Middle-level representation for human activities recognition : the role of spatio-temporal relationships
We tackle the challenging problem of human activity recognition in realistic video sequences. Unlike local features-based methods or global template-based methods, we propose to represent a video sequence by a set of middle-level parts. A part, or component, has consistent spatial structure and cons...
Saved in:
Main Authors: | Yuan, Fei, Prinet, V´eronique, Yuan, Junsong |
---|---|
Other Authors: | Kutulakos, Kiriakos N. |
Format: | Book Chapter |
Language: | English |
Published: |
Springer Berlin Heidelberg
2014
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/103853 http://hdl.handle.net/10220/19350 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Learning sparse representation via spatio-temporal smoothing for human activity recognition
by: Peng, Haiyun
Published: (2015) -
Max-margin structured output regression for spatio-temporal action localization
by: Tran, Du, et al.
Published: (2014) -
Video event detection : from subvolume localization to spatio-temporal path search
by: Tran, Du, et al.
Published: (2014) -
Video anomaly search in crowded scenes via spatio-temporal motion context
by: Cong, Yang, et al.
Published: (2013) -
Facial expression recognition in the spatio-temporal domain
by: Xiang, Tuo Wen
Published: (2011)