.png){kind=icon}
返回
Visual sentiment analysis using data-augmented deep transfer learning techniques
.png){kind=icon}
PRE
AI
DOI：10.1007/s00530-024-01308-w.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The use of visual content to express emotions on social media platforms has become increasingly popular. Visual sentiment analysis can be used to understand the sentiment conveyed by the users using images. Compared to text, visual sentiment analysis is a challenging task since images are a more condensed form of data, have ambiguity and do not have explicit textual clues. Recently, a few studies used deep transfer learning techniques for visual sentiment analysis but the results reported can be significantly improved. In this research paper, we introduce a novel architecture that combines data augmentation and transfer learning. Our approach involves feature fusion of the pretrained VGG16 and MobileNetV1 models, followed by fine-tuning using an SVM classifier using augmented training data. For evaluation, we used two image datasets. To augment these datasets, we apply various techniques. The proposed model is also compared with three other transfer techniques, as well as four machine learning models (excluding SVM). VGG16+MobileNetV1-SVM has the best accuracy of 96% and recall of 99% for both datasets. Compared to other studies that also employed the same dataset, the proposed model produced the best results.
Keyword:
Visual sentiment analysis
Feature fusion
VGG16
Data augmentation
Deep and transfer learning
期刊
IF:
3.1
论文数:
2.8K
被引数:
2.7K
机构
暂无机构信息
引用论文
Quality aspects vs consumption values: What affects intention to book hotels in the post-Covid era?
PREAI
分享收藏3D Integrated 300°C Tunable RF Oscillator exploiting AlGaN/GaN HEMT for High Temperature Applications基于AlGaN/GaN HEMT的高温应用3D集成300°C可调射频振荡器
PREAI
分享收藏
A novel and efficient xanthenic dye–organometallic ion‐pair complex for photoinitiating polymerization一种用于光引发聚合的新型高效的黄原胶染料-有机金属离子对配合物
PREAI
分享收藏Pyruvate Occupancy in the Carboxyl Transferase Domain of Pyruvate Carboxylase Facilitates Product Release from the Biotin Carboxylase Domain through an Intermolecular Mechanism.png)
Biochemistry
BiochemistryIF0
PREAI
分享收藏Selective Prins Reaction of Styrenes and Formaldehyde Catalyzed by 2,6-Di-tert-butylphenoxy(difluoro)boraneSynthesis
SynthesisIF0
PREAI
分享收藏分享收藏
查看更多内容