Citation

Liang, Xuefeng and Tong, Song and Kumada, Takatsune and Loh, Yuen Peng (2019) Understanding the Photo-shooting Patterns of Sightseeing. In: DSIT 2019: Proceedings of the 2019 2nd International Conference on Data Science and Information, 19-21 July 2019, Seoul, South Korea.

Text 29.pdf - Published Version Restricted to Repository staff only Download (738kB)

Abstract

In this paper, we investigate whether photographers’ preference in shooting patterns could be a reliable index to represent the sightseeing value of a travel spot. To this end, we collected 30k geotagged images from 30 scenic spots over 4 continents. First, an effective framework based on convolution neural network (CNN) is proposed to establish the photographer’s preferred shooting patterns (wide- or narrow-angle) inferred from a single photo. Subsequently, our statistical results reveal that the ratio of photoshooting patterns at a spot strongly correlates with its sightseeing value. The results suggest that photographers prefer to take wideangle photos at the spot with high value, which also accords to the notion in positive psychology — “positive emotions broaden the scope of attention”. In addition, we mapped the spatial distribution of photographers’ shooting patterns to find out common regions of interests within a spot and discuss the potential applications that could arise from our study

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Photo-shooting patterns, multimedia mining, sightseeing value
Subjects:	Q Science > Q Science (General)
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	24 Aug 2021 13:37
Last Modified:	24 Aug 2021 13:37
URII:	http://shdl.mmu.edu.my/id/eprint/8715

Downloads

Edit (login required)