Discriminative human action segmentation and recognition using semi-Markov model
-
Altmetric Citations
Shi, Qinfeng; Wang, Li; Cheng , Li; Smola, Alexander
Description
Given an input video sequence of one person conducting a sequence of continuous actions, we consider the problem of jointly segmenting and recognizing actions. We propose a discriminative approach to this problem under a semi-Markov model framework, where we are able to define a set of features over input-output space that captures the characteristics on boundary frames, action segments and neighboring action segments, respectively. In addition, we show that this method can also be used to...[Show more]
dc.contributor.author | Shi, Qinfeng | |
---|---|---|
dc.contributor.author | Wang, Li | |
dc.contributor.author | Cheng , Li | |
dc.contributor.author | Smola, Alexander | |
dc.coverage.spatial | Anchorage Alaska | |
dc.date.accessioned | 2015-12-10T22:28:47Z | |
dc.date.created | June 24-26 2008 | |
dc.identifier.isbn | 9781424422432 | |
dc.identifier.uri | http://hdl.handle.net/1885/54606 | |
dc.description.abstract | Given an input video sequence of one person conducting a sequence of continuous actions, we consider the problem of jointly segmenting and recognizing actions. We propose a discriminative approach to this problem under a semi-Markov model framework, where we are able to define a set of features over input-output space that captures the characteristics on boundary frames, action segments and neighboring action segments, respectively. In addition, we show that this method can also be used to recognize the person who performs in this video sequence. A Viterbi-like algorithm is devised to help efficiently solve the induced optimization problem. Experiments on a variety of datasets demonstrate the effectiveness of the proposed method. | |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE Inc) | |
dc.relation.ispartofseries | Computer Vision and Pattern Recognition Conference (CVPR 2008) | |
dc.source | Proceedings of CVPR 2008 | |
dc.subject | Keywords: Artificial intelligence; Computer vision; Feature extraction; Image processing; Imaging techniques; Pattern recognition; Photography; Video recording; Viterbi algorithm; Continuous actions; Data-sets; Discriminative approach; Human actions; Input video se | |
dc.title | Discriminative human action segmentation and recognition using semi-Markov model | |
dc.type | Conference paper | |
local.description.notes | Imported from ARIES | |
local.description.refereed | Yes | |
dc.date.issued | 2008 | |
local.identifier.absfor | 080109 - Pattern Recognition and Data Mining | |
local.identifier.ariespublication | u8803936xPUB305 | |
local.type.status | Published Version | |
local.contributor.affiliation | Shi, Qinfeng, College of Engineering and Computer Science, ANU | |
local.contributor.affiliation | Wang, Li, Southeast University | |
local.contributor.affiliation | Cheng , Li, College of Engineering and Computer Science, ANU | |
local.contributor.affiliation | Smola, Alexander, College of Engineering and Computer Science, ANU | |
local.description.embargo | 2037-12-31 | |
local.bibliographicCitation.startpage | 1 | |
local.bibliographicCitation.lastpage | 8 | |
local.identifier.doi | 10.1109/CVPR.2008.4587557 | |
dc.date.updated | 2015-12-09T09:50:55Z | |
local.identifier.scopusID | 2-s2.0-51949091791 | |
Collections | ANU Research Publications |
Download
File | Description | Size | Format | Image |
---|---|---|---|---|
01_Shi_Discriminative_human_action_2008.pdf | 1.94 MB | Adobe PDF | Request a copy |
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.
Updated: 17 November 2022/ Responsible Officer: University Librarian/ Page Contact: Library Systems & Web Coordinator