Learning object class detectors from weakly annotated video
Top Cited Papers
- 1 June 2012
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3282-3289
- https://doi.org/10.1109/cvpr.2012.6248065
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.Keywords
This publication has 29 references indexed in Scilit:
- Large-scale live active learning: Training object detectors with crawled data and crowdsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- P-N learning: Bootstrapping binary classifiers by structural constraintsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Multiple kernels for object detectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Combining efficient object localization and image classificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- A walk through the web’s video clipsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- On-line Boosting and VisionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Rapid object detection using a boosted cascade of simple featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Histograms of Oriented Gradients for Human DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- LOCUS: learning object classes with unsupervised segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Object class recognition by unsupervised scale-invariant learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003