Recurrent Multimodal Interaction for Referring Image Segmentation

Abstract

In this paper we are interested in the problem of image segmentation given natural language descriptions, i.e. referring expressions. Existing works tackle this problem by first modeling images and sentences independently and then segment images by combining these two types of representations. We argue that learning word-to-image interaction is more native in the sense of jointly modeling two modalities for the image segmentation task, and we propose convolutional multimodal LSTM to encode the sequential interactions between individual words, visual information, and spatial information. We show that our proposed model outperforms the baseline model on benchmark datasets. In addition, we analyze the intermediate output of the proposed multimodal LSTM approach and empirically explain how this approach enforces a more effective word-to-image interaction.

To appear in ICCV 2017. See http://www.cs.jhu.edu/~cxliu/ for code and supplementary material

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Recurrent Models of Visual Attention
• Fully Convolutional Networks for Semantic Segmentation
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
• Unsupervised Learning for Physical Interaction through Video Prediction
• Multimodal Residual Learning for Visual QA
• Review Networks for Caption Generation
• Attention Correctness in Neural Image Captioning
• Modeling Context in Referring Expressions
• Segmentation from Natural Language Expressions
• Utilizing Large Scale Vision and Text Datasets for Image Segmentation from Referring Expressions
• MAT: A Multimodal Attentive Translator for Image Captioning