Affordable Access

deepdyve-link
Publisher Website

Deep Aesthetic Quality Assessment With Semantic Information.

Authors
  • Kao, Yueying
  • He, Ran
  • Huang, Kaiqi
Type
Published Article
Journal
IEEE Transactions on Image Processing
Publisher
Institute of Electrical and Electronics Engineers
Publication Date
Mar 01, 2017
Volume
26
Issue
3
Pages
1482–1495
Identifiers
DOI: 10.1109/TIP.2017.2651399
PMID: 28092553
Source
Medline
License
Unknown

Abstract

Human beings often assess the aesthetic quality of an image coupled with the identification of the image's semantic content. This paper addresses the correlation issue between automatic aesthetic quality assessment and semantic recognition. We cast the assessment problem as the main task among a multi-task deep model, and argue that semantic recognition task offers the key to address this problem. Based on convolutional neural networks, we employ a single and simple multi-task framework to efficiently utilize the supervision of aesthetic and semantic labels. A correlation item between these two tasks is further introduced to the framework by incorporating the inter-task relationship learning. This item not only provides some useful insight about the correlation but also improves assessment accuracy of the aesthetic task. In particular, an effective strategy is developed to keep a balance between the two tasks, which facilitates to optimize the parameters of the framework. Extensive experiments on the challenging Aesthetic Visual Analysis dataset and Photo.net dataset validate the importance of semantic recognition in aesthetic quality assessment, and demonstrate that multitask deep models can discover an effective aesthetic representation to achieve the state-of-the-art results.

Report this publication

Statistics

Seen <100 times