Learning object class detectors from weakly annotated video

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Prest, Alessandro, Leistner, C., Civera, J., Schmid, C., Ferrari, V.
Format: Conference Proceeding
Language:English
Subjects:
Detectors
Electron tubes
Hidden Markov models
Image segmentation
Motion segmentation
Tracking
Training
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1063-6919
DOI:10.1109/CVPR.2012.6248065