Sciweavers

1375 search results - page 275 / 275
» Matching Points with Things
Sort
View
CVPR
2011
IEEE
13 years 22 days ago
action recognition by dense trajectories
Feature trajectories have shown to be efficient for representing videos. Typically, they are extracted using the KLT tracker or matching SIFT descriptors between frames. However,...
Heng Wang, Alexander Kläser, Cordelia Schmid, Che...
CORR
2011
Springer
171views Education» more  CORR 2011»
13 years 9 days ago
Fairness issues in a chain of IEEE 802.11 stations
: We study a simple general scenario of ad hoc networks based on IEEE 802.11 wireless communications, consisting in a chain of transmitters, each of them being in the carrier sense...
Bertrand Ducourthial, Yacine Khaled, Stépha...
SIGIR
2010
ACM
13 years 23 hour ago
Personalised video retrieval: application of implicit feedback and semantic user profiles
TION ABSTRACT Personalised Video Retrieval: Application of Implicit Feedback and Semantic User Profiles Frank Hopfgartner University of Glasgow Glasgow G12 8QQ United Kingdom A ch...
Frank Hopfgartner
IACR
2011
139views more  IACR 2011»
12 years 4 months ago
Improved Meet-in-the-Middle Cryptanalysis of KTANTAN
We revisit meet-in-the-middle attacks on block ciphers and recent developments in meet-in-the-middle preimage attacks on hash functions. Despite the presence of a secret key in the...
Lei Wei, Christian Rechberger, Jian Guo 0001, Hong...
CORR
2012
Springer
170views Education» more  CORR 2012»
12 years 1 months ago
What Cannot be Learned with Bethe Approximations
We address the problem of learning the parameters in graphical models when inference is intractable. A common strategy in this case is to replace the partition function with its B...
Uri Heinemann, Amir Globerson