Visual affective classification by combining visual and text features.
Affective analysis of images in social networks has drawn much attention, and the texts surrounding images are proven to provide valuable semantic meanings about image content, which can hardly be represented by low-level visual features. In this paper, we propose a novel approach for visual affecti...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2017-01-01
|
Series: | PLoS ONE |
Online Access: | http://europepmc.org/articles/PMC5574549?pdf=render |
id |
doaj-6c2fb5da41ff4d7197957142a9a7c3b7 |
---|---|
record_format |
Article |
spelling |
doaj-6c2fb5da41ff4d7197957142a9a7c3b72020-11-24T21:30:01ZengPublic Library of Science (PLoS)PLoS ONE1932-62032017-01-01128e018301810.1371/journal.pone.0183018Visual affective classification by combining visual and text features.Ningning LiuKai WangXin JinBoyang GaoEmmanuel DellandréaLiming ChenAffective analysis of images in social networks has drawn much attention, and the texts surrounding images are proven to provide valuable semantic meanings about image content, which can hardly be represented by low-level visual features. In this paper, we propose a novel approach for visual affective classification (VAC) task. This approach combines visual representations along with novel text features through a fusion scheme based on Dempster-Shafer (D-S) Evidence Theory. Specifically, we not only investigate different types of visual features and fusion methods for VAC, but also propose textual features to effectively capture emotional semantics from the short text associated to images based on word similarity. Experiments are conducted on three public available databases: the International Affective Picture System (IAPS), the Artistic Photos and the MirFlickr Affect set. The results demonstrate that the proposed approach combining visual and textual features provides promising results for VAC task.http://europepmc.org/articles/PMC5574549?pdf=render |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ningning Liu Kai Wang Xin Jin Boyang Gao Emmanuel Dellandréa Liming Chen |
spellingShingle |
Ningning Liu Kai Wang Xin Jin Boyang Gao Emmanuel Dellandréa Liming Chen Visual affective classification by combining visual and text features. PLoS ONE |
author_facet |
Ningning Liu Kai Wang Xin Jin Boyang Gao Emmanuel Dellandréa Liming Chen |
author_sort |
Ningning Liu |
title |
Visual affective classification by combining visual and text features. |
title_short |
Visual affective classification by combining visual and text features. |
title_full |
Visual affective classification by combining visual and text features. |
title_fullStr |
Visual affective classification by combining visual and text features. |
title_full_unstemmed |
Visual affective classification by combining visual and text features. |
title_sort |
visual affective classification by combining visual and text features. |
publisher |
Public Library of Science (PLoS) |
series |
PLoS ONE |
issn |
1932-6203 |
publishDate |
2017-01-01 |
description |
Affective analysis of images in social networks has drawn much attention, and the texts surrounding images are proven to provide valuable semantic meanings about image content, which can hardly be represented by low-level visual features. In this paper, we propose a novel approach for visual affective classification (VAC) task. This approach combines visual representations along with novel text features through a fusion scheme based on Dempster-Shafer (D-S) Evidence Theory. Specifically, we not only investigate different types of visual features and fusion methods for VAC, but also propose textual features to effectively capture emotional semantics from the short text associated to images based on word similarity. Experiments are conducted on three public available databases: the International Affective Picture System (IAPS), the Artistic Photos and the MirFlickr Affect set. The results demonstrate that the proposed approach combining visual and textual features provides promising results for VAC task. |
url |
http://europepmc.org/articles/PMC5574549?pdf=render |
work_keys_str_mv |
AT ningningliu visualaffectiveclassificationbycombiningvisualandtextfeatures AT kaiwang visualaffectiveclassificationbycombiningvisualandtextfeatures AT xinjin visualaffectiveclassificationbycombiningvisualandtextfeatures AT boyanggao visualaffectiveclassificationbycombiningvisualandtextfeatures AT emmanueldellandrea visualaffectiveclassificationbycombiningvisualandtextfeatures AT limingchen visualaffectiveclassificationbycombiningvisualandtextfeatures |
_version_ |
1725964462450540544 |