Sciweavers

486 search results - page 45 / 98
» Boosting and Hard-Core Sets
Sort
View
99
Voted
ICCV
2009
IEEE
16 years 5 months ago
Is a detector only good for detection?
A common design of an object recognition system has two steps, a detection step followed by a foreground withinclass classification step. For example, consider face detection by...
Quan Yuan and Stan Sclaroff
MICRO
2010
IEEE
99views Hardware» more  MICRO 2010»
14 years 10 months ago
ScalableBulk: Scalable Cache Coherence for Atomic Blocks in a Lazy Environment
Recently-proposed architectures that continuously operate on atomic blocks of instructions (also called chunks) can boost the programmability and performance of shared-memory mult...
Xuehai Qian, Wonsun Ahn, Josep Torrellas
98
Voted
GLOBECOM
2009
IEEE
14 years 10 months ago
Time-Critical Data Dissemination in Cooperative Peer-to-Peer Systems
How to rapidly disseminate a large-sized file to many recipients is a fundamental problem in many applications, such as updating software patches and distributing large scientific ...
Chi-Jen Wu, Cheng-Ying Li, Kai-Hsiang Yang, Jan-Mi...
132
Voted
ICDAR
2009
IEEE
14 years 10 months ago
Extraction of Characters on Signboards in Natural Scene Images by Stump Classifiers
We present a method to detect characters on signboards in natural scene images. For many applications, both classifier with small computational cost and the efficient feature set,...
Minoru Maruyama, Takuma Yamaguchi
101
Voted
ICDM
2009
IEEE
150views Data Mining» more  ICDM 2009»
14 years 10 months ago
Filtering and Refinement: A Two-Stage Approach for Efficient and Effective Anomaly Detection
Anomaly detection is an important data mining task. Most existing methods treat anomalies as inconsistencies and spend the majority amount of time on modeling normal instances. A r...
Xiao Yu, Lu An Tang, Jiawei Han