Learning Deep Structure-Preserving Image-Text Embeddings [article]

Liwei Wang, Yin Li, Svetlana Lazebnik
2016 arXiv   pre-print
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
more » ... t-to-image retrieval. Our method achieves new state-of-the-art results on the Flickr30K and MSCOCO image-sentence datasets and shows promise on the new task of phrase localization on the Flickr30K Entities dataset.
arXiv:1511.06078v2 fatcat:zagdm4qg3resxfgnv4afq4xyvm