Prof. Dr. Laura Leal-Taixé



Academic Career and Research Areas

Prof. Dr.-Ing. Laura Leal-Taixé (b. 1984) conducts research in the area of Computer Vision and Machine Learning. In particular, she focuses on video analysis and solving tasks, such as multiple object tracking, motion analysis or semantic segmentation. Allowing machines to automatically analyze video data is essential for applications, such as Autonomous Driving. In the project socialMaps, for which she has been granted a Sofja Kovalevskaja Award, she proposes to include dynamic and social information into static maps, in an effort to decouple vehicle traffic from pedestrian traffic.
Prof. Leal-Taixé was born in Barcelona, where she earned her B.Sc. and M.Sc. in Telecommunications Engineering at the Technical University of Catalonia (UPC). From 2009 to 2013, she conducted her doctoral research at the Institute for Information Processing (TNT) of the Leibniz University of Hannover in Germany. While pursuing her doctorate, she spent a year as a visiting scholar at the University of Michigan, Ann Arbor, USA, working with Prof. Silvio Savarese. She then spent two years as a postdoctoral researcher at the Institute for Geodesy and Photogrammetry at ETH Zürich, Switzerland, working on tracking and benchmarking. In February 2018, she became a Rudolf Mossbauer Tenure Track Professor for Dynamic Vision and Learning.


  • Google Faculty Award (2020)
  • Sofja Kovalevskaja Award, Humboldt Foundation (2017)
  • DAAD Funding, Australia-German Joint Research Corporation Scheme (2017)
  • Travel grant awarded by the Women in Computer Vision Association at CVPR (2016)
  • Travel grant awarded for the Doctoral Consortium at CVPR (2013)

The Center of Attention: Center-Keypoint Grouping Attention for Multi-Person Pose Estimation. Guillem Braso, Nikita Kister, and Laura Leal-Taixe. International Conference on Computer Vision (ICCV), 2021.


Learning Intra-Batch Connections for Deep Metric Learning. Jenny Seidenschwarz, Ismail Elezi, and Laura Leal-Taixe. International Conference on Machine Learning (ICML), 2021.


Patch2Pix: Epipolar-Guided Pixel-Level Correspondences. Qunjie Zhou, Torsten Sattler, and Laura Leal-Taixe. Conference on Computer Vision and Pattern Recognition (CVPR), 2021.


Guillem Braso and Laura Leal-Taixé. Learning a neural solver for multiple object tracking. Conference on Computer Vision and Pattern Recognition (CVPR), 2020.


Maxim Maximov, Ismail Elezi, and Laura Leal-Taixé. CIAGAN: Conditional identity anonymizationgenerative adversarial networks. Conference on Computer Vision and Pattern Recogni- tion (CVPR), 2020.