Name
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 uni-directional ranking examples. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1145/2502081.2502097 | ACM Multimedia 2001 |
Keywords | Field | DocType |
image-query-text ranking example,uni-directional ranking example,bi-directional ranking mean,cross-media semantic representation,latent space embedding,certain ranking criterion,listwise ranking problem,bi-directional ranking example,text-query-image ranking example,general cross-media ranking algorithm,bi-directional listwise ranking loss | Learning to rank,Feature vector,Embedding,Ranking SVM,Ranking,Computer science,Multimedia information retrieval,Ranking (information retrieval),Artificial intelligence,Semantic representation,Machine learning | Conference |
Citations | PageRank | References |
49 | 1.20 | 29 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Fei Wu | 1 | 2209 | 153.88 |
| Xinyan Lu | 2 | 84 | 3.14 |
| Zhongfei (Mark) Zhang | 3 | 2451 | 164.30 |
| Shuicheng Yan | 4 | 9701 | 359.54 |
| Yong Rui | 5 | 7052 | 449.08 |
| Yue-Ting Zhuang | 6 | 3549 | 216.06 |