Recognizing action primitives in complex actions using hidden Markov models
(2006) 2nd International Symposium on Visual Computing, ISVC 2006 In Lecture Notes in Computer Science 4291. p.538-547- Abstract
There is biological evidence that human actions are composed out of action primitives, similarly to words and sentences being composed out of phonemes. Given a set of action primitives and an action composed out of these primitives we present a Hidden Markov Model-based approach that allows to recover the action primitives in that action. In our approach, the primitives may have different lengths, no clear "divider" between the primitives is necessary. The primitive detection is done online, no storing of past data is necessary. We verify our approach on a large database. Recognition rates are slightly smaller than the rate when recognizing the singular action primitives.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/9c75070f-4163-488f-b08a-bc4818e700c3
- author
- Krüger, V.
LU
- publishing date
- 2006-01-01
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Advances in Visual Computing - Second International Symposium, ISVC 2006, Proceedings
- series title
- Lecture Notes in Computer Science
- volume
- 4291
- pages
- 10 pages
- publisher
- Springer
- conference name
- 2nd International Symposium on Visual Computing, ISVC 2006
- conference location
- Lake Tahoe, NV, United States
- conference dates
- 2006-11-06 - 2006-11-08
- external identifiers
-
- scopus:33845435437
- ISSN
- 0302-9743
- 1611-3349
- ISBN
- 3540486283
- 9783540486282
- DOI
- 10.1007/11919476_54
- language
- English
- LU publication?
- no
- id
- 9c75070f-4163-488f-b08a-bc4818e700c3
- date added to LUP
- 2019-07-08 21:19:11
- date last changed
- 2024-01-01 15:51:11
@inproceedings{9c75070f-4163-488f-b08a-bc4818e700c3, abstract = {{<p>There is biological evidence that human actions are composed out of action primitives, similarly to words and sentences being composed out of phonemes. Given a set of action primitives and an action composed out of these primitives we present a Hidden Markov Model-based approach that allows to recover the action primitives in that action. In our approach, the primitives may have different lengths, no clear "divider" between the primitives is necessary. The primitive detection is done online, no storing of past data is necessary. We verify our approach on a large database. Recognition rates are slightly smaller than the rate when recognizing the singular action primitives.</p>}}, author = {{Krüger, V.}}, booktitle = {{Advances in Visual Computing - Second International Symposium, ISVC 2006, Proceedings}}, isbn = {{3540486283}}, issn = {{0302-9743}}, language = {{eng}}, month = {{01}}, pages = {{538--547}}, publisher = {{Springer}}, series = {{Lecture Notes in Computer Science}}, title = {{Recognizing action primitives in complex actions using hidden Markov models}}, url = {{http://dx.doi.org/10.1007/11919476_54}}, doi = {{10.1007/11919476_54}}, volume = {{4291}}, year = {{2006}}, }