Sciweavers

1457 search results - page 218 / 292
» Surrogate data: A novel approach to object detection
Sort
View
CVPR
2010
IEEE
15 years 6 months ago
Efficient Action Spotting based on a Spacetime Oriented Structure Representation
This paper addresses action spotting, the spatiotemporal detection and localization of human actions in video. A novel compact local descriptor of video dynamics in the context of...
Konstantinos Derpanis, Mikhail Sizintsev, Kevin Ca...
ICMCS
2006
IEEE
167views Multimedia» more  ICMCS 2006»
15 years 3 months ago
Automatic Classification of Field of View in Video
Automatic systems are needed for audiovisual databases to efficiently index, browse, summarize and retrieve, because the amount of stored data is increasing tremendously. Historic...
Maria Ferrer, Mauro Barbieri, Hans Weda
IJCAI
2003
14 years 11 months ago
Active Learning with Strong and Weak Views: A Case Study on Wrapper Induction
Multi-view learners reduce the need for labeled data by exploiting disjoint sub-sets of features (views), each of which is sufficient for learning. Such algorithms assume that eac...
Ion Muslea, Steven Minton, Craig A. Knoblock
ACL
2012
13 years 7 days ago
Reducing Wrong Labels in Distant Supervision for Relation Extraction
In relation extraction, distant supervision seeks to extract relations between entities from text by using a knowledge base, such as Freebase, as a source of supervision. When a s...
Shingo Takamatsu, Issei Sato, Hiroshi Nakagawa
ICCV
2007
IEEE
15 years 11 months ago
From Uncertainties to Statistical Model Building and Segmentation of the Left Ventricle
Reliable segmentation of the left ventricle is a long sought objective in medical imaging for automatic retrieval of anatomical and pathological measurements and detection of malf...
Maxime Taron, Nikos Paragios, Marie-Pierre Jolly