TY - GEN
T1 - Learning Actions From the Web
AU - Ikizler-Cinbis, Nazli
AU - Cinbis, R. Gokberk
AU - Sclaroff, Stan
AU - Ieee, null
PY - 2009
Y1 - 2009
N2 - This paper proposes a generic method for action recognition in uncontrolled videos. The idea is to use images collected from the Web to learn representations of actions and use this knowledge to automatically annotate actions in videos. Our approach is unsupervised in the sense that it requires no human intervention other than the text querying. Its benefits are two-fold: 1) we can improve retrieval of action images, and 2) we can collect a large generic database of action poses, which can then be used in tagging videos. We present experimental evidence that using action images collected from the Web, annotating actions is possible.
AB - This paper proposes a generic method for action recognition in uncontrolled videos. The idea is to use images collected from the Web to learn representations of actions and use this knowledge to automatically annotate actions in videos. Our approach is unsupervised in the sense that it requires no human intervention other than the text querying. Its benefits are two-fold: 1) we can improve retrieval of action images, and 2) we can collect a large generic database of action poses, which can then be used in tagging videos. We present experimental evidence that using action images collected from the Web, annotating actions is possible.
UR - https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=performanshacettepe&SrcAuth=WosAPI&KeyUT=WOS:000294955300128&DestLinkType=FullRecord&DestApp=WOS_CPL
U2 - 10.1109/ICCV.2009.5459368
DO - 10.1109/ICCV.2009.5459368
M3 - Conference contribution
T3 - Ieee International Conference On Computer Vision
SP - 995
EP - 1002
BT - 2009 Ieee 12th International Conference On Computer Vision (iccv)
PB - IEEE Canada
T2 - 12th IEEE International Conference on Computer Vision
Y2 - 29 September 2009 through 2 October 2009
ER -