This technical report provides extra details of the deep multimodal similarity model (DMSM) which was proposed in (Fang et al. 2015, arXiv:1411.4952). The model is trained via maximizing global semantic similarity between images and their captions in natural language using the public Microsoft COCO database, which consists of a large set of images and their corresponding captions. The learned representations attempt to capture the combination of various visual concepts and cues.
@article{arxiv.1504.03083,
title = {Joint Learning of Distributed Representations for Images and Texts},
author = {Xiaodong He and Rupesh Srivastava and Jianfeng Gao and Li Deng},
journal= {arXiv preprint arXiv:1504.03083},
year = {2015}
}
Comments
This is a previous tech report of a part of the work of arXiv:1411.4952. In order to avoid confusion, we'd like to withdraw this report from arXiv