DAGM GCPR | 2021
DAGM German Conference on Pattern Recognition, Bonn
Machine Learning & Pattern Recognition and Computer Vision Nectar Track
14:15-15:00 Learning Decision Trees Recurrently Through Communication
Stephan Alaniz, Diego Marcos, Bernt Schiele, Zeynep Akata
HOPS: Probabilistic Subtree Mining for Small and Large Graphs
Pascal Welke, Florian Seiffarth, Michael Kamp, Stefan Wrobel
Graph Moving Object Segmentation
Jhony H. Giraldo, Sajid Javed, Thierry Bouwmans
Learning Graph Embeddings for Compositional Zero-shot Learning
Muhammad Ferjad Naeem, Yongqin Xian, Federico Tombari, Zeynep Akata
Lifted Disjoint Paths with Application in Multiple Object Tracking
Andrea Hornakova, Roberto Henschel, Bodo Rosenhahn, Paul Swoboda
Spatial-Temporal Transformer for Dynamic Scene Graph Generation
Yuren Cong, Wentong Liao, Hanno Ackermann, Bodo Rosenhahn, Michael Ying Yang
15:00-15:45
LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration
Bharat Lal Bhatnagar, Cristian Sminchisescu, Christian Theobalt, Gerard Pons-Moll
Self-Supervised 3D Human Pose Estimation with Multiple-View Geometry
Arij Bouazizi, Julian Wiederer, Ulrich Kressel, Vasileios Belagiannis
Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows
Tom Wehrbein, Marco Rudolph, Bodo Rosenhahn, Bastian Wandt
Real-Time Multi-View 3D Human Pose Estimation using Semantic Feedback to Smart Edge Sensors
Simon Bultmann, Sven Behnke
Human POSEitioning System: Human Pose Estimation and Self-Localization in Large Scenes from Body Mounted Sensors
Vladimir Guzov, Aymen Mir, Torsten Sattler, Gerard Pons-Moll
3D CNNs with Adaptive Temporal Feature Resolutions
Mohsen Fayyaz, Emad Bahrami, Ali Diba, Mehdi Noroozi, Ehsan Adeli, Luc Van Gool, Juergen Gall
15:45-16:30
Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images
Florian Kluger, Hanno Ackermann, Eric Brachmann, Michael Ying Yang, Bodo Rosenhahn
CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild
Bastian Wandt, Marco Rudolph, Petrissa Zell, Helge Rhodin, Bodo Rosenhahn
Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction
Bharat Lal Bhatnagar, Cristian Sminchisescu, Christian Theobalt, Gerard Pons-Moll
Distilling Audio-Visual Knowledge by Compositional Contrastive Learning
Uddeshya Upadhyay, Yanbei Chen, Tobias Hepp, Sergios Gatidis, Zeynep Akata
CoMIR: Contrastive Multimodal Image Representation for Registration
Nicolas Pielawski, Elisabeth Wetzer, Johan Öfverstedt, Jiahao Lu, Carolina Wählby, Joakim Lindblad, Nataša Sladoje
NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation
Angtian Wang, Adam Kortylewski, Alan Yuille
16:30-17:15
Long Short View Feature Decomposition via Contrastive Video Representation Learning
Nadine Behrmann, Mohsen Fayyaz, Juergen Gall, Mehdi Noroozi
Square Root Bundle Adjustment for Large-Scale Reconstruction
Nikolaus Demmel, Christiane Sommer, Daniel Cremers, Vladyslav Usenko
DeepFH Segmentations for Superpixel-based Object Proposal Refinement
Christian Wilms, Simone Frintrop
Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths
Andrea Hornakova, Timo Kaiser, Paul Swoboda, Michal Rolinek, Bodo Rosenhahn, Roberto Henschel
Open World Compositional Zero-Shot Learning
Massimiliano Mancini, Muhammad Ferjad Naeem, Yongqin Xian, Zeynep Akata
Reliable Fidelity and Diversity Metrics for Generative Models
Muhammad Ferjad Naeem, Seong Joon Oh, Youngjung Uh, Yunjey Choi, Jaejun Yoo
17:15-17:45
Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustness
Philipp Terhörst, Jan Niklas Kolf, Naser Damer, Florian Kirchbuchner, Arjan Kuijper
Uncertainty-Guided Progressive GANs for Medical Image Translation
Uddeshya Upadhyay, Yanbei Chen, Tobias Hepp, Sergios Gatidis, Zeynep Akata
Certification of Model Robustness in Active Class Selection
Mirko Bunse, Katharina Morik
Certifiably Adversarially Robust Detection of Out-of-Distribution Data
Julian Bitterwolf, Alexander Meinke, Matthias Hein