Wentong Liao, M.Sc.
Leibniz Universität Hannover
Institut für Informationsverarbeitung
Appelstr. 9A
30167 Hannover
phone: +49 511 762-5312
fax: +49 511 762-5333
office location: room 1302

Wentong Liao graduated with a Bachelor's degree in Communication Engineering from Xidian University, China, in 2011. He furthered his studied at Leibniz Universität Hannover with a focus on signal processing and communication techniques and received his Master's degree in summer 2015. After graduation he joined Institut für Informationsverarbeitung at Leibniz Universität Hannover where he currently pursues a PhD. He is co-supervised by Prof. Bodo Rosenhahn and Assistant Prof. Michael Ying Yang from ITC, University of Twente. From Feb. 1st till Nov. 30rd 2018, he works with Dr. Zeng and Dr. Lan as an intern at Microsoft Research Asia (MSRA).

Show selected publications only
  • Yuren Cong, Hanno Ackermann, Wentong Liao, Michael Ying Yang, Bodo Rosenhahn
    NODIS: Neural Ordinary Differential Scene Understanding
    European Conference on Computer Vision (ECCV), August 2020
  • Tongxin Hu, Wentong Liao, Michael Ying Yang, Bodo Rosenhahn
    Exploiting Attention for Visual Relationship Detection
    41th German Conference on Pattern Recognition, Dortmund, Germany, September 2019
  • Michael Ying Yang, Wentong Liao, Xinbo Li, Yanpeng Cao, Bodo Rosenhahn
    Vehicle Detection in Aerial Images
    Photogrammetric Engineering & Remote Sensing, 2019
  • Michael Ying Yang, Wentong Liao, Yanpeng Cao, Bodo Rosenhahn
    Video event recognition and anomaly detection by combining gaussian process and hierarchical dirichlet process models
    Photogrammetric Engineering & Remote Sensing, 2018
  • Michael Ying Yang, Wentong Liao, Xinbo Li, Bodo Rosenhahn
    Deep Learning for Vehicle Detection in Aerial Images
    IEEE International Conference on Image Processing (ICIP), 2018
  • Michael Ying Yang, Wentong Liao, Hanno Ackermann, Bodo Rosenhahn
    On support relations and semantic scene graphs
    ISPRS Journal of Photogrammetry and Remote Sensing, Elsevier, Vol. 131, pp. 15-25, July 2017
  • Wentong Liao, Chun Yang, Michael Ying Yang, Bodo Rosenhahn
    Security Event Recognition for Visual Surveillance
    ISPRS Annals of Photogrammetry, Remote Sensing \& Spatial Information Sciences, Vol. 4, June 2017
  • Wentong Liao, Michael Ying Yang, Ni Zhan, Bodo Rosenhahn
    Triplet-based Deep Similarity Learning for Person Re-Identification
    In ICCV Workshop on Multi-Sensor Fusion for Dynamic Scene Understanding, 2017
  • Wentong Liao, Lin Shuai, Bodo Rosenhahn, Michael Ying Yang
    Natural Language Guided Visual Relationship Detection
    Arxiv 1711.06032, 2017
  • Michael Ying Yang, Wentong Liao, Hanno Ackermann, Bodo Rosenhahn
    On Support Relations and Semantic Scene Graphs
    arXiv, CUL, 2016
  • Wentong Liao, Yang Michael, Bodo Rosenhahn
    Video Event Recognition by Combining HDP and Gaussian Process
    IEEE International Conference on Computer Vision (ICCV) Workshop, pp. 19-27, Santiago, Chile, December 2015
  • Michael Yang, Matthias Reso, Jun Tang, Wentong Liao, Bodo Rosenhahn
    Temporally Object-based Video Co-Segmentation
    Advances in Visual Computing, The final publication is available at link.springer.com, Springer-Verlag, Las Vegas, NV, USA, December 2015
  • Wentong Liao, Bodo Rosenhahn, Yang Michael
    Gaussian Process for Activity Modeling and Anomaly Detection
    International Society for Photogrammetry and Remote Sensing ISA workshop, La Grande Motte, France, September 2015
  • Michael Yang, Wentong Liao, Bodo Rosenhahn, Zheng Zhang
    Hyperspectral Image Classification Using Gaussian Process Models
    International Geoscience and Remote Sensing Symposium (IGARSS), Milan, Italy, IEEE Xplore Digital Library, July 2015
  • Wentong Liao, Jun Tang, Bodo Rosenhahn, Micheal Ying Yang
    Integration of Gaussian Process and MRF for Hyperspectral Image Classification
    Joint Urban Remote Sensing Event, IEEE, March 2015
Other activities

If you would like to have Student-/Bachelor-/Masterarbeit in the filed of

with me is welcome to contact.