Ana gezinime atla Aramaya atla Ana içeriğe atla

Learning Actions From the Web

  • Boston University

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde BölümKonferans katkısıbilirkişi

Özet

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.
Orijinal dilİngilizce
Ana bilgisayar yayını başlığı2009 Ieee 12th International Conference On Computer Vision (iccv)
YayınlayanIEEE Canada
Sayfalar995-1002
Sayfa sayısı8
ISBN (Elektronik)978-1-4244-4419-9
DOI'lar
Yayın durumuYayınlandı - 2009
Etkinlik12th IEEE International Conference on Computer Vision - Kyoto, !!Japan
Süre: 29 Eyl 20092 Eki 2009

Yayın serisi

AdıIeee International Conference On Computer Vision

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???12th IEEE International Conference on Computer Vision
Ülke/Bölge!!Japan
ŞehirKyoto
Periyot29/09/092/10/09

Parmak izi

Learning Actions From the Web' araştırma başlıklarına git. Birlikte benzersiz bir parmak izi oluştururlar.

Bundan alıntı yap