%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 01:20:41 PM

@INPROCEEDINGS{monayACM:2003,
         author = {Monay, Florent and Gatica-Perez, Daniel},
       projects = {Idiap},
          title = {On Image Auto-Annotation with Latent Space Models},
      booktitle = {Proc. ACM Int. Conf. on Multimedia (ACM MM)},
           year = {2003},
           note = {IDIAP-RR 03-31},
       crossref = {monay01},
       abstract = {Image auto-annotation, i.e., the association of words to whole images, has attracted considerable attention. In particular, unsupervised, probabilistic latent variable models of text and image features have shown encouraging results, but their performance with respect to other approaches remains unknown. In this paper, we apply and compare two simple latent space models commonly used in text analysis, namely Latent Semantic Analysis (LSA) and Probabilistic LSA (PLSA). Annotation strategies for each model are discussed. Remarkably, we found that, on a 8000-image dataset, a classic LSA model defined on keywords and a very basic image representation performed as well as much more complex, state-of-the-art methods. Furthermore, non-probabilistic methods (LSA and direct image matching) outperformed PLSA on the same dataset.},
            pdf = {https://publications.idiap.ch/attachments/papers/2003/monay-acm-sp054.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/papers/2003/monay-acm-sp054.ps.gz},
ipdmembership={vision},
}



crossreferenced publications: 
@TECHREPORT{monay01,
         author = {Monay, Florent and Gatica-Perez, Daniel},
       projects = {Idiap},
          title = {On Automatic Annotation of Images with Latent Space Models},
           type = {Idiap-RR},
         number = {Idiap-RR-31-2003},
           year = {2003},
    institution = {IDIAP},
           note = {Published in ``Proc. ACM Multimedia 2003'', 2003},
       abstract = {Image auto-annotation, i.e., the association of words to whole images, has attracted considerable attention. In particular, unsupervised, probabilistic latent variable models of text and image features have shown encouraging results, but their performance with respect to other approaches remains unknown. In this paper, we apply and compare two simple latent space models commonly used in text analysis, namely Latent Semantic Analysis (LSA) and Probabilistic LSA (PLSA). Annotation strategies for each model are discussed. Remarkably, we found that, on a 8000-image dataset, a classic LSA model defined on keywords and a very basic image representation performed as well as much more complex, state-of-the-art methods. Furthermore, non-probabilistic methods (LSA and direct image matching) outperformed PLSA on the same dataset.},
            pdf = {https://publications.idiap.ch/attachments/reports/2003/rr03-31.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2003/rr03-31.ps.gz},
ipdmembership={vision},
}