the Principle of Independent Causal MechanismsJens Müller, Robert Schmier, Lynton Ardizzone, Carsten Rother, Ullrich Köthe. 79-110 [doi]
• Reintroducing Straight-Through Estimators as Principled Methods for Stochastic Binary NetworksAlexander Shekhovtsov, Viktor Yanush. 111-126 [doi]
• Bias-Variance Tradeoffs in Single-Sample Binary Gradient EstimatorsAlexander Shekhovtsov. 127-141 [doi]
• End-to-End Learning of Fisher Vector Encodings for Part Features in Fine-Grained RecognitionDimitri Korsch, Paul Bodesheim, Joachim Denzler. 142-158 [doi]
• Investigating the Consistency of Uncertainty Sampling in Deep Active LearningNiklas Penzel, Christian Reimers, Clemens-Alexander Brust, Joachim Denzler. 159-173 [doi]
• ScaleNet: An Unsupervised Representation Learning Method for Limited InformationHuili Huang, M. Mahdi Roozbahani. 174-188 [doi]
• A New Split for Evaluating True Zero-Shot Action RecognitionShreyank N. Gowda, Laura Sevilla-Lara, Kiyoon Kim, Frank Keller, Marcus Rohrbach. 191-205 [doi]
• Video Instance Segmentation with Recurrent Graph Neural NetworksJoakim Johnander, Emil Brissman, Martin Danelljan, Michael Felsberg. 206-221 [doi]
• Distractor-Aware Video Object SegmentationAndreas Robinson, Abdelrahman Eldesokey, Michael Felsberg. 222-234 [doi]
• 2Net for Generalized Zero-Label Semantic SegmentationAnurag Das, Yongqin Xian, Yang He 0005, Bernt Schiele, Zeynep Akata. 235-249 [doi]
• Contrastive Representation Learning for Hand Shape EstimationChristian Zimmermann 0001, Max Argus, Thomas Brox. 250-264 [doi]
• Fusion-GCN: Multimodal Action Recognition Using Graph Convolutional NetworksMichael Duhme, Raphael Memmesheimer, Dietrich Paulus. 265-281 [doi]
• FIFA: Fast Inference Approximation for Action SegmentationYaser Souri, Yazan Abu Farha, Fabien Despinoy, Gianpiero Francesca, Juergen Gall. 282-296 [doi]
• Hybrid SNN-ANN: Energy-Efficient Classification and Object Detection for Event-Based VisionAlexander Kugele, Thomas Pfeil, Michael Pfeiffer 0001, Elisabetta Chicca. 297-312 [doi]
• A Comparative Study of PnP and Learning Approaches to Super-Resolution in a Real-World SettingSamim Zahoor Taray, Sunil Prasad Jaiswal, Shivam Sharma, Noshaba Cheema, Klaus Illgner-Fehns, Philipp Slusallek, Ivo Ihrke. 313-327 [doi]
• Merging-ISP: Multi-exposure High Dynamic Range Image Signal ProcessingPrashant Chaudhari, Franziska Schirrmacher, Andreas Maier 0001, Christian Riess, Thomas Köhler 0004. 328-342 [doi]
• Spatiotemporal Outdoor Lighting Aggregation on Image SequencesHaebom Lee, Robert Herzog, Jan Rexilius, Carsten Rother. 343-357 [doi]
• AttrLostGAN: Attribute Controlled Image Synthesis from Reconfigurable Layout and StyleStanislav Frolov, Avneesh Sharma, Jörn Hees, Tushar Karayil, Federico Raue, Andreas Dengel 0001. 361-375 [doi]
• Learning Conditional Invariance Through Cycle ConsistencyMaxim Samarin, Vitali Nesterov, Mario Wieser, Aleksander Wieczorek, Sonali Parbhoo, Volker Roth 0001. 376-391 [doi]
• CAGAN: Text-To-Image Generation with Combined Attention Generative Adversarial NetworksHenning Schulze, Dogucan Yaman, Alexander H. Waibel. 392-404 [doi]
