Human action recognition based on comparative similarity
Human action recognition is a key issue in computer vision. This thesis aims to solve the problem of human action recognition, especially when there are few or no positive examples. This case is very important due to the intrinsic long-tailed distribution of categories in real world, which...
Main Author: | Cao, Zhiguang |
---|---|
Other Authors: | School of Electrical and Electronic Engineering |
Format: | Thesis |
Language: | English |
Published: |
2013
|
Subjects: | |
Online Access: | http://hdl.handle.net/10356/54714 |
Similar Items
-
Recognition of human actions
by: Nguyen, Viet Khoi.
Published: (2012) -
Mining actionlet ensemble for action recognition with depth cameras
by: Wang, Jiang, et al.
Published: (2013) -
Compressed video action recognition with refined motion vectors
by: Yu, Shining
Published: (2019) -
Pose-invariant action recognition for automated behaviour analysis
by: Manoj Ramanathan
Published: (2017) -
Clustering with multiviewpoint-based similarity measure
by: Nguyen, Duc Thang, et al.
Published: (2013)