eprintid: 3788
rev_number: 9
eprint_status: archive
userid: 413
dir: disk0/00/00/37/88
datestamp: 2019-12-10 15:51:10
lastmod: 2019-12-10 15:51:10
status_changed: 2019-12-10 15:51:10
type: conference_item
metadata_visibility: show
creators_name: Nguyen, Diep Thi Ngoc
creators_name: Nakayama, Hideki
creators_name: Okazaki, Naoaki
creators_name: Sakaeda, Tatsuya
title: PoB
ispublished: pub
subjects: IT
subjects: Scopus
divisions: fac_fit
abstract: Aiming to develop of computational grammar system for visual information, we design a 4-tier framework that consists of four levels of 'visual grammar of images.' As a first step of realization, we propose a new dataset, named the PoB dataset, in which each image is annotated with multiple labels of armature patterns that compose the pictorial scene. The PoB dataset includes of a 10,000-painting dataset for art and a 4,959-image dataset for photography. In this paper, we discuss the consistency analysis of our dataset and its applicability. We also demonstrate how the armature patterns in the PoB dataset are useful in assessing aesthetic quality of images, and how well a deep learning algorithm can recognize these patterns. This paper seeks to set a new direction in image understanding with a more holistic approach beyond discrete objects and in aesthetic reasoning with a more interpretative way.
date: 2018
date_type: completed
official_url: http://dx.doi.org/10.1145/3240508.3240711
id_number: 10.1145/3240508.3240711
contact_email: ngocdiep@vnu.edu.vn
full_text_status: public
pres_type: paper
pagerange: 1786-1793
event_title: The 26th ACM international conference on Multimedia
event_location: Seoul, Korea
event_dates: October 22-26, 2018
event_type: conference
refereed: TRUE
book_title: 2018 ACM Multimedia Conference on Multimedia Conference - MM '18
related_url_url: https://dl.acm.org/citation.cfm?id=3240711
citation:   Nguyen, Diep Thi Ngoc and Nakayama, Hideki and Okazaki, Naoaki and Sakaeda, Tatsuya  (2018) PoB.  In: The 26th ACM international conference on Multimedia, October 22-26, 2018, Seoul, Korea.     
document_url: https://eprints.uet.vnu.edu.vn/eprints/id/eprint/3788/1/%5B2018%20acmmm%5Dpob_diep.pdf