Conflation of Geospatial POI Data and Ground-level Imagery via Link Prediction on Joint Semantic Graph

Rutuja Gurav; Debraj De; Gautam Thakur; Junchuan Fan

doi:10.1145/3486635.3491068

Conflation of Geospatial POI Data and Ground-level Imagery via Link Prediction on Joint Semantic Graph

Rutuja Gurav, Debraj De, Gautam Thakur, Junchuan Fan

Location Intelligence

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

With the proliferation of smartphone cameras and social networks, we have rich, multi-modal data about points of interest (POIs) - like cultural landmarks, institutions, businesses, etc. - within a given areas of interest (AOI) (e.g., a county, city or a neighborhood) available to us. Data conflation across multiple modalities of data sources is one of the key challenges in maintaining a geographical information system (GIS) which accumulate data about POIs. Given POI data from nine different sources, and ground-level geo-tagged and scene-captioned images from two different image hosting platforms, in this work we explore the application of graph neural networks (GNNs) to perform data conflation, while leveraging a natural graph structure evident in geospatial data. The preliminary results demonstrate the capacity of a GNN operation to learn distributions of entity (POIs and images) features, coupled with topological structure of entity's local neighborhood in a semantic nearest neighbor graph, in order to predict links between a pair of entities.

Original language	English
Title of host publication	Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021
Editors	Dalton Lunga, Lexie Yang, Song Gao, Bruno Martins, Yingjie Hu, Xueqing Deng, Shawn Newsam
Publisher	Association for Computing Machinery, Inc
Pages	5-8
Number of pages	4
ISBN (Electronic)	9781450391207
DOIs	https://doi.org/10.1145/3486635.3491068
State	Published - Nov 2 2021
Event	4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021 - Beijing, China Duration: Nov 2 2021 → Nov 2 2021

Publication series

Name	Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021

Conference

Conference	4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021
Country/Territory	China
City	Beijing
Period	11/2/21 → 11/2/21

Funding

This manuscript has been authored by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). The US government retains and the publisher, by accepting the article for publication, acknowledges that the US government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for US government purposes. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (https://energy.gov/downloads/doe-public-access-plan).

Keywords

Areas of Interest (AOI)
POI configuration
Points of Interest (POI)
data conflation
graph neural network
ground-level imagery
semantic space
word embedding

Access to Document

10.1145/3486635.3491068

Cite this

Gurav, R., De, D., Thakur, G., & Fan, J. (2021). Conflation of Geospatial POI Data and Ground-level Imagery via Link Prediction on Joint Semantic Graph. In D. Lunga, L. Yang, S. Gao, B. Martins, Y. Hu, X. Deng, & S. Newsam (Eds.), Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021 (pp. 5-8). (Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021). Association for Computing Machinery, Inc. https://doi.org/10.1145/3486635.3491068

Gurav, Rutuja ; De, Debraj ; Thakur, Gautam et al. / Conflation of Geospatial POI Data and Ground-level Imagery via Link Prediction on Joint Semantic Graph. Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021. editor / Dalton Lunga ; Lexie Yang ; Song Gao ; Bruno Martins ; Yingjie Hu ; Xueqing Deng ; Shawn Newsam. Association for Computing Machinery, Inc, 2021. pp. 5-8 (Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021).

@inproceedings{ad6f69eaa4bf4c3e87ecb09eb11d7b96,

title = "Conflation of Geospatial POI Data and Ground-level Imagery via Link Prediction on Joint Semantic Graph",

abstract = "With the proliferation of smartphone cameras and social networks, we have rich, multi-modal data about points of interest (POIs) - like cultural landmarks, institutions, businesses, etc. - within a given areas of interest (AOI) (e.g., a county, city or a neighborhood) available to us. Data conflation across multiple modalities of data sources is one of the key challenges in maintaining a geographical information system (GIS) which accumulate data about POIs. Given POI data from nine different sources, and ground-level geo-tagged and scene-captioned images from two different image hosting platforms, in this work we explore the application of graph neural networks (GNNs) to perform data conflation, while leveraging a natural graph structure evident in geospatial data. The preliminary results demonstrate the capacity of a GNN operation to learn distributions of entity (POIs and images) features, coupled with topological structure of entity's local neighborhood in a semantic nearest neighbor graph, in order to predict links between a pair of entities.",

keywords = "Areas of Interest (AOI), POI configuration, Points of Interest (POI), data conflation, graph neural network, ground-level imagery, semantic space, word embedding",

author = "Rutuja Gurav and Debraj De and Gautam Thakur and Junchuan Fan",

note = "Publisher Copyright: {\textcopyright} 2021 Public Domain.; 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021 ; Conference date: 02-11-2021 Through 02-11-2021",

