Combining generic and specific information for cross-modal retrieval - Archive ouverte HAL Access content directly
Conference Papers Year : 2015

Combining generic and specific information for cross-modal retrieval

(1) , (1) , (2)
1
2

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.
Fichier principal
Vignette du fichier
tran15icmr.pdf (241.66 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

cea-01813724 , version 1 (11-12-2019)

Identifiers

Cite

Thi Quynh Nhi Tran, Hervé 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⟩
74 View
84 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More