A Survey Paper on Learning Pullback HMM Distance for Recognition of Action
International Journal of Science and Research (IJSR)

International Journal of Science and Research (IJSR)
Call for Papers | Fully Refereed | Open Access | Double Blind Peer Reviewed

ISSN: 2319-7064


Downloads: 117 | Views: 354

Survey Paper | Computer Science & Engineering | India | Volume 3 Issue 11, November 2014 | Popularity: 6.7 / 10


     

A Survey Paper on Learning Pullback HMM Distance for Recognition of Action

Vanita Babane, Poonam Sangar


Abstract: Recent work in action recognition has exposed the limitations of features extracted from spatiotemporal video volumes. Whereas, encoding the actions dynamics using generative dynamical models has a number of attractive features, in this respect Hidden Markov models (HMMs) is a popular choice. A general framework based on pullback metrics for learning distance functions of a given training set of labeled videos has been generated, The optimal distance function is selected among a family of pullback ones, which is generated by a parameterized automorphism of the space models. An experimental result shows that how pullback learning greatly improves action recognition performances with respect to base distances.


Keywords: Distance learning, pullback metrics, hidden Markov models HMM, action recognition


Edition: Volume 3 Issue 11, November 2014


Pages: 2225 - 2226



Please Disable the Pop-Up Blocker of Web Browser

Verification Code will appear in 2 Seconds ... Wait



Text copied to Clipboard!
Vanita Babane, Poonam Sangar, "A Survey Paper on Learning Pullback HMM Distance for Recognition of Action", International Journal of Science and Research (IJSR), Volume 3 Issue 11, November 2014, pp. 2225-2226, https://www.ijsr.net/getabstract.php?paperid=OCT141446, DOI: https://www.doi.org/10.21275/OCT141446

Top