Please use this identifier to cite or link to this item:
|Title:||Cross-media semantic representation via bi-directional learning to rank|
|Keywords:||Bi-directional learning to rank|
Latent space embedding
|Source:||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. https://doi.org/10.1145/2502081.2502097|
|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.|
|Source Title:||MM 2013 - Proceedings of the 2013 ACM Multimedia Conference|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Dec 13, 2017
checked on Dec 9, 2017
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.