Hans Peter Graf

Department Head
Machine Learning

NEC Laboratories America, Inc.
4 Independence Way, Suite 200
Princeton, NJ  08540
Telephone: +1 609-951-4883
Fax: +1 609-951-2482
Email: hpg@nec-labs.com

Hans Peter Graf is head of the machine learning research department at NEC Laboratories America in Princeton. The department develops machine learning algorithms, as well as a range of applications in semantic text analysis, cognitive video interpretation and bio-medical analysis. His responsibilities include technology transfer to business units and the commercialization of research results. An example is the recently released e-Pathologist, a system assisting pathologists with the interpretation of histological samples, which contains key algorithms developed by the department.


  • Learning Higher-order Object Interactions for Keypoint-based Video Understanding

    SRVU - ICCV 2021 Workshop
    pp. 1-11, 2021

    Yi Huang, Asim Kadav, Farley Lai, Deep Patel, Hans Peter Graf
  • Hopper: Multi-hop Transformer for Spatio-Temporal Reasoning

    ICLR 2021
    pp. 1- 29, 2021

    Honglu Zhou, Asim Kadav, Farley Lai, Alexandru Niculescu-Mizil, Martin Renqiang Min, Mubbasir Kapadia, Hans Peter Graf
  • Tripping through time: Efficient Localization of Activities in Videos

    BMVC 2020
    pp. 1-14, 2020

    Meera Hahn, Asim Kadav, James M. Rehg, Hans Peter Graf
  • S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation

    CVPR 2020
    pp. 6537-6546, 2020

    Yizhe Zhu, Martin Renqiang Min, Asim Kadav, Hans Peter Graf
  • 15 Keypoints Is All You Need

    CVPR 2020
    pp. 6737-6747, 2020

    Michael Snower, Asim Kadav, Farley Lai, Hans Peter Graf

More Publications