Abstract | ||
---|---|---|
Content is increasingly available in multiple modalities (such as images, text, and video), each of which provides a different representation of some entity. The cross-modal retrieval problem is: given the representation of an entity in one modality, find its best representation in all other modalities. We propose a novel approach to this problem based on pairwise classification. The approach seamlessly applies to both the settings where ground-truth annotations for the entities are absent and present. In the former case, the approach considers both positive and unlabelled links that arise in standard cross-modal retrieval datasets. Empirical comparisons show improvements over state-of-theart methods for cross-modal retrieval. |
Year | Venue | Field |
---|---|---|
2015 | SDM | Modalities,Pairwise comparison,Computer science,Multiple modalities,Artificial intelligence,Modal,Machine learning |
DocType | Citations | PageRank |
Conference | 3 | 0.37 |
References | Authors | |
17 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Aditya Krishna Menon | 1 | 709 | 40.01 |
Didi Surian | 2 | 76 | 7.52 |
Sanjay Chawla | 3 | 1372 | 105.09 |