An Efficient Temporal Model for Action Recognition Using Multivariate Linear Prediction
碩士 === 國立臺灣大學 === 電信工程學研究所 === 100 === To recognize temporally extended actions, it is useful to introduce high-order temporal dependence into the recognition task. However, this will highly increase the computational complexity, when the commonly used graphical models such as HMM and CRF are employ...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | en_US |
| Published: |
2012
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/09778366885373145653 |