An Effective Visual Attention Mechanism

DOI

10.2991/cnci-19.2019.47How to use a DOI?

Keywords

Visual Sentiment Analysis, Local Image Re- gions, Attention Mechanism.

Abstract

Visual sentiment analysis is mainly to study the emotional response of the observer after reading the image. Now, as images become exploding in social networks, the need for visual sentiment analysis is increasing. A major problem with the existing image sentiment analysis is that the emotional label is often related to the local area of the image rather than the whole, but the existing algorithms cannot detect them, so the prediction effect is very poor. In this paper, we propose an attention mechanism to detect areas that are closely related to visual emotions. The experimental results show that the performance of the sentiment classifier based on the detection area has been significantly improved.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zhuanghui Wu
AU  - Guoheng Huang
AU  - Lianglun Cheng
PY  - 2019/05
DA  - 2019/05
TI  - An Effective Visual Attention Mechanism
BT  - Proceedings of the 2019 International Conference on Computer, Network, Communication and Information Systems (CNCI 2019)
PB  - Atlantis Press
SP  - 320
EP  - 325
SN  - 2352-538X
UR  - https://doi.org/10.2991/cnci-19.2019.47
DO  - 10.2991/cnci-19.2019.47
ID  - Wu2019/05
ER  -