Please use this identifier to cite or link to this item:
https://doi.org/10.1145/2502081.2502097
DC Field | Value | |
---|---|---|
dc.title | Cross-media semantic representation via bi-directional learning to rank | |
dc.contributor.author | Wu, F. | |
dc.contributor.author | Lu, X. | |
dc.contributor.author | Zhang, Z. | |
dc.contributor.author | Yan, S. | |
dc.contributor.author | Rui, Y. | |
dc.contributor.author | Zhuang, Y. | |
dc.date.accessioned | 2014-06-19T03:04:26Z | |
dc.date.available | 2014-06-19T03:04:26Z | |
dc.date.issued | 2013 | |
dc.identifier.citation | Wu, F.,Lu, X.,Zhang, Z.,Yan, S.,Rui, Y.,Zhuang, Y. (2013). Cross-media semantic representation via bi-directional learning to rank. MM 2013 - Proceedings of the 2013 ACM Multimedia Conference : 877-886. ScholarBank@NUS Repository. <a href="https://doi.org/10.1145/2502081.2502097" target="_blank">https://doi.org/10.1145/2502081.2502097</a> | |
dc.identifier.isbn | 9781450324045 | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/69768 | |
dc.description.abstract | In multimedia information retrieval, most classic approaches tend to represent different modalities of media in the same feature space. Existing approaches take either one-to-one paired data or uni-directional ranking examples (i.e., utilizing only text-query-image ranking examples or image-query text ranking examples) as training examples, which do not make full use of bi-directional ranking examples (bi-directional ranking means that both text-query-image and image-query text ranking examples are utilized in the training period) to achieve a better performance. In this paper, we consider learning a cross-media representation model from the perspective of optimizing a listwise ranking problem while taking advantage of bi-directional ranking examples. We propose a general cross-media ranking algorithm to optimize the bi-directional listwise ranking loss with a latent space embedding, which we call Bi-directional Cross-Media Semantic Representation Model (Bi-CMSRM). The latent space embedding is discriminatively learned by the structural large margin learning for optimization with certain ranking criteria (mean average precision in this paper) directly. We evaluate Bi-CMSRM on the Wikipedia and NUS-WIDE datasets and show that the utilization of the bi-directional ranking examples achieves a much better performance than only using the unidirectional ranking examples. Copyright © 2013 ACM. | |
dc.description.uri | http://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1145/2502081.2502097 | |
dc.source | Scopus | |
dc.subject | Bi-directional learning to rank | |
dc.subject | Cross-media representation | |
dc.subject | Latent space embedding | |
dc.type | Conference Paper | |
dc.contributor.department | ELECTRICAL & COMPUTER ENGINEERING | |
dc.description.doi | 10.1145/2502081.2502097 | |
dc.description.sourcetitle | MM 2013 - Proceedings of the 2013 ACM Multimedia Conference | |
dc.description.page | 877-886 | |
dc.identifier.isiut | NOT_IN_WOS | |
Appears in Collections: | Staff Publications |
Show simple item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.