Supervised guiding long-short term memory for image caption generation based on object classes

Jian Wang; Zhiguo Cao; Yang Xiao; Xinyuan Qi

doi:10.1117/12.2284665

8 March 2018 Supervised guiding long-short term memory for image caption generation based on object classes

Jian Wang, Zhiguo Cao, Yang Xiao, Xinyuan Qi

Proceedings Volume 10609, MIPPR 2017: Pattern Recognition and Computer Vision; 106090P (2018) https://doi.org/10.1117/12.2284665
Event: Tenth International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR2017), 2017, Xiangyang, China

Abstract

The present models of image caption generation have the problems of image visual semantic information attenuation and errors in guidance information. In order to solve these problems, we propose a supervised guiding Long Short Term Memory model based on object classes, named S-gLSTM for short. It uses the object detection results from R-FCN as supervisory information with high confidence, and updates the guidance word set by judging whether the last output matches the supervisory information. S-gLSTM learns how to extract the current interested information from the image visual se-mantic information based on guidance word set. The interested information is fed into the S-gLSTM at each iteration as guidance information, to guide the caption generation. To acquire the text-related visual semantic information, the S-gLSTM fine-tunes the weights of the network through the back-propagation of the guiding loss. Complementing guidance information at each iteration solves the problem of visual semantic information attenuation in the traditional LSTM model. Besides, the supervised guidance information in our model can reduce the impact of the mismatched words on the caption generation. We test our model on MSCOCO2014 dataset, and obtain better performance than the state-of-the- art models.

Citation Download Citation

Jian Wang, Zhiguo Cao, Yang Xiao, and Xinyuan Qi "Supervised guiding long-short term memory for image caption generation based on object classes", Proc. SPIE 10609, MIPPR 2017: Pattern Recognition and Computer Vision, 106090P (8 March 2018); https://doi.org/10.1117/12.2284665

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Information visualization

Visualization

Visual process modeling

Computer programming

Data modeling

Performance modeling

Seaborgium

Show All Keywords

Keywords/Phrases

Search In:

Publication Years