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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

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 : Thursday, December 12, 2019 - 9:42:15 AM

File

tran15icmr.pdf
Files produced by the author(s)

Identifiers

Citation

T.Q.N. Tran, H. Le Borgne, M. Crucianu. Combining generic and specific information for cross-modal retrieval. ICMR '15 Proceedings of the 5th ACM on International Conference on Multimedia Retrieval, Jun 2015, Shangai, China. pp.551-554, ⟨10.1145/2671188.2749348⟩. ⟨cea-01813724⟩

Share

Metrics

Record views

95

Files downloads

2