File(s) under permanent embargo
Evaluating the covariance matrix constraints for data-driven statistical human motion reconstruction
conference contribution
posted on 2023-06-08, 16:25 authored by Christos Mousas, Paul NewburyPaul Newbury, Christos-Nikolaos AnagnostopoulosThis paper presents the evaluation process of the character's motion reconstruction while constraints are applied to the covariance matrix of the motion prior learning process. For the evaluation process, a maximum a posteriori (MAP) framework is first generated, which receives input trajectories and reconstructs the motion of the character. Then, using various methods to constrain the covariance matrix, information that reflects certain assumptions about the motion reconstruction process is retrieved. Each of the covariance matrix constraints are evaluated by its ability to reconstruct the desired motion sequences either by using a large amount of motion data or by using a small dataset that contains only specific motions.
History
Publication status
- Published
File Version
- Published version
Journal
SCCG '14: Proceedings of the 30th Spring Conference on Computer GraphicsPublisher
Association for Computing MachineryPublisher URL
External DOI
Page range
99-106Event name
ACM/Eurographics Spring Conference on Computer GraphicsEvent location
ViennaEvent type
conferenceEvent date
28th - 30th May 2014Place of publication
New York, NY, United StatesISBN
9781450330701Department affiliated with
- Informatics Publications
Full text available
- No
Peer reviewed?
- Yes
Legacy Posted Date
2014-09-29First Compliant Deposit (FCD) Date
2020-10-16Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC