Program

The conference will be held from September 28 to October 1, 2021. On September 28, there will be a tutorial on Geometric Deep Learning, a workshop on Scene Understanding in Unstructured Environments, and two Nectar Tracks for Machine Learning and Pattern Recognition. The Nectar Tracks offer the opportunity to present and discuss the latest works that have been published at top-tier machine learning or pattern recognition conferences and journals. The special session on Unsolved Problems in Pattern Recognition on September 29 provides a unique venue for discussing the major challenges of pattern recognition in the next years. The event is an opportunity to take a step back from the daily business and debate about the currently most relevant problems in the field and emphasize the most promising future research directions.

Tuesday, 28.09.

Nectar Tracks 14:00 - 17:50

Workshop on Scene Understanding in Unstructured Environments 14:00 - 18:15

Tutorial on Geometric Deep Learning 15:00 - 17:45

Wednesday, 29.09.

Welcome to Special Session on Unsolved Problems in Pattern Recognition 08:45 - 09:00

Can the outputs of deep nets be used as a posteriori probabilities in fine-grained recognition? Jiri Matas 09:00 - 10:15

Open problems in multi-object tracking Laura Leal-Taixé 10:15 - 11:00

Algorithm validation and the essence of data science Joachim M. Buhmann 11:00 - 11:45

Automatic recognition of patterns prior to machine learning - Robots perceiving the exceptional Eckart Michaelsen 11:45 - 12:30

Lunch Break 12:30 - 13:45

On the prospects and limitations of synthetic data augmentation with GANs Anna Khoreva 13:45 - 14:30

The 3rd wave of AI - combining symbolic and statistical methods Kristian Kersting 14:30 - 15:15

Generative models: can they work? Thomas Brox 15:15 - 16:00

Learning shading and lighting without ground truth David Forsyth 16:00 - 17:15

Wrap-up 17:15 - 17:30

DAGM Assembly 17:30 - 19:00

Thursday, 30.09.

Welcome 08:45 - 09:00

DAGM Awards 09:00 - 09:20

Visual Recognition with Minimal Supervision and Explainability Zeynep Akata 09:20 - 10:00

Computational Photography and Lighting 10:00 - 11:00

Vision Systems and Applications 11:00 - 12:00

Lunch Break 12:00 - 13:00

Machine Learning and Optimization 13:00 - 14:00

Machine Learning 14:00 - 15:00

Break 15:00 - 15:15

Action Recognition and Video Understanding 15:15 - 16:15

Actions, Events, and Segmentation 16:15 - 17:15

Pattern Recognition in the Life- and Natural Sciences 17:15 - 17:55

Sights, sounds, and space: Audio-visual learning in 3D environments Kristen Grauman 18:00 - 19:00

Friday, 1.10.

Learning from Logged Action Data Thorsten Joachims 09:00 - 10:00

Machine Learning 10:00 - 11:00

Generative Models and Multimodal Data 11:00 - 12:00

Lunch Break 12:00 - 13:00

Photogrammetry and Remote Sensing 13:00 - 14:00

3D Modeling and Reconstruction 14:00 - 15:00

Break 15:00 - 15:15

Labeling and Self-Supervised Learning 15:15 - 16:15

Best Paper Awards 16:15 - 16:45