OpenBU

Learning Actions From the Web

OpenBU

Show simple item record

dc.contributor.author Ikizler-Cinbis, Nazli en_US
dc.contributor.author Cinbis, Gokberk en_US
dc.contributor.author Sclaroff, Stan en_US
dc.date.accessioned 2012-05-21T18:59:36Z
dc.date.available 2012-05-21T18:59:36Z
dc.date.issued 2010-07-06 en_US
dc.identifier.citation Ikizler-Cinbis, Nazli; Cinbis, Gokberk; Sclaroff, Stan. "Learning Actions From the Web", Technical Report BUCS-TR-2010-017, Computer Science Department, Boston University, July 6, 2010. [Available from: http://hdl.handle.net/2144/3794] en_US
dc.identifier.uri http://hdl.handle.net/2144/3794
dc.description.abstract 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. en_US
dc.language.iso en-US en_US
dc.publisher CS Department, Boston University en_US
dc.relation.ispartofseries BUCS Technical Reports;BUCS-TR-2010-017 en_US
dc.title Learning Actions From the Web en_US
dc.type Technical Report en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search OpenBU


Browse

Deposit Materials

Statistics