For the current REF see the REF 2021 website REF 2021 logo

Output details

11 - Computer Science and Informatics

University of Leeds

Return to search Previous output Next output
Output 39 of 95 in the submission
Article title

Explaining Activities as Consistent Groups of Events: A Bayesian Framework Using Attribute Multiset Grammars

Type
D - Journal article
Title of journal
International Journal of Computer Vision
Article number
-
Volume number
98
Issue number
1
First page of article
83
ISSN of journal
0920-5691
Year of publication
2012
URL
-
Number of additional authors
1
Additional information

<23>In 2007 (BMVC, not in RAE2008), the authors demonstrated that better explanations could be found for a particular activity by exploiting constraints between constituent events. This journal article is based on two substantial conference papers (IEEE-CVPR 2009, DOI:10.1109/CVPR.2009.5206636; BMVC’2009, DOI:10.5244/C.23.123) that develop this idea to: (i) handle many activities through specifying compositional structure and constraints using attribute multi-set grammars, (ii) evaluate potential solutions using Bayesian methods and (iii) optimise efficiently using MCMC. Based on this work (and [Hogg4]), Damen secured a Lectureship (in Bristol). The work is covered in a 2011 ACM Computing Surveys review on human activity analysis (DOI:10.1145/1922649.1922653).

Interdisciplinary
-
Cross-referral requested
-
Research group
None
Citation count
1
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-