Social media based 3D visual popularity

Autor: Rozenn Dahyot, Abdullah Bulbul
Jazyk: angličtina
Rok vydání: 2017
Předmět:
Popis: A visible area detection method that depends on online available information is proposed.Visual popularity and sentiment are calculated based on images and their accompanying text that people share in social mediaThe visual popularity information is presented in a 3D virtual environment using Unreal engine. Display Omitted This paper proposes to use a geotagged virtual world for the visualization of peoples visual interest and their sentiment as captured from their social network activities. Using mobile devices, people widely share their experiences and the things they find interesting through social networks. We experimentally show that accumulating information over a period of time from multiple social network users allows to efficiently map and visualize popular landmarks as found in cities such as Rome in Italy and Dublin in Ireland. The proposed approach is also sensitive to temporal and spatial events that attract visual attention. We visualize the calculated popularity on 3D virtual cities using game engine technologies.
Databáze: OpenAIRE