Visual Sentiment Analysis（视觉情感计算·南开大学）
Visual sentiment analysis (VSA) from images has attracted significant attention with the increasing tendency of expressing opinions through posting images on social media. We focus on the challenging problem of automatic assessment of image sentiment, which has many applications, e.g. education, entertainment, advertisement, etc.
Here, the resources related to our recent work in this hot topic, including paper, code, data, model are released to the community. Please feel free to drop me an email (yangjufeng AT nankai DOT edu DOT cn) if you have any questions.
[Return to NKU Computer Vision Lab]
Region-based Single Dominant Label Classification
Demo: Coming soon ....
- Jufeng Yang, Dongyu She, Yu-Kun Lai, Paul L. Rosin, Ming-Hsuan Yang, Weakly Supervised Coupled Networks for Visual Sentiment Analysis, CVPR, 2018, Spotlight [Paper][Code][BibTex]
- Jufeng Yang, Dongyu She, Ming Sun, Ming-Ming Cheng, Paul L. Rosin, Liang Wang, Visual Sentiment Prediction based on Automatic Discovery of Affective Regions, TMM, 2018 [Paper][Code][BibTex]
- Ming Sun, Jufeng Yang, Kai Wang, Hui Shen, Discovering Affective Regions in Deep Convolutional Neural Networks for Visual Sentiment Prediction, ICME, 2016 [Paper][Code][BibTex]
Label Distribution Prediction
Datasets: Flickr_LDL, Twitter_LDL, Readme
- Jufeng Yang, Dongyu She, Ming Sun, Joint Image Emotion Classification and Distribution Learning via Deep Convolutional Neural Network, IJCAI, 2017, Oral [Paper][Code][BibTex]
- Jufeng Yang, Ming Sun, Xiaoxiao Sun, Learning Visual Sentiment Distributions via Augmented Conditional Probability Neural Network, AAAI, 2017, [Paper][Code][BibTex]
Applications & Related Topics