MEETING-DATE:November 22, 2012
MEETING-LOCATION:DC 1331
MEETING-TIME:11:30
MEETING-CHAIR:Elodie Fourquet
MEETING-CHAIRPIC:elodie.jpg
COFFEE-HOUR-LAST-WEEK:Zainab
COFFEE-HOUR-THIS-WEEK:Volunteers?
COFFEE-HOUR-NEXT-WEEK:Volunteers?
FORTH-DATE1:November 29, 2012
FORTH-DATE2:December 6, 2012 
FORTH-DATE3:December 13, 2012 
FORTH-DATE4:December 20, 2012 
FORTH-LOCATION1:DC 1331 11:30
FORTH-LOCATION2:DC 1331 11:30
FORTH-LOCATION3:DC 1331 11:30
FORTH-LOCATION4:DC 1331 11:30
FORTH-CHAIR1:Bill Cowan
FORTH-CHAIR2:Tiffany Inglis
FORTH-CHAIR3:Craig Kaplan
FORTH-CHAIR4:Marta Kryven
FORTH-CHAIRPIC1:cowan_unflipped.gif
FORTH-CHAIRPIC2:tiffany.jpg
FORTH-CHAIRPIC3:cr.jpg
FORTH-CHAIRPIC4:martaPicture.jpg
FORTH-TP1:Zainab AlMeraj
FORTH-TP2:Bill Cowan
FORTH-TP3:Elodie Fourquet
FORTH-TP4:Tiffany Inglis
FORTH-TPPIC1:zainab.jpg
FORTH-TPPIC2:cowan_unflipped.gif
FORTH-TPPIC3:elodie.jpg
FORTH-TPPIC4:tiffany.jpg
TPNAME:Grace Yao
TPTITLE:An algorithm which represents objects in a background using discriminative non-orthogonal binary space(DNBS)
TPABSTRACT:In visual tracking problem, how to represent the object is a crucial problem. This DNBS is a succinct and discriminative representation of the object spanned by Harr-like feature. However, the problem of finding the DNBS bases from an over-complete dictionary is NP-hard. The previous D-OOMP can be done in a greedy way and make it faster. Due to the huge search space, the algorithm is still expensive. At the same time they only care about the foreground with only one template which is not that stable. The DNBS is an efficient, generative and discriminative method. I will explain the original one, the iterative one and the hierarchical one in my tech presentation.  
TPPIC:grace-small.jpg
DIONE:
DITWO:
DITHREE:
DIFOUR:
AIONE:Papier Mache painting
AITWO:
AITHREE:
AIFOUR:
LEONE:
LETWO:
LETHREE:
LEFOUR:
DMONE:
DMTWO:
DMTHREE:
DMFOUR:
SEMINARS:<dl><nl><dt> <A HREF=https://cs.uwaterloo.ca/odyssey/event/1623>Friday, Nov. 23</A>, 10 a.m. in DC1316: Master's Thesis Presentation/Software Engineering  Research Group </dt><nl><dd><I>Software Journeys</I>, Adrian Filip.</dd><nl></dl><nl><nl><dl><nl><dt><A HREF=https://cs.uwaterloo.ca/odyssey/event/1611>Friday, Nov. 23</A>,  10:30 a.m. in DC 2585: PhD Defence/Algorithms and Complexity Research Group </dt><nl><dd>    <I>Algorithms for Geometric Covering and Piercing Problems</I>,<nl>    Robert Fraser.</dd><nl></dl><nl><nl><nl><dl><nl><dt><A HREF=https://cs.uwaterloo.ca/odyssey/event/1620>Friday, Nov. 23</A>, 11:30 a.m. in DC 2306C(AI Lab):  Artificial Intelligence/Centre for Theoretical Neuroscience<nl></dt><nl><dd><I>Grid Search is a Bad Hyperparameter Optimization Algorithm</I>,<nl>        James Bergstra, Postdoctoral researcher, Centre for Theoretical Neuroscience</dd><nl></dl>     <nl>  <nl><nl><dl><nl><dt><A HREF=https://cs.uwaterloo.ca/odyssey/event/1626>Friday, November 23</A>, 2:00 p.m. in DC 2585: Algorithms and Complexity Seminar</dt><nl><dd> <I>Computing with Uncertainty</I><nl>        Thomas Erlebach, University of Leicester.</dd><nl></dl>    <nl>      <nl><BR><BR><nl><nl><nl><dl><nl><dt><A HREF=https://cs.uwaterloo.ca/odyssey/event/1622><nl>Tuesday, Nov. 27</A>, 11:00 a.m. in DC 2310: Master's Essay Presentation/Databases Research Group</dt><nl><dd> <I>Materialized Views for Eventually-Consistent Record Stores</I>,<nl>        Changjiu Jin.</dd><nl></dl>    <nl>   <nl><nl><dl><nl><dt><A HREF=https://cs.uwaterloo.ca/odyssey/event/1628> Tuesday, No.v 27</a>, 1:30 in DC 1304: Symbolic Computation Group PhD Seminar</dt><nl><dd> <I>Computing Column Bases of Polynomial Matrices</I>, Wei Zhou.</dd><nl></dl>    <nl><nl><dl><nl><dt><A HREF=https://cs.uwaterloo.ca/odyssey/event/1627> <nl>Thursday, Nov. 29,</A>  1:00 p.m. in DC 2310:<nl>        PhD Defence/Computer Graphics Research Group</dt><nl><dd> <I>Perspective in Two Dimensions for Computer Graphics</I>,<nl>        Elodie Fourquet.</dd><nl></dl>    <nl>       <nl><nl><nl><nl><nl>