Changes

No change in size ,  16:13, 15 April 2013
Line 150: Line 150:  
===Analyzing 3D objects in cluttered images===
 
===Analyzing 3D objects in cluttered images===
 
Speaker: [http://www.umiacs.umd.edu/~sshekha/ Sumit Shekhar] : April 18, 2013
 
Speaker: [http://www.umiacs.umd.edu/~sshekha/ Sumit Shekhar] : April 18, 2013
 +
 
Data-driven dictionaries have produced state-of-the-art results in various classification tasks. However, when the target data has a different distribution than the source data, the learned sparse representation may not be optimal. In this talk, I will discuss a technique to learn a joint dictionary which can work well for the target data as well, and present some results on face and object recognition.
 
Data-driven dictionaries have produced state-of-the-art results in various classification tasks. However, when the target data has a different distribution than the source data, the learned sparse representation may not be optimal. In this talk, I will discuss a technique to learn a joint dictionary which can work well for the target data as well, and present some results on face and object recognition.
      
===Analyzing 3D objects in cluttered images===
 
===Analyzing 3D objects in cluttered images===
50

edits