• TxT: Crossmodal End-to-End Learning with TransformersJan-Martin O. Steitz, Jonas Pfeiffer, Iryna Gurevych, Stefan Roth 0001. 405-420 [doi]
• Diverse Image Captioning with Grounded StyleFranz Klein, Shweta Mahajan, Stefan Roth 0001. 421-436 [doi]
• Leveraging Group Annotations in Object Detection Using Graph-Based Pseudo-labelingDaniel Pototzky, Matthias Kirschner, Lars Schmidt-Thieme. 439-452 [doi]
• Quantifying Uncertainty of Image Labelings Using Assignment FlowsDaniel Gonzalez-Alvarado, Alexander Zeilmann, Christoph Schnörr. 453-466 [doi]
• Implicit and Explicit Attention for Zero-Shot LearningFaisal Alamri, Anjan Dutta 0001. 467-483 [doi]
• Self-supervised Learning for Object Detection in Autonomous DrivingDaniel Pototzky, Azhar Sultan, Matthias Kirschner, Lars Schmidt-Thieme. 484-497 [doi]
• Assignment Flows and Nonlocal PDEs on GraphsDmitrij Sitenko, Bastian Boll, Christoph Schnörr. 498-512 [doi]
• Viewpoint-Tolerant Semantic Segmentation for Aerial LogisticsShiming Wang, Fabiola Maffra, Ruben Mascaro, Lucas Teixeira, Margarita Chli. 515-529 [doi]
• T6D-Direct: Transformers for Multi-object 6D Pose Direct RegressionArash Amini, Arul Selvam Periyasamy, Sven Behnke. 530-544 [doi]
• TetraPackNet: Four-Corner-Based Object Detection in Logistics Use-CasesLaura Dörr, Felix Brandt 0002, Alexander Naumann, Martin Pouls. 545-558 [doi]
• Detecting Slag Formations with Deep Convolutional Neural NetworksChristian von Koch, William Anzén, Max Fischer, Raazesh Sainudiin. 559-573 [doi]
• Virtual Temporal Samples for Recurrent Neural Networks: Applied to Semantic Segmentation in AgricultureAlireza Ahmadi, Michael Halstead, Chris McCool. 574-588 [doi]
• Weakly Supervised Segmentation Pretraining for Plant Cover PredictionMatthias Körschens, Paul Bodesheim, Christine Römermann, Solveig Franziska Bucher, Mirco Migliavacca, Josephine Ulrich, Joachim Denzler. 589-603 [doi]
• How Reliable Are Out-of-Distribution Generalization Methods for Medical Image Segmentation?Antoine Sanner, Camila González, Anirban Mukhopadhyay 0003. 604-617 [doi]
• Clustering Persistent Scatterer Points Based on a Hybrid Distance MetricPhilipp J. Schneider, Uwe Soergel. 621-632 [doi]
• CATEGORISE: An Automated Framework for Utilizing the Workforce of the Crowd for Semantic Segmentation of 3D Point CloudsMichael Kölle, Volker Walter 0001, Ivan Shiller, Uwe Soergel. 633-648 [doi]
• Zero-Shot Remote Sensing Image Super-Resolution Based on Image Continuity and Self TessellationsRupak Bose, Vikrant Rangnekar, Biplab Banerjee, Subhasis Chaudhuri. 649-662 [doi]
• A Comparative Survey of Geometric Light Source Calibration MethodsMariya Kaisheva, Volker Rodehorst. 663-680 [doi]
• Quantifying Point Cloud Realism Through Adversarially Learned Latent RepresentationsLarissa T. Triess, David Peter, Stefan A. Baur, J. Marius Zöllner. 681-696 [doi]
• Full-Glow: Fully Conditional Glow for More Realistic Image GenerationMoein Sorkhei, Gustav Eje Henter, Hedvig Kjellström. 697-711 [doi]
• Multidirectional Conjugate Gradients for Scalable Bundle AdjustmentSimon Weber, Nikolaus Demmel, Daniel Cremers. 712-724 [doi]