University of Cambridge > Talks.cam > Machine Learning @ CUED > An application of HDP And IBP for stream-based action recognition and high dimensional data

An application of HDP And IBP for stream-based action recognition and high dimensional data

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Zoubin Ghahramani.

The dynamism of Bayesian non-parametric methods in making data-driven decisions based on infinite models, has motivated many studies in various fields. This talk presents the application of HDP switching models in action recognition for video data. We have proposed a stream-based online model, capable of adaptive learning of unlimited actions with real-time performance. Results on three action datasets prove a remarkable performance. This study is further followed by integrating other BNP models like IBP to enhance pattern recognition in high-dimensional contexts.

This talk is part of the Machine Learning @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2017 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity