| Issue |
MATEC Web Conf.
Volume 277, 2019
2018 International Joint Conference on Metallurgical and Materials Engineering (JCMME 2018)
|
|
|---|---|---|
| Article Number | 02006 | |
| Number of page(s) | 6 | |
| Section | Data and Signal Processing | |
| DOI | https://doi.org/10.1051/matecconf/201927702006 | |
| Published online | 02 April 2019 | |
Semantic representation for visual reasoning
1
School of Automation, University of Electronic Science and Technology of China, Chengdu, 610054, China
2
Geographical & Sustainability Sciences Department, University of Iowa, Iowa City, IA, 52242, USA
3
Department of Modelling, Simulation, and Visualization Engineering, Old Dominion University, Norfolk, VA 23529, USA
* Corresponding author: wenfeng.zheng.cn@gmail.com
In the field of visual reasoning, image features are widely used as the input of neural networks to get answers. However, image features are too redundant to learn accurate characterizations for regular networks. While in human reasoning, abstract description is usually constructed to avoid irrelevant details. Inspired by this, a higher-level representation named semantic representation is introduced in this paper to make visual reasoning more efficient. The idea of the Gram matrix used in the neural style transfer research is transferred here to build a relation matrix which enables the related information between objects to be better represented. The model using semantic representation as input outperforms the same model using image features as input which verifies that more accurate results can be obtained through the introduction of high-level semantic representation in the field of visual reasoning.
© The Authors, published by EDP Sciences, 2019
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.