Learning Object Class Detectors from Weakly Annotated Video

Abstract : Object detectors are typically trained on a large set of still images annotated by bounding-boxes. This paper introduces an approach for learning object detectors from real-world web videos known only to contain objects of a target class. We propose a fully automatic pipeline that localizes objects in a set of videos of the class and learns a detector for it. The approach extracts candidate spatio-temporal tubes based on motion segmentation and then selects one tube per video jointly over all videos. To compare to the state of the art, we test our detector on still images, i.e., Pascal VOC 2007. We observe that frames extracted from web videos can differ significantly in terms of quality to still images taken by a good camera. Thus, we formulate the learning from videos as a domain adaptation task. We show that training from a combination of weakly annotated videos and fully annotated still images using domain adaptation improves the performance of a detector trained from still images alone.
Type de document :
Communication dans un congrès
CVPR 2012 - Conference on Computer Vision and Pattern Recognition, Jun 2012, Providence, RI, United States. IEEE, pp.3282-3289, 2012, 〈10.1109/CVPR.2012.6248065〉
Liste complète des métadonnées

Littérature citée [37 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00695940
Contributeur : Alessandro Prest <>
Soumis le : lundi 2 juillet 2012 - 09:59:33
Dernière modification le : mercredi 11 avril 2018 - 01:58:03
Document(s) archivé(s) le : jeudi 15 décembre 2016 - 19:44:50

Fichier

VO.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Alessandro Prest, Christian Leistner, Javier Civera, Cordelia Schmid, Vittorio Ferrari. Learning Object Class Detectors from Weakly Annotated Video. CVPR 2012 - Conference on Computer Vision and Pattern Recognition, Jun 2012, Providence, RI, United States. IEEE, pp.3282-3289, 2012, 〈10.1109/CVPR.2012.6248065〉. 〈hal-00695940v2〉

Partager

Métriques

Consultations de la notice

576

Téléchargements de fichiers

1106