Please use this identifier to cite or link to this item:
Title: Object-level attention for aesthetic rating distribution prediction
Authors: Hou, Jingwen
Yang, Sheng
Lin, Weisi
Keywords: Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Issue Date: 2020
Source: Hou, J., Yang, S., & Lin, W. (2020). Object-level attention for aesthetic rating distribution prediction. Proceedings of the 28th ACM International Conference on Multimedia, 816-824. doi:10.1145/3394171.3413695
metadata.dc.contributor.conference: 2020 ACM International Conference on Multimedia
Abstract: We study the problem of image aesthetic assessment (IAA) and aim to automatically predict the image aesthetic quality in the form of discrete distribution, which is particularly important in IAA due to its nature of having possibly higher diversification of agreement for aesthetics. Previous works show the effectiveness of utilizing object-agnostic attention mechanisms to selectively concentrate on more contributive regions for IAA, e.g., attention is learned to weight pixels of input images when inferring aesthetic values. However, as suggested by some neuropsychology studies, the basic units of human attention are visual objects, i.e., the trace of human attention follows a series of objects. This inspires us to predict contributions of different regions at \textit{object level} for better aesthetics evaluation. With our framework, region-of-interests (RoIs) are proposed by an object detector, and each RoI is associated with a regional feature vector. Then the contribution of each regional feature to the aesthetics prediction is adaptively determined. To the best of our knowledge, this is the first work modeling object-level attention for IAA and experimental results confirm the superiority of our framework over previous relevant methods.
ISBN: 9781450379885
DOI: 10.1145/3394171.3413695
Schools: School of Computer Science and Engineering 
Rights: © 2020 Association for Computing Machinery (ACM). All rights reserved. This paper was published in 2020 ACM International Conference on Multimedia and is made available with permission of Association for Computing Machinery (ACM).
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Conference Papers

Files in This Item:
File Description SizeFormat 
Object-level attention for aesthetic rating distribution prediction.pdf4.46 MBAdobe PDFThumbnail

Citations 20

Updated on Nov 20, 2023

Web of ScienceTM
Citations 50

Updated on Oct 24, 2023

Page view(s)

Updated on Nov 28, 2023

Download(s) 10

Updated on Nov 28, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.