Object recognition by scene alignment

Bryan C. Russell, Antonio Torralba, Ce Liu, Rob Fergus, William T. Freeman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Current object recognition systems can only recognize a limited number of object categories; scaling up to many categories is the next challenge. We seek to build a system to recognize and localize many different object categories in complex scenes. We achieve this through a simple approach: by matching the input image, in an appropriate representation, to images in a large training set of labeled images. Due to regularities in object identities across similar scenes, the retrieved matches provide hypotheses for object identities and locations. We build a probabilistic model to transfer the labels from the retrieval set to the input image. We demonstrate the effectiveness of this approach and study algorithm component contributions using held-out test sets from the LabelMe database.

Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference
PublisherNeural Information Processing Systems
ISBN (Print)160560352X, 9781605603520
StatePublished - 2008
Event21st Annual Conference on Neural Information Processing Systems, NIPS 2007 - Vancouver, BC, Canada
Duration: Dec 3 2007Dec 6 2007

Publication series

NameAdvances in Neural Information Processing Systems 20 - Proceedings of the 2007 Conference

Other

Other21st Annual Conference on Neural Information Processing Systems, NIPS 2007
Country/TerritoryCanada
CityVancouver, BC
Period12/3/0712/6/07

ASJC Scopus subject areas

  • Information Systems

Fingerprint

Dive into the research topics of 'Object recognition by scene alignment'. Together they form a unique fingerprint.

Cite this