Group Meeting

Randomized Methods for Image Classification

This talk presents randomized methods including randomized trees, forests and ferns and their application in image classification. [ppt] Presented by Feng Tang on 5/1/08. Main paper: Bosch, A. Zisserman, A. Muoz, X."Image Classification using Random Forests and Ferns" CVPR 2007 http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4409066 Some background papers: V. Lepetit and P. Fua. Keypoint recognition using randomized
Event Type: 

Image Processing in the Human Visual System: A Quick Overview

This is an introduction to the low-level image processing that the signal from the photo-receptors undergoes on its way to the cortex. Presentes by Orazio Gallo, on 04/24/1008. (pdf)
Event Type: 

Locality Sensitive Hashing and Fast Pose Estimation with Parameter Sensitive Hashing

Locality Sensitive Hashing and Fast Pose Estimation with Parameter Sensitive Hashing, presented by Doug Gray, on 4/17/2008. (PPT)
Event Type: 

Computer Vision and the Web

Applying computer vision techniques to web applications that make use of the wealth of contents on the Internet is a research area that receives more and more attention. Two topics of "80 million tiny images" and "open mind" are presented here (PPT) by Qi Zhao, and more interesting contents can be found at http://www.cs.unc.edu/~lazebnik/fall07/ . 2/26/08.
Event Type: 

Real-Time Edge-Aware Image Processing with the Bilateral Grid

A work by J. Chen, S. Paris, F. Durand, from SIGGRAPH 2007. Presented by Orazio Gallo, on 01/29/2008 (pdf)
Event Type: 

Beyond Soft Focus: Beautifying Images without Blur

Beyond Soft Focus: Beautifying Images without Blur, presented by Doug Gray on 1/15/08. (PPT)
Event Type: 

Tracking in Low Frame Rate Video: A Cascade Particle Filter with Discriminative Observers of Different Lifespans

Tracking in low frame rate video is a practical problem to solve. This paper presents a temporal probabilistic combination of discriminative observers with different lifespans, where the observers are learned from different ranges of samples, with different subsets of features, to ensure a complementary fusion. The paper is by Yuan Li, Haizhou Ai, Takayoshi Yamashita, Shihong Lao and Masato Kamade, and it received the CVPR 2007 best student paper award. Here (PPT) is a presentation by Qi Zhao.
Event Type: 

Image Deblurring from a Single Image

Papers presented:
  • R. Fergus, B. Singh, A. Hertzmann, S. T. Roweis, and W. T. Freeman, "Removing Camera Shake from a Single Photograph", SIGGRAPH 06.
  • J. Jia, "Single Image Motion Deblurring Using Transparency", CVPR 07.
  • Presented by Orazio Gallo, on 10/18/2007 (pdf)
    Event Type: 

    Learning Local Image Descriptors

    Learning Local Image Descriptors, presented by Doug Gray on 5/23/2007. (PPT)
    Event Type: 

    Co-Training and its Applications

    Co-Training and its Applications, presented by Shane Brennan on 4/18/2007. (PPT)
    Event Type: 

    Pages