Understanding The Aesthetic Styles of Social Images
| Autor: | Wentao Han, Yufan Hou, Jia Jia, Yihui Ma, Yaohua Bu |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Painting
Computer science business.industry 05 social sciences 010501 environmental sciences Space (commercial competition) computer.software_genre Aesthetic perception 01 natural sciences Visualization Image (mathematics) 0502 economics and business Benchmark (computing) Artificial intelligence 050207 economics business computer Natural language processing 0105 earth and related environmental sciences |
| Zdroj: | ICASSP |
| Popis: | Aesthetic perception is nearly the most direct impact people could receive from images. Recent research on image understanding is mainly focused on image analysis, recognition and classification, regardless of the aesthetic meanings embedded in images. In this paper, we systematically study the problem of understanding the aesthetic styles of social images. First, we build a two-dimensional Image Aesthetic Space (IAS) to describe image aesthetic styles quantitatively and universally. Then, we propose a Bimodal Deep Autoen-coder with Cross Edges (BDA-CE) to deeply fuse the social image related features (i.e. images' visual features, tags' textual features). Connecting BDA-CE with a regression model, we are able to map the features to the IAS. The experimental results on the benchmark dataset we build with 120 thousand Flickr images show that our model outperforms (+5.5% in terms of MSE) alternative baselines. Furthermore, we conduct an interesting case study to demonstrate the advantages of our methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|