Alexander Kirillov

Ph.D. student

Technische Universität Dresden
Nöthnitzer Str. 46, 01187 Dresden
Room: APB-2030
Tel.: +49 (351) 463 43557
Email: alexander.kirillov at tu-dresden.de

Postal address:

Fakultät Informatik
Institut für Künstliche Intelligenz
Lehrstuhl Bildverarbeitung / Computer Vision
01062 Dresden

Publications

2017:

  • A. Kirillov, E. Levinkov, B. Andres, B. Savchynskyy, C. Rother
    InstanceCut: from Edges to Instances with MultiCut. [pdf]
    CVPR, 2017
  • F. Michel, A. Kirillov, E. Brachmann, A. Krull, S. Gumhold, B. Savchynskyy, C. Rother
    Global Hypothesis Generation for 6D Object Pose Estimation. [pdf]
    CVPR, 2017
  • E. Levinkov, J. Uhrig, S. Tang, M. Omran, E. Insafutdinov, A. Kirillov, C. Rother, T. Brox, B. Schiele, B. Andres
    Joint Graph Decomposition & Node Labeling: Problem, Algorithms, Applications. [pdf]
    CVPR, 2017

2016:

  • A. Kirillov, A. Shekhovtsov, C. Rother, B. Savchynskyy
    Joint M-Best-Diverse Labelings as a Parametric Submodular Minimization. [pdf][supplementary material]
    NIPS, 2016
  • A. Kirillov, D. Schlesinger, S. Zheng, B. Savchynskyy, P. Torr,  C. Rother
    Joint Training of Generic CNN-CRF Models with Stochastic Optimization. [pdf]
    ACCV, 2016
  • A. Kirillov, M. Gavrikov, E. Lobacheva, A. Osokin, D. Vetrov
    Deep Part-Based Generative Shape Model with Latent Variables. [pdf][supplementary material]
    BMVC, 2016

2015 and before:

  • A. Kirillov, D. Schlesinger, D. Vetrov,  C. Rother, B. Savchynskyy
    M-Best-Diverse Labelings for Submodular Energies and Beyond. [pdf with supplementary material][bib]
    NIPS 2015
  • A. Kirillov, B. Savchynskyy, D. Schlesinger, D. Vetrov,  C. Rother
    Inferring M-Best Diverse Labelings in a Single One. [pdf with supplementary material][bib][video spotlight]
    ICCV 2015
  • M. Figurnov, A. Kirillov
    Linear combination of random forests for the Relevance Prediction Challenge. [pdf]
    Workshop on Web Search Click Data, WSDM 2012

Talks

  • Tutorial: Diversity meets Deep Networks – Inference, Ensemble Learning, and Applications (CVPR 2016) [web-page]

Teaching