11. Oktober 2018 |

Siyu Tang receives DAGM MVTec 2018 Dissertation Award

The German Association for Pattern Recognition praises her work to be “outstanding”

Tübingen – Dr. Siyu Tang received the DAGM MVTec 2018 Dissertation Award at the German Conference on Pattern Recognition (GCPR) conference in Stuttgart today. Her thesis with the title “People Detection and Tracking in Crowded Scenes” was praised by the board and the technical committee of the DAGM (Deutsche Arbeitsgemeinschaft für Mustererkennung) to be outstanding. “There was quite some competition this year”, said Reinhard Koch, the President of DAGM, which can be translated as German Association for Pattern Recognition. “This year we even decided to double the award money and grant two first places. Mrs. Tang will receive one of both. Congratulations for this achievement!” The award comes with a price money of 2.500 Euro and was given during the DAGM Award ceremony on Wednesday afternoon.

Tang leads the Holistic Vision Group in the Perceiving Systems Department at the Max Planck Institute for Intelligent Systems (MPI-IS) in Tübingen. Her research is at the intersection between Computer Vision and Machine Learning with a focus on holistic visual scene understanding. In particular, she and her team are interested in analyzing and modeling people in complex visual scenes. “Winning the dissertation award means a lot to me, as it recognizes the contribution, impact and hard work that went into my PhD thesis,” Tang says and explains further what her thesis is about: “It has been a long-standing goal in Computer Vision to develop methods aiming at analyzing humans in visual data. Due to the complexity of real-world scenes, visual understanding of people remains challenging for machine perception. In my thesis I focus on advancing the Computer Vision techniques for people detection, tracking and pose estimation in crowded street scenes. I propose several novel ideas and rigorous mathematical formulations, push the boundary of the state-of- the-art which resulted in superior performance.”

The work presented in the thesis wasn´t considered outstanding for the first time: it has received several prizes, including the best paper award at BMVC 2012, the winner of the multi-object tracking challenge at the MOT workshop, ECCV 2016 and the winner of the multi-object tracking challenge at the MOT workshop CVPR 2017.

Tang received an early career research grant to start her own research group at the Max Planck Institute for Intelligent Systems in April 2018. She moved to Tübingen in February 2017 to work with Michael Black, who heads the Perceiving System Department at the MPI-IS. She finished her PhD at the Max Planck Institute for Informatics in 2017, under the supervision of Professor Bernt Schiele. Before that, Tang received her Master’s degree in Computer Science at RWTH Aachen University, advised by Prof. Bastian Leibe and her Bachelor degree in Computer Science and Technology Department at Zhejiang University, China. She was a research intern at the National Institute of Informatics, under the supervision of Prof. Helmut Prendinger.

The DAGM e.V. has been awarding the DAGM MVTec Dissertation Award since 2015. The Dissertation Award honors an outstanding dissertation in the fields of pattern recognition, image processing, machine vision and machine learning, which was successfully completed the year before.

Find out more here: https://www.dagm.de/award-winners/dagm-mvtec-dissertation-award

The German Conference on Pattern Recognition (GCPR) is the annual symposium of the German Association for Pattern Recognition (DAGM). It is the national venue for recent advances in image processing, pattern recognition, and computer vision and it follows the long tradition of the DAGM conference series, which has been renamed to GCPR in 2013 to reflect its increasing internationalization. In 2018 in Stuttgart, the conference series will celebrate its 40th anniversary.

Find out more here: https://conferences.mpi-inf.mpg.de/dagm/2018/