Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)

TitleDeep Captioning with Multimodal Recurrent Neural Networks (m-RNN)
Publication TypeCBMM Memos
Year of Publication2015
AuthorsMao, J, Xu, W, Yang, Y, Wang, J, Huang, Z, Yuille, A
Number033
Date Published05/07/2015
Publication LanguageEnglish
Abstract

In this paper, we present a multimodal Recurrent Neural Network (m-RNN) model for generating novel image captions. It directly models the probability distribution of generating a word given previous words and an image. Image captions are generated according to this distribution. The model consists of two sub-networks: a deep recurrent neural network for sentences and a deep convolutional network for images. These two sub-networks interact with each other in a multimodal layer to form the whole m-RNN model. The effectiveness of our model is validated on four benchmark datasets (IAPR TC-12, Flickr 8K, Flickr 30K and MS COCO). Our model outperforms the state-of-the-art methods. In addition, the m-RNN model can be applied to retrieval tasks for retrieving images or sentences, and achieves significant performance improvement over the state-of-the-art methods which directly
optimize the ranking objective function for retrieval.

arXiv

arXiv:1412.6632

DSpace@MIT

http://hdl.handle.net/1721.1/100198

Download:  PDF icon CBMM Memo 033.pdf
CBMM Memo No:  033

Research Area: 

CBMM Relationship: 

  • CBMM Funded