Recurrent Multimodal Interaction for Referring Image Segmentation
Name
CBMM-Memo-079.pdf
Size
10.16 MB
Format
Adobe PDF
Checksum (MD5)
4c12f504f6adfeda6e0adcdf488190b1
Author(s)
Liu, Chenxi
Lin, Zhe
Shen, Xiaohui
Yang, Jimei
Lu, Xin
Yuille, Alan L.
Date Issued
May 10, 2018
Publisher
Center for Brains, Minds and Machines (CBMM)
Series/Report no.
CBMM Memo Series;079
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.
Persistent DSpace Link
