Abstract | ||
---|---|---|
This paper proposes a method for learning joint embeddings of images and text using a two-branch neural network with multiple layers of linear projections followed by nonlinearities. The network is trained using a large-margin objective that combines cross-view ranking constraints with within-view neighborhood structure preservation constraints inspired by metric learning literature. Extensive experiments show that our approach gains significant improvements in accuracy for image-to-text and text-to-image retrieval. Our method achieves new state-of-theart results on the Flickr30K and MSCOCO image-sentence datasets and shows promise on the new task of phrase localization on the Flickr30K Entities dataset. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/CVPR.2016.541 | 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) |
DocType | Volume | Issue |
Conference | abs/1511.06078 | 1 |
ISSN | Citations | PageRank |
1063-6919 | 95 | 1.94 |
References | Authors | |
41 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Liwei Wang | 1 | 1272 | 88.14 |
Yin Li | 2 | 797 | 35.85 |
Svetlana Lazebnik | 3 | 7379 | 449.66 |