Recognizing human actions by their pose

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F09%3A00163713" target="_blank" >RIV/68407700:21230/09:00163713 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Recognizing human actions by their pose
Original language description
Human action recognition from images increasing interest throughout the last years. The majority of approaches are restricted to dynamic motion features and not universally applicable. In this paper, we propose to recognize human actions by evaluating adistribution over a set of predefined static poses which we refer to as pose primitives. We aim at the approach that also works in still images, or for images taken from a moving camera. Experimental validation takes varying video sequence lengths into account and emphasizes the possibility for action recognition from single images, which we believe is an often overlooked but nevertheless important aspect of action recognition.
Czech name
—
Czech description
—

Project
<a href="/en/project/7E08031" target="_blank" >7E08031: Dynamic Interactive Perception-action Learning in Cognitive Systems</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year
2009
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Book/collection name
Statistical and Geometrical Approaches to Visual Motion Analysis
ISBN
978-3-642-03060-4
Number of pages of the result
24
Pages from-to
—
Number of pages of the book
322
Publisher name
Springer-Verlag
Place of publication
Berlin
UT code for WoS chapter
—

Similar results(10)