User-Centric Affective Computing of Image Emotion Perceptions

Sicheng Zhao, Hongxun Yao, Wenlong Xie, Xiaolei Jiang

AAAI 2016 pp. 4284-4285

doi:10.1609/AAAI.V30I1.9947 /aaai/2016/zhao2016aaai-user/

Abstract

We propose to predict the personalized emotion perceptions of images for each viewer. Different factors that may influence emotion perceptions, including visual content, social context, temporal evolution, and location influence are jointly investigated via the presented rolling multi-task hypergraph learning. For evaluation, we set up a large scale image emotion dataset from Flickr, named Image-Emotion-Social-Net, with over 1 million images and about 8,000 users. Experiments conducted on this dataset demonstrate the superiority of the proposed method, as compared to state-of-the-art.

PDF AAAI Semantic Scholar

Cite

Text

Zhao et al. "User-Centric Affective Computing of Image Emotion Perceptions." AAAI Conference on Artificial Intelligence, 2016. doi:10.1609/AAAI.V30I1.9947

Markdown

[Zhao et al. "User-Centric Affective Computing of Image Emotion Perceptions." AAAI Conference on Artificial Intelligence, 2016.](https://mlanthology.org/aaai/2016/zhao2016aaai-user/) doi:10.1609/AAAI.V30I1.9947

BibTeX

@inproceedings{zhao2016aaai-user,
  title     = {{User-Centric Affective Computing of Image Emotion Perceptions}},
  author    = {Zhao, Sicheng and Yao, Hongxun and Xie, Wenlong and Jiang, Xiaolei},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2016},
  pages     = {4284-4285},
  doi       = {10.1609/AAAI.V30I1.9947},
  url       = {https://mlanthology.org/aaai/2016/zhao2016aaai-user/}
}