Deep Learning for Semantic Scene Analysis

Scene understanding is a challenging topic in computer vision, robots and artificial intelligence. Given one or more images, we want to infer what type of scene is shown in the image, what objects are visible, and physical or contextual relations between the observed objects. 
Deep learning has transformed the field of computer vision, and now rivals human-level performance in tasks such as image recognition and object detection. We exploit convolutional neural networks (CNNs) for solving challenging scene interpretation task.



https://sites.google.com/site/michaelyingyang/deep-learning-for-scene-interpretation/sg_imag.jpg


Related Publications

Wentong Liao, Lin Shuai, Bodo Rosenhahn and Michael Ying Yang
Arxiv 1711.06032, 2017

Christoph Reinders, Hanno Ackermann, Michael Ying Yang and Bodo Rosenhahn. 
Arxiv 1709.05910, 2017

Michael Ying Yang, Wentong Liao, Hanno Ackermann, and Bodo Rosenhahn. 
ISPRS Journal of Photogrammetry and Remote Sensing, Elsevier, 131: 15-25, 2017 (Project link) (Code)

Florian Kluger, Hanno Ackermann, Michael Ying Yang, Bodo Rosenhahn.
Omid Hosseini, Oliver Groth, Alexander Kirillov, Michael Ying Yang and Carsten Rother. 
In International Conference on Robotics and Automation (ICRA), 2017 

Michael Ying Yang, Wentong Liao, Hanno Ackermann, and Bodo Rosenhahn. 
Arxiv 1609.05834, 2016

Siva Mustikovela, Michael Ying Yang, and Carsten Rother.
In ECCV Workshop on Video Segmentation, 2016

David Richmond, Dagmar Kainmueller, Michael Ying Yang, Gene Myers, and Carsten Rother.
In British Machine Vision Conference (BMVC), 2016

Alexander Krull, Eric Brachmann, Frank Michel, Michael Ying Yang, Stefan Gumhold, and Carsten Rother. 
In IEEE International Conference on Computer Vision (ICCV), 2015