Object Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary

P. Sahin, Kobus Barnard, João Freitas, D. Forsyth · European Conference on Computer Vision · 2002

Summary

This work shows how to cluster words that individually are difficult to predict into clusters that can be predicted well, and cannot predict the distinction between train and locomotive using the current set of features, but can predict the underlying concept.

Published: 2002-05-28
Cited by: 1,880
References: 11
DOI: https://doi.org/10.1007/3-540-47979-1_7
Semantic Scholar: https://api.semanticscholar.org/CorpusID:12561212

References

Computer Vision: A Modern ApproachDavid Forsyth, Jean Ponce — 2002
Multiple-Instance Learning for Natural Scene ClassificationOded Maron, Aparna Lakshmi Ratan — 1998
Learning from AmbiguityOded Maron, Tomás Lozano‐Pérez — 1998
Book Reviews: Foundations of Statistical Natural Language ProcessingChristopher D. Manning, Hinrich Schütze — 1999
End-User Searching Challenges Indexing Practices in the Digital Newspaper Photo ArchiveMarjo Markkula, Eero Sormunen — 2004
Learning the semantics of words and picturesKobus Barnard, David Forsyth — 2001
The Mathematics of Statistical Machine Translation: Parameter EstimationPeter F. Brown, Vincent J. Della Pietra, Stephen A. Della Pietra — 1993
Empirical Methods for Exploiting Parallel TextsI. Dan Melamed — 2001
Normalized cuts and image segmentationJianbo Shi, Jitendra Malik — 1997
Clustering artKobus Barnard, Pınar Duygulu, David Forsyth — 2001
Book Reviews: Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech RecognitionDan Jurafsky, James H. Martin — 2000

Cited by

Context Dependent Automatic Textile Image Annotation Using Networked KnowledgeYosuke Furukawa, Yusuke Kamoi, Tatsuya Sato — 2007
Image annotation and retrieval based on multi-modal feature clustering and similarity propagation.Mohamed Ismail — 2011
Can a Probabilistic Image Annotation System be Improved Using a Co-Occurrence Approach?Ainhoa Llorente, Stefan Rüger — 2008
Automatic Generation of Semantic Fields for Annotating Web ImagesGang Wang, Tat‐Seng Chua, Chong‐Wah Ngo — 2010
The Sound of an Album Cover: A Probabilistic Approach to MultimediaEric Brochu, Nando de Freitas, Kejie Bao — 2003
Leveraging Dominant Language Image Tags for Automatic Image Annotation in Minor LanguagesHjalmar Wennerström — 2010
Parallelizing support vector machines for scalable image annotationNasullah Khalid Alham — 2011
Model Summaries for Location-related ImagesAhmet Aker, Robert Gaizauskas — 2010
Information fusion techniques for automatic image annotationF. Vella, Chin-Hui Lee — 2007
SLED: Semantic Label Embedding Dictionary Representation for Multilabel Image AnnotationXiaochun Cao, Hua Zhang, Xiaojie Guo — 2015
Robust statistical techniques for the categorization of images using associated textKathleen McKeown, Carl Sable — 2003
Multimedia Information Extraction in Ontology-based Semantic Annotation of Product CataloguesRoberto Bartolini, Emiliano Giovannetti, Simone Marchi — 2006
Building and Using Knowledge Models for Semantic Image AnnotationHichem Bannour, AIGUIER, Marc — 2013
On the creation of visual models for keywords through crowdsourcingΖήνωνας Θεοδοσίου, Nicolas Tsapatsoulis — 2012
Integrating Computer Vision in Web Based Context RecognitionAviv Segev, Ilan Shimshoni — 2006
Subspace-based Semantic Concept Detection and Retrieval for Multimedia Information SystemsChao Chen — 2012
Multilabel Classification with Label Correlations and Missing LabelsWei Bi, James T. Kwok — 2014
Semantic Video Annotation using Background Knowledge and Similarity-based Video RetrievalAinhoa Llorente, Srđan Zagorac, Suzanne Little — 2008
Co-training for search-based automatic image annotationYufeng Zhao, Yao Zhao, Zhenfeng Zhu — 2008
Novel Application of Neutrosophic Logic in Classifiers Evaluated under Region-Based Image Categorization SystemWen Ju — 2011

Related papers

No related papers recorded.