The Visual Learning Group researches methods to acquire models of the real-world from visual data, such as images, videos, and motion sequences. Most of this research lies at the boundary between computer vision, machine learning and computer animation. Projects include learning image representations for visual recognition - the problem of determining what is where in a picture - but also extracting models of human movement from video and motion capture data.

news


  1. 6 new papers on arXiv:

  2. -   ViCom: Benchmark and Methods for Video Comprehension,
        with Du Tran and Manohar Paluri.

  3. -   Colorization for Image Compression,
        with Haris Baig.

  4. -   Local Perturb-and-MAP for Structured Prediction,
        with Gedas Bertasius, Qiang Liu and Jianbo Shi.

  5. -   Convolutional Random Walk Networks for Semantic Image Segmentation,
        with Gedas Bertasius, Stella Yu and Jianbo Shi.

  6. -   Network of Experts for Large-Scale Image Categorization,
        with Karim Ahmed and Haris Baig.

  7. -   Recurrent Mixture Density Network for Spatiotemporal Visual Attention,
        with Loris Bazzani and Hugo Larochelle.



  1. new paper at CVPR 2016:
    Semantic Segmentation with Boundary Neural Fields,
    G. Bertasius, J. Shi, and L. Torresani.


  1. new paper at the 3rd Workshop on Deep Learning in Computer Vision, 2016:

    Deep End2End Voxel2Voxel Prediction,
    D. Tran, L. Bourdev, R. Fergus, L. Torresani and M. Paluri.


  1. new article in IJCV:

     EXMOVES: Mid-level Features for Efficient Action Recognition and Video Analysis,
     D Tran, L. Torresani.


  1. new paper at WACV 2016:
    Self-taught Object Localization with Deep Networks,
    L. Bazzani, A. Bergamo, D. Anguelov, and L. Torresani.


  1. new paper at WACV 2016:
    Coupled Depth Learning,
    M.H. Baig, and L. Torresani.


  1. new paper at ICCV 2015:
    High-for-Low and Low-for-High: Efficient Boundary Detection from Deep Object
    Features and its Applications to High-Level Vision
    ,
    G. Bertasius, J. Shi, and L. Torresani.


  1. new paper at ICCV 2015:
    Learning Spatiotemporal Features with 3D Convolutional Networks,
    D. Tran, L. Bourdev, R. Fergus, L. Torresani, and M. Paluri.


  1. new article at CVPR 2015:
    DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection,
    G. Bertasius, J. Shi, and L. Torresani.


  1. new article in IEEE TPAMI (June 2015):
    What Can Pictures Tell Us About Web Pages? Improving Document Search using 
    Images
    ,
    S. Rodriguez-Vaamonde, L. Torresani, and A. Fitzgibbon.

sponsors

We thank the following sources for supporting our research.

Logo design by Christine Claudino