Direkt zum Inhalt springen
Computer Vision Group
Faculty of Informatics
Technical University of Munich

Technical University of Munich

Menu
Home Members Philip Häusser

Philip Häusser

Philip Häusser

PhD Student

Technische Universität München

Department of Computer Science
Informatik 9
Boltzmannstrasse 3
85748 Garching
Germany

Tel: +49-89-289-17788
Fax: +49-89-289-17757
Office: 02.09.041
Mail: haeusser@cs.tum.edu

About

I'm a third-year PhD student in computer science at TUM, doing research in computer vision and machine learning (colloquially known as “artificial intelligence”) advised by Prof. Daniel Cremers.

I hold a Master's degree in physics from the University of California, Santa Cruz (USA) and a Bachelor's degree in physics from the LMU Munich where I was working at the cavity quantum optics group headed by Prof. T.W. Haensch.

When I'm not in the lab you might find me playing squash or volleyball or you might encounter one of my TV productions.

I will be on leave from May 2017 – September 2017 for an internship at Google..

More about my research at Google can be found here.

Deep learning projects

  • Optical flow estimation (coop with Freiburg; ICCV paper 2015)
  • Scene flow estimation (coop with Freiburg; CVPR paper 2016)
  • Facial expression recognition (student project)
  • Mathematical handwriting recognition (Bachelor thesis)
  • Video frame prediction (Master's thesis)
  • Construction zone recognition for self-driving cars (Master's thesis)
  • Semi-supervised training “learning by association” (Google internship 2016; CVPR paper 2017)
  • Domain adaptation with neural networks

Teaching

Summer Term 2015

Summer Term 2016

Winter Term 2016/17

Publications

Conference and Workshop Papers
2017
Associative Domain Adaptation (P. Haeusser, T. Frerix, A. Mordvintsev, D. Cremers), In IEEE International Conference on Computer Vision (ICCV), 2017. ([code]) [bib] [pdf]
Better Text Understanding Through Image-To-Text Transfer (K. Kurach, S. Gelly, M. Jastrzebski, P. Haeusser, O. Teytaud, D. Vincent, O. Bousquet), In arxiv:1705.08386, 2017. [bib] [pdf]
Learning by Association - A versatile semi-supervised training method for neural networks (P. Haeusser, A. Mordvintsev, D. Cremers), In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. ([code]) [bib] [pdf]
2016
A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation (N.Mayer, E.Ilg, P.Haeusser, P.Fischer, D.Cremers, A.Dosovitskiy, T.Brox), In IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2016. (arXiv:1512.02134) [bib] [pdf]
2015
FlowNet: Learning Optical Flow with Convolutional Networks (A. Dosovitskiy, P. Fischer, E. Ilg, P. Haeusser, C. Hazirbas, V. Golkov, P. van der Smagt, D. Cremers, T. Brox), In IEEE International Conference on Computer Vision (ICCV), 2015. ([video],[code]) [bib] [pdf] [doi]
Powered by bibtexbrowser
Export as PDF or BIB

Talks

  • Challenges in Dynamic Imaging Data, June 9th 2015, Cambridge University slides video
  • Deep Learning and Convolutional Networks, July 9th 2015, University of Augsburg
  • Kuenstliche Intelligenz und Digitalisierung, April 8th, 2017, Akademie fuer politische Bildung, Tutzing

Connect

Feel free to connect via

Rechte Seite

Informatik IX
Chair for Computer Vision & Artificial Intelligence

Boltzmannstrasse 3
85748 Garching

info@vision.in.tum.de