Sciweavers

242 search results - page 18 / 49
» Learning human actions via information maximization
Sort
View
90
Voted
MM
2004
ACM
170views Multimedia» more  MM 2004»
15 years 3 months ago
Effective automatic image annotation via a coherent language model and active learning
Image annotations allow users to access a large image database with textual queries. There have been several studies on automatic image annotation utilizing machine learning techn...
Rong Jin, Joyce Y. Chai, Luo Si
ICML
2005
IEEE
15 years 10 months ago
Multi-way distributional clustering via pairwise interactions
We present a novel unsupervised learning scheme that simultaneously clusters variables of several types (e.g., documents, words and authors) based on pairwise interactions between...
Ron Bekkerman, Ran El-Yaniv, Andrew McCallum
MIR
2006
ACM
195views Multimedia» more  MIR 2006»
15 years 3 months ago
Automatically selecting shots for action movie trailers
Movie trailers, or previews, are an important method of advertising movies. They are extensively shown before movies in cinemas, as well as on television and increasingly, over th...
Alan F. Smeaton, Bart Lehane, Noel E. O'Connor, Co...
CVPR
2007
IEEE
15 years 11 months ago
Learning Motion Categories using both Semantic and Structural Information
Current approaches to motion category recognition typically focus on either full spatiotemporal volume analysis (holistic approach) or analysis of the content of spatiotemporal in...
Shu-Fai Wong, Tae-Kyun Kim, Roberto Cipolla
AI
2006
Springer
15 years 1 months ago
Satisfaction Equilibrium: Achieving Cooperation in Incomplete Information Games
So far, most equilibrium concepts in game theory require that the rewards and actions of the other agents are known and/or observed by all agents. However, in real life problems, a...
Stéphane Ross, Brahim Chaib-draa