Joint Learning of Distributed Representations for Images and Texts
arXiv:1504.03083
Abstract
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.
arXiv commentThis 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
References in corpus (5)
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Deep Fragment Embeddings for Bidirectional Image Sentence Mapping
- CNN Features off-the-shelf: an Astounding Baseline for Recognition
- A Convolutional Neural Network for Modelling Sentences
- Modelling, Visualising and Summarising Documents with a Single Convolutional Neural Network