Sciweavers

604 search results - page 30 / 121
» The Hardness of Metric Labeling
Sort
View
GIS
2004
ACM
14 years 9 months ago
A novel improvement to the R*-tree spatial index using gain/loss metrics
The R*-tree is a state-of-the-art spatial index structure. It has already found its way into commercial systems. The most important improvement of the R*-tree over the original R-...
Donghui Zhang, Tian Xia
MM
2009
ACM
203views Multimedia» more  MM 2009»
14 years 21 days ago
Distance metric learning from uncertain side information with application to automated photo tagging
Automated photo tagging is essential to make massive unlabeled photos searchable by text search engines. Conventional image annotation approaches, though working reasonably well o...
Lei Wu, Steven C. H. Hoi, Rong Jin, Jianke Zhu, Ne...
VLSID
2009
IEEE
108views VLSI» more  VLSID 2009»
14 years 8 months ago
Metric Based Multi-Timescale Control for Reducing Power in Embedded Systems
Abstract--Digital control for embedded systems often requires low-power, hard real-time computation to satisfy high control-loop bandwidth, low latency, and low-power requirements....
Forrest Brewer, João Pedro Hespanha, Nitin ...
CVPR
2010
IEEE
14 years 4 months ago
Semi-supervised Hashing for Scalable Image Retrieval
Large scale image search has recently attracted considerable attention due to easy availability of huge amounts of data. Several hashing methods have been proposed to allow approx...
Jun Wang, Sanjiv Kumar, Shih-Fu Chang
WACV
2005
IEEE
14 years 1 months ago
Semi-Supervised Self-Training of Object Detection Models
The construction of appearance-based object detection systems is time-consuming and difficult because a large number of training examples must be collected and manually labeled i...
Chuck Rosenberg, Martial Hebert, Henry Schneiderma...