University of Sussex
Browse

File(s) not publicly available

Learning and Understanding Dynamic Scence Activity: A Review

journal contribution
posted on 2023-06-07, 22:23 authored by Hilary Buxton
We are entering an era of more intelligent cognitive vision systems. Such systems can analyse activity in dynamic scenes to compute conceptual descriptions from motion trajectories of moving people and the objects they interact with. Here we review progress in the development of flexible, generative models that can explain visual input as a combination of hidden variables and can adapt to new types of input. Such models are particularly appropriate for the tasks posed by cognitive vision as they incorporate learning as well as having sufficient structure to represent a general class of problems. In addition, generative models explain all aspects of the input rather than attempting to ignore irrelevant sources of variation as in exemplar-based learning. Applications of these models in visual interaction for education, smart rooms and cars, as well as surveillance systems is also briefly reviewed.

History

Publication status

  • Published

Journal

Image and Vision Computing

ISSN

02628856

Publisher

Elsevier

Issue

1

Volume

21

Page range

125-136

Pages

12.0

Department affiliated with

  • Informatics Publications

Full text available

  • No

Peer reviewed?

  • Yes

Legacy Posted Date

2012-02-06

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC