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.

Date Published: 8 March 2018
PDF: 8 pages
Proc. SPIE 10609, MIPPR 2017: Pattern Recognition and Computer Vision, 106090P (8 March 2018); doi: 10.1117/12.2284665

Published in SPIE Proceedings Vol. 10609:
MIPPR 2017: Pattern Recognition and Computer Vision
Zhiguo Cao; Yuehuang Wang; Chao Cai, Editor(s)