Josephine Sullivan

Phone (office):+46 8 790 6136
Email : sullivan at nada.kth.se
Address : KTH, CSC/CVAP, S-100 44 Stockholm, Sweden.

My research efforts are devoted to the field of computer vision. In particular, I've investigated aspects of visual tracking, human/object pose recognition and multi-target tracking.

Currently, I am a post-doctoral researcher at the CVAP group in the School of Computer Science and Communication (CSC) at KTH, the Royal Institute of Technology, Stockholm, Sweden.

Publications

Here are most of my publications in chronological order:

  • Face Alignment with Part-Based Modeling
    V. Kazemi, J. Sullivan and S. Carlsson,
    In Proc. IEEE British Machine Vision Conference (BMVC 2011), Dundee, Scotland, Sept 2011.
    (coming soon)
  • Novelty Detection from an Ego-Centric Perspective
    O. Aghazadeh, J. Sullivan and S. Carlsson,
    In Proc. IEEE Computer Vision and Pattern recognition (CVPR 2011), Colorado Springs, June 2011.
    (PDF 12MB)

  • Human 3D Motion Computation from a Varying Number of Cameras
    M. Burenius, J. Sullivan, S. Carlsson and K. Halvorsen,
    In Proc. IEEE Scandinavian Conference on Image Analysis (SCIA 2011), Ystad, Sweden, May 2011.
    (PDF)

  • Automatic Learning and Extraction of Multi-Local Features
    O. Danielsson, S. Carlsson and J. Sullivan,
    In Proc. IEEE International Conference on Computer Vision (ICCV 2009), Kyoto, Japan, 2009
    (PDF 9.7MB)

  • Shading Models for Illumination and Reflectance Invariant Shape Detectors
    P. Nillius, J. Sullivan and A. Antonis,
    In Proc. IEEE Computer Vision and Pattern recognition (CVPR 2008), Anchorage, June 2008
    (PDF 2.2MB)

  • Multi-Target Tracking -- Linking Identities using Bayesian Network Inference
    P. Nillius, J. Sullivan and S. Carlsson,
    In Proc. IEEE Computer Vision and Pattern Recognition (CVPR 2006), New York City, June 2006
    (PDF 0.5MB)

  • Tracking and Labelling of Interacting Multiple Targets
    J. Sullivan and S. Carlsson,
    In Proc. 9th European Conf. on Computer Vision (ECCV 2006), 2006.
    (PDF 4.8MB)

  • Monocular 3D Reconstruction of Human Motion in Long Action Sequences
    G. Loy, M. Eriksson, J. Sullivan and S. Carlsson,
    In Proc of European Conference on Computer Vision (ECCV 2004), 2004.
    (PDF 1.9MB)

  • Pose-Based Clustering in Action Sequences
    G. Loy, J. Sullivan and S. Carlsson,
    Workshop on Higher-Level Knowledge in 3D Modeling & Motion Analysis, 2003.
    (PDF 1.2MB)

  • Recognizing and Tracking Human Action
    J. Sullivan and S. Carlsson.
    In Proc of European Conference on Computer Vision (ECCV 2002), 2002.
    (PDF 591KB)

  • Bayesian Correlation
    J. Sullivan, A. Blake, M. Isard and J. MacCormick,
    In International Journal of Computer Vision, 44(2), pages 111-135, 2001

  • Action Recognition by Shape Matching to Key Frames
    S. Carlsson and J. Sullivan,
    Workshop on Models versus Exemplars in Computer Vision, 2001.
    (PDF 180KB)

  • Guiding Random Samples by Deterministic Search
    J. Sullivan and J. Rittscher,
    In Proc. International Conference on Computer Vision (ICCV 2001), Vancouver, Canada, 2001.
    (gzipped PS 2MB)

  • Statistical Foreground Modelling for Object Localisation
    J. Sullivan, A. Blake, and J. Rittscher.
    In Proc. European Conference on Computer Vision (ECCV 2000), Dublin, Ireland, May 2000.
    (gzipped PS 2.2MB)

  • Object Localisation by Bayesian Correlation
    J. Sullivan, A. Blake, M. Isard, and J. MacCormick.
    In Proc. International Conference on Computer Vision (ICCV 1999), Corfu, Greece, Sept. 1999.
    (gzipped PS 2.2MB)

CV

I obtained a D.Phil from Oxford University, Dept. Of Engineering Sciences in 2001 under the supervision of Prof. Andrew Blake. Prior to that I did a BA in Mathematics at Trinity College Dublin, Ireland. Since my D.Phil studies I've been working mainly with Stefan Carlsson at KTH.

Software

Video Reading Code for Matlab. This link brings you to some code a colleague and myself wrote that interfaces with the package ffmpeg to enable video file reading into Matlab (compiles on either Linux or Windows). From experience I know this can be a frustrating task so I hope this code is helpful.

Presentations

Here are some of the talks I've made:
Head data
josephinesullivan