Zhiyong Zhou
Zhiyong Zhou
Home
Posts
Projects
Publications
Blog
Contact
Light
Dark
Automatic
2
Move and remove: Multi-task learning for building simplification in vector maps with a graph convolutional neural network
This research proposes a multi-task learning method with graph convolutional neural networks. The proposed method formulates the building simplification problem as a joint task of node removal classification and node movement regression.
Zhiyong Zhou
,
Cheng Fu
,
Robert Weibel
Project
DOI
HiVG: A hierarchical indoor visibility-based graph for navigation guidance in multi-storey buildings
This study develops a hierarchical indoor data model from a route perspectve to enable the route instructions on multiple levels of detail in buildings.
Zhiyong Zhou
,
Robert Weibel
,
Kai-Florian Richter
,
Haosheng Huang
Project
DOI
Familiarity-dependent computational modelling of indoor landmark selection for route communication: a ranking approach
The study introduces a LambdMART-based approach to select suitable landmarks for communicating with familiar and unfamiliar users in indoor environments.
Zhiyong Zhou
,
Robert Weibel
,
Haosheng Huang
Project
DOI
Indoor Landmark Selection for Route Communication: The Influence of Route-Givers’ Social Roles and Receivers’ Familiarity with the Environment.
This research investigated how these two factors influence landmark selection when communicating routes in indoor environments.
Zhiyong Zhou
,
Robert Weibel
,
Cheng Fu
,
Stephan Winter
,
Haosheng Huang
Project
DOI
Cite
×