https://scholars.lib.ntu.edu.tw/handle/123456789/581316
Title: | Aesthetic Critiques Generation for Photos | Authors: | Chang K.-Y Lu K.-H CHU-SONG CHEN |
Keywords: | Computer science; Computers; Electrical engineering; Aesthetic qualities; Attention mechanisms; Fusion methods; Image captioning; Professional photographers; Quality ratings; Computer vision | Issue Date: | 2017 | Journal Volume: | 2017-October | Start page/Pages: | 3534-3543 | Source: | Proceedings of the IEEE International Conference on Computer Vision | Abstract: | It is said that a picture is worth a thousand words. Thus, there are various ways to describe an image, especially in aesthetic quality analysis. Although aesthetic quality assessment has generated a great deal of interest in the last decade, most studies focus on providing a quality rating of good or bad for an image. In this work, we extend the task to produce captions related to photo aesthetics and/or photography skills. To the best of our knowledge, this is the first study that deals with aesthetics captioning instead of AQ scoring. In contrast to common image captioning tasks that depict the objects or their relations in a picture, our approach can select a particular aesthetics aspect and generate captions with respect to the aspect chosen. Meanwhile, the proposed aspect-fusion method further uses an attention mechanism to generate more abundant aesthetics captions. We also introduce a new dataset for aesthetics captioning called the Photo Critique Captioning Dataset (PCCD), which contains pair-wise image-comment data from professional photographers. The results of experiments on PCCD demonstrate that our approaches outperform existing methods for generating aesthetic-oriented captions for images. ? 2017 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85041926880&doi=10.1109%2fICCV.2017.380&partnerID=40&md5=7221d6893603af491276787ac30c90e2 https://scholars.lib.ntu.edu.tw/handle/123456789/581316 |
ISSN: | 15505499 | DOI: | 10.1109/ICCV.2017.380 |
Appears in Collections: | 資訊工程學系 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.