Project :  

The goal of this project is to study a state-of-the-art topic. You can do this by either implementing a recent paper, or by coming up with your own idea of a cool application.

 A good  way to collect ideas is by going over papers published in one of the leading computer vision conferences (ICCV,CVPR or ECCV). Here is a link to all the papers of recent years:
http://www.cvpapers.com/index.html

Project proposal

You must send me a project proposal  (at most 2 pages long) describing the project you've selected.  The project proposal should include the following:


Final submission

1. Project summary

Your project summary should include the following:

2. Code+data

Your submission should include:




Here are a few papers I have selected (no need to stick to this list)


Topic Paper Presented by Project page
Fun with images Optimizing Content-Preserving Projections for Wide-Angle Images
Robert Carroll, Maneesh Agrawala, Aseem Agarwala

SIGGRAPH'09
 
  Content-Preserving Warps for 3D Video Stabilization
Feng Liu, Michael Gleicher, Hailin Jin, Aseem Agarwala

SIGGRAPH'09
   
 
Filter Flow (PDF, supplemental material)
Steven M. Seitz, Simon Baker
ICCV'09
   
Image matching SIFT flow: dense correspondence across different scenes
Ce Liu, Jenny Yuen, Antonio Torralba, Josef Sivic, William T. Freeman ECCV'08
   
  Scale & Affine Invariant Interest Point Detectors
K Mikolajczyk & C. Schmid,  IJCV'04

 
  Linear Solution to Scale and Rotation Invariant Object Matching
Hao Jiang, Stella X. Yu CVPR'09
   
 
 
Multi-camera action recognition Multi-Camera Activity Correlation Analysis
Chen Change Loy, Tao Xiang, Shaogang Gong
CVPR'09
   
  Free viewpoint action recognition using motion history volumes
D Weinland, R Ronfard, E Boyer -
Computer Vision and Image Understanding, 2006
   
  Motion history volumes for free viewpoint action recognition
D Weinland, R Ronfard, E Boyer -
IEEE International Workshop on Modeling People and Human , 2005
   
Action recognition Recognizing Realistic Actions from Videos "in the Wild"
Jingen Liu, Jiebo Luo, and Mubarak Shah
CVPR'09
   
  Actions in context (project page)
Marcin Marszalek, Ivan Laptev, Cordelia Schmid
CVPR'09
   
Video summarization Understanding Videos, Constructing Plots - Learning a Visually Grounded Storyline Model from Annotated Videos
Abhinav Gupta, Praveen Srinivasan, Jianbo Shi, Larry S. Davis
CVPR'09
   
       
Saliency detection

 

 

 

 
   

 

 
   

 

 
Image features
Compact Signatures for High-Speed Interest Point Description and Matching (PDF)
Michael Calonder, Vincent Lepetit, Pascal Fua, Kurt Konolige, James Bowman, Patrick Mihelich
ICCV'09