Learning object categories from Google's image search
Authors:
- L. Fei-FeiLFL. Fei-Fei
- P. PeronaPPP. Perona
- A. ZissermanAZA. Zisserman
Top Cited Papers
- 1 January 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (15505499) , 1816
Abstract
Current approaches to object category recognition require datasets of training images to be manually prepared, with varying degrees of supervision. We present an approach that can learn an object category from just its name, by utilizing the raw output of image search engines available on the Internet. We develop a new model, TSI-pLSA, which extends pLSA (as applied to visual words) to include spatial information in a translation and scale invariant manner. Our approach can handle the high intra-class variability and large proportion of unrelated images returned by search engines. We evaluate tire models on standard test sets, showing performance competitive with existing methods trained on hand prepared datasetsKeywords
This publication has 14 references indexed in Scilit:
- Rapid object detection using a boosted cascade of simple features2005
- Shape Matching and Object Recognition Using Low Distortion Correspondences2005
- Learning methods for generic object recognition with invariance to pose and lighting2004
- Sharing features: efficient boosting procedures for multiclass object detection2004
- Video Google: a text retrieval approach to object matching in videos2003
- Object recognition with informative features and linear classification2003
- Saliency, Scale and Image DescriptionInternational Journal of Computer Vision, 2001
- Indexing based on scale invariant interest points2001
- Probabilistic latent semantic indexing1999
- Object recognition from local scale-invariant features1999