Vibhav Vineet
Ph.D. student in Brookes Vision Group
at Oxford Brookes University
vibhav.vineet-2010@brookes.ac.uk

I spend time developing efficient optimization methods for learning and inference in probabilistic graphical models, which are useful to large scale computer vision problems.
I am supervised by Phil Torr.
Papers

  1. Vibhav Vineet, Glenn Sheasby, Jonathan Warrell, Philip H.S. Torr
    PoseField: An Efficient Mean-field based Method for Joint Estimation of Human Pose, Segmentation and Depth (oral)
    EMMCVPR 2013, Lund, Sweden

  2. Vibhav Vineet, Jonathan Warrell, Philip H.S. Torr
    A Tiered Move-making Algorithm for General Non-submodular Pairwise Energies
    PAMI 2013, [Under Submission]

  3. Vibhav Vineet, Jonathan Warrell, Philip H.S. Torr
    Filter-based Mean-Field Inference for Random Fields with Higher Order Terms and Product Label-Spaces (Oral)
    ECCV 2012, [pdf] [supplementary pdf][code][presentations]

  4. Vibhav Vineet, Jonathan Warrell, Paul Sturgess, Philip H.S. Torr
    Improved Initialization and Gaussian Mixture Pairwise Terms for Dense Random Fields with Mean-field Inference (Oral)
    BMVC 2012, [pdf], [presentation]

  5. Vibhav Vineet, Jonathan Warrell, Philip H.S. Torr
    Tiered Move Making Algorithm for General Pairwise MRFs
    CVPR 2012, [pdf][project page] [presentation] [code]

  6. Vibhav Vineet, Jonathan Warrell, Paul Sturgess, Philip H.S. Torr
    Learning and Inference for General Non-submodular Pairwise Energies
    Rank Prize Symposium 2012, [pdf]

  7. Vibhav Vineet, Jonathan Warrell, Lubor Ladicky, Philip H.S. Torr
    Human Instance Segmentation from Video using Detector-based Conditional Random Fields
    BMVC-2011, [pdf][project page]  


Talks

  1. Filter based mean-field inference
    VGG Reading Group, [ppt] [demo]

  2. Filter-based mean-field inference for random fields with higher order terms and product label spaces
    ECCV-12, [video] [ppt]

  3. Improved initialization and Gaussian mixture pairwise terms for dense random fields with mean-field inference
    BMVC-12, [video] [ppt]

  4. Learning and Inference for General Non-submodular Pairwise Energies
    Rank Prize Symposium 2012, [pdf]



Some [papers] from past, focussed on optimizing graph-cuts and other large scale graph algorithms on Nvidia GPU.

Links:    VGG-RG | Brookes-RG | Blog