Image captioning via semantic element embedding
Publication Type
Journal Article
Publication Date
6-2020
Abstract
Image caption approaches that use the global Convolutional Neural Network (CNN) features are not able to represent and describe all the important elements in complex scenes. In this paper, we propose to enrich the semantic representations of images and update the language model by proposing semantic element embedding. For the semantic element discovery, an object detection module is used to predict regions of the image, and a captioning model, Long Short-Term Memory (LSTM), is employed to generate local descriptions for these regions. The predicted descriptions and categories are used to generate the semantic feature, which not only contains detailed information but also shares a word space with descriptions, and thus bridges the modality gap between visual images and semantic captions. We further integrate the CNN feature with the semantic feature into the proposed Element Embedding LSTM (EE-LSTM) model to predict a language description. Experiments on MS COCO datasets demonstrate that the proposed approach outperforms conventional caption methods and is flexible to combine with baseline models to achieve superior performance. (C) 2019 Published by Elsevier B.V.
Keywords
Image captioning, Element embedding, CNN, LSTM
Discipline
Information Security
Research Areas
Information Systems and Management
Publication
Neurocomputing
Volume
395
First Page
212
Last Page
221
ISSN
0925-2312
Identifier
10.1016/j.neucom.2018.02.112
Publisher
Elsevier
Citation
ZHANG, Xiaodan; HE, Shengfeng; SONG, Xinhang; LAU, Rynson W.H.; JIAO, Jianbin; and YE, Qixiang.
Image captioning via semantic element embedding. (2020). Neurocomputing. 395, 212-221.
Available at: https://ink.library.smu.edu.sg/sis_research/7863
Additional URL
https://doi.org/10.1109/10.1016/j.neucom.2018.02.112