Sciweavers

242 search results - page 14 / 49
» Learning human actions via information maximization
Sort
View
JMLR
2010
119views more  JMLR 2010»
14 years 4 months ago
Semi-Supervised Learning via Generalized Maximum Entropy
Various supervised inference methods can be analyzed as convex duals of the generalized maximum entropy (MaxEnt) framework. Generalized MaxEnt aims to find a distribution that max...
Ayse Erkan, Yasemin Altun
CONSTRAINTS
2007
94views more  CONSTRAINTS 2007»
14 years 9 months ago
A Constraint-based Approach for Annotating Music Scores with Gestural Information
The physical gestures that operate music instruments are responsible for the qualities of the sound being produced in a performance. Gestural information is thereby crucial for a ...
Daniele P. Radicioni, Vincenzo Lombardo
CVPR
2008
IEEE
15 years 11 months ago
Action recognition using exemplar-based embedding
In this paper, we address the problem of representing human actions using visual cues for the purpose of learning and recognition. Traditional approaches model actions as space-ti...
Daniel Weinland, Edmond Boyer
72
Voted
CHI
2006
ACM
15 years 10 months ago
Engaging with a situated display via picture messaging
We outline initial investigations into how choices of spatial configuration, input devices and display technologies influence action and interaction in hybrid electronic and physi...
Karen Martin, Alan Penn, Lesley Gavin
CIKM
2009
Springer
15 years 4 months ago
Semi-supervised learning of semantic classes for query understanding: from the web and for the web
Understanding intents from search queries can improve a user’s search experience and boost a site’s advertising profits. Query tagging via statistical sequential labeling mode...
Ye-Yi Wang, Raphael Hoffmann, Xiao Li, Jakub Szyma...