 |
Conference papers
Combining generic and specific information for cross-modal retrieval
Abstract : Cross-modal retrieval increasingly relies on joint statistical models built from large amounts of data represented according to several modalities. However, some information that is poorly represented by these models can be very significant for a retrieval task. We show that, by appropriately identifying and taking such information into account, the results of cross-modal retrieval can be strongly improved. We apply our model to three benchmarks for the text illustration task and find that the more data has misrepresented information, the more our model is comparatively effective.
Cited literature [9 references]
https://hal-cea.archives-ouvertes.fr/cea-01813724
Contributor : Léna Le Roy <>
Submitted on : Wednesday, December 11, 2019 - 5:39:12 PM
Last modification on : Monday, September 7, 2020 - 12:10:03 PM
Long-term archiving on: : Thursday, March 12, 2020 - 11:06:55 PM
Contributor : Léna Le Roy <>
Submitted on : Wednesday, December 11, 2019 - 5:39:12 PM
Last modification on : Monday, September 7, 2020 - 12:10:03 PM
Long-term archiving on: : Thursday, March 12, 2020 - 11:06:55 PM
File
tran15icmr.pdf
Files produced by the author(s)