Chinese Paintings Emotion Recognition Based on End-to-end Weakly Supervised Learning Network Model

Emotion recognition research is a hot spot in computer vision, and the study of Chinese painting emotion is of great significance to the appreciation of works. In order to improve the recognition performance, the traditional convolutional neural network used to extract local information of Chinese p...

Full description

Saved in:
Bibliographic Details
Main Authors: LU Ke-bin, YIN Shou-lin
Format: Article
Language:zho
Published: Harbin University of Science and Technology Publications 2022-02-01
Series:Journal of Harbin University of Science and Technology
Subjects:
Online Access:https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2058
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849705630878662656
author LU Ke-bin
YIN Shou-lin
author_facet LU Ke-bin
YIN Shou-lin
author_sort LU Ke-bin
collection DOAJ
description Emotion recognition research is a hot spot in computer vision, and the study of Chinese painting emotion is of great significance to the appreciation of works. In order to improve the recognition performance, the traditional convolutional neural network used to extract local information of Chinese painting will lead to the loss of effective information. Therefore, the end-to-end weakly supervised learning network is proposed to recognize the Chinese painting emotion.The proposed learning network consists of two classification modules and one affective intensity prediction module.First, the intensity prediction flow is constructed on the basis of improved feature pyramid network to extract multi-level features.The gradient-based class activation map technique is used to generate pseudo-intensity maps from the first classification stream to guide the emotional intensity learning of the proposed network. The predicted intensity map is input into the second classification stream for the final Chinese painting emotion recognition. Finally, the proposed method is verified on the open data set.The experiment results show that the proposed network has improved the confounding matrix, average classification accuracy and average emotion recognition rate by 10%, 15% and 13% respectively.
format Article
id doaj-art-b96463b8ebc7444591468df73f4d9083
institution DOAJ
issn 1007-2683
language zho
publishDate 2022-02-01
publisher Harbin University of Science and Technology Publications
record_format Article
series Journal of Harbin University of Science and Technology
spelling doaj-art-b96463b8ebc7444591468df73f4d90832025-08-20T03:16:25ZzhoHarbin University of Science and Technology PublicationsJournal of Harbin University of Science and Technology1007-26832022-02-012701697810.15938/j.jhust.2022.01.010Chinese Paintings Emotion Recognition Based on End-to-end Weakly Supervised Learning Network ModelLU Ke-bin0YIN Shou-lin1College of Applied Engineering, Henan University of Science and Technology, Sanmenxia 472000, China;Sanmenxia Polytechnic, Sanmenxia 472000, ChinaSchool of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150001, China;Institute of Imaging and Information Technology, Harbin Institute of Technology, Harbin 150001, ChinaEmotion recognition research is a hot spot in computer vision, and the study of Chinese painting emotion is of great significance to the appreciation of works. In order to improve the recognition performance, the traditional convolutional neural network used to extract local information of Chinese painting will lead to the loss of effective information. Therefore, the end-to-end weakly supervised learning network is proposed to recognize the Chinese painting emotion.The proposed learning network consists of two classification modules and one affective intensity prediction module.First, the intensity prediction flow is constructed on the basis of improved feature pyramid network to extract multi-level features.The gradient-based class activation map technique is used to generate pseudo-intensity maps from the first classification stream to guide the emotional intensity learning of the proposed network. The predicted intensity map is input into the second classification stream for the final Chinese painting emotion recognition. Finally, the proposed method is verified on the open data set.The experiment results show that the proposed network has improved the confounding matrix, average classification accuracy and average emotion recognition rate by 10%, 15% and 13% respectively.https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2058emotion recognition in chinese paintingend-to-end weakly supervised learning networkemotion intensitymapgradient-based class activation map
spellingShingle LU Ke-bin
YIN Shou-lin
Chinese Paintings Emotion Recognition Based on End-to-end Weakly Supervised Learning Network Model
Journal of Harbin University of Science and Technology
emotion recognition in chinese painting
end-to-end weakly supervised learning network
emotion intensitymap
gradient-based class activation map
title Chinese Paintings Emotion Recognition Based on End-to-end Weakly Supervised Learning Network Model
title_full Chinese Paintings Emotion Recognition Based on End-to-end Weakly Supervised Learning Network Model
title_fullStr Chinese Paintings Emotion Recognition Based on End-to-end Weakly Supervised Learning Network Model
title_full_unstemmed Chinese Paintings Emotion Recognition Based on End-to-end Weakly Supervised Learning Network Model
title_short Chinese Paintings Emotion Recognition Based on End-to-end Weakly Supervised Learning Network Model
title_sort chinese paintings emotion recognition based on end to end weakly supervised learning network model
topic emotion recognition in chinese painting
end-to-end weakly supervised learning network
emotion intensitymap
gradient-based class activation map
url https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2058
work_keys_str_mv AT lukebin chinesepaintingsemotionrecognitionbasedonendtoendweaklysupervisedlearningnetworkmodel
AT yinshoulin chinesepaintingsemotionrecognitionbasedonendtoendweaklysupervisedlearningnetworkmodel