Sciweavers

108 search results - page 4 / 22
» Labeled posets are universal
Sort
View
ICCV
2011
IEEE
12 years 6 months ago
Learning Universal Multi-view Age Estimator by Video Contexts
Most existing techniques for analyzing face images assume that the faces are at near-frontal poses. Generalizing to non-frontal faces is often difficult, due to a dearth of groun...
Zheng Song, Bingbing Ni, Dong Guo, Terence Sim, Sh...
CVPR
2009
IEEE
15 years 1 months ago
What's It Going to Cost You?: Predicting Effort vs. Informativeness for Multi-Label Image Annotations
Active learning strategies can be useful when manual labeling effort is scarce, as they select the most informative examples to be annotated first. However, for visual category ...
Sudheendra Vijayanarasimhan (University of Texas a...
SPAA
2009
ACM
14 years 6 months ago
On randomized representations of graphs using short labels
Informative labeling schemes consist in labeling the nodes of graphs so that queries regarding any two nodes (e.g., are the two nodes adjacent?) can be answered by inspecting mere...
Pierre Fraigniaud, Amos Korman
ICASSP
2008
IEEE
14 years 14 days ago
Fine-grained pitch accent and boundary tone labeling with parametric F0 features
Motivated by linguistic theories of prosodic categoricity, symbolic representations of prosody have recently attracted the attention of speech technologists. Categorical represent...
Sankaranarayanan Ananthakrishnan, Shrikanth Naraya...
TREC
2007
13 years 7 months ago
The Robert Gordon University at the Opinion Retrieval Task of the 2007 TREC Blog Track
Abstract. The Robert Gordon University (RGU) participated in the Opinion Retrieval Task of the Trec 2007 Blog Track. At the core of the system we developed is a set of training doc...
Rahman Mukras, Nirmalie Wiratunga, Robert Lothian