year = "2021",

month = nov,

day = "2",

doi = "10.1145/3486635.3491068",

language = "English",

series = "Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021",

publisher = "Association for Computing Machinery, Inc",

pages = "5--8",

editor = "Dalton Lunga and Lexie Yang and Song Gao and Bruno Martins and Yingjie Hu and Xueqing Deng and Shawn Newsam",

booktitle = "Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021",

}

Gurav, R, De, D, Thakur, G & Fan, J 2021, Conflation of Geospatial POI Data and Ground-level Imagery via Link Prediction on Joint Semantic Graph. in D Lunga, L Yang, S Gao, B Martins, Y Hu, X Deng & S Newsam (eds), Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021. Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021, Association for Computing Machinery, Inc, pp. 5-8, 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021, Beijing, China, 11/2/21. https://doi.org/10.1145/3486635.3491068

Conflation of Geospatial POI Data and Ground-level Imagery via Link Prediction on Joint Semantic Graph. / Gurav, Rutuja; De, Debraj; Thakur, Gautam et al.
Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021. ed. / Dalton Lunga; Lexie Yang; Song Gao; Bruno Martins; Yingjie Hu; Xueqing Deng; Shawn Newsam. Association for Computing Machinery, Inc, 2021. p. 5-8 (Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Conflation of Geospatial POI Data and Ground-level Imagery via Link Prediction on Joint Semantic Graph

AU - Gurav, Rutuja

AU - De, Debraj

AU - Thakur, Gautam

AU - Fan, Junchuan

PY - 2021/11/2

Y1 - 2021/11/2

N2 - With the proliferation of smartphone cameras and social networks, we have rich, multi-modal data about points of interest (POIs) - like cultural landmarks, institutions, businesses, etc. - within a given areas of interest (AOI) (e.g., a county, city or a neighborhood) available to us. Data conflation across multiple modalities of data sources is one of the key challenges in maintaining a geographical information system (GIS) which accumulate data about POIs. Given POI data from nine different sources, and ground-level geo-tagged and scene-captioned images from two different image hosting platforms, in this work we explore the application of graph neural networks (GNNs) to perform data conflation, while leveraging a natural graph structure evident in geospatial data. The preliminary results demonstrate the capacity of a GNN operation to learn distributions of entity (POIs and images) features, coupled with topological structure of entity's local neighborhood in a semantic nearest neighbor graph, in order to predict links between a pair of entities.

AB - With the proliferation of smartphone cameras and social networks, we have rich, multi-modal data about points of interest (POIs) - like cultural landmarks, institutions, businesses, etc. - within a given areas of interest (AOI) (e.g., a county, city or a neighborhood) available to us. Data conflation across multiple modalities of data sources is one of the key challenges in maintaining a geographical information system (GIS) which accumulate data about POIs. Given POI data from nine different sources, and ground-level geo-tagged and scene-captioned images from two different image hosting platforms, in this work we explore the application of graph neural networks (GNNs) to perform data conflation, while leveraging a natural graph structure evident in geospatial data. The preliminary results demonstrate the capacity of a GNN operation to learn distributions of entity (POIs and images) features, coupled with topological structure of entity's local neighborhood in a semantic nearest neighbor graph, in order to predict links between a pair of entities.

KW - Areas of Interest (AOI)

KW - POI configuration

KW - Points of Interest (POI)

KW - data conflation

KW - graph neural network

KW - ground-level imagery

KW - semantic space

KW - word embedding

UR - http://www.scopus.com/inward/record.url?scp=85119485709&partnerID=8YFLogxK

U2 - 10.1145/3486635.3491068

DO - 10.1145/3486635.3491068

M3 - Conference contribution

AN - SCOPUS:85119485709

T3 - Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021

SP - 5

EP - 8

BT - Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021

A2 - Lunga, Dalton

A2 - Yang, Lexie

A2 - Gao, Song

A2 - Martins, Bruno

A2 - Hu, Yingjie

A2 - Deng, Xueqing

A2 - Newsam, Shawn

PB - Association for Computing Machinery, Inc

T2 - 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021

Y2 - 2 November 2021 through 2 November 2021

ER -

Gurav R, De D, Thakur G , Fan J. Conflation of Geospatial POI Data and Ground-level Imagery via Link Prediction on Joint Semantic Graph. In Lunga D, Yang L, Gao S, Martins B, Hu Y, Deng X, Newsam S, editors, Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021. Association for Computing Machinery, Inc. 2021. p. 5-8. (Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery, GeoAI 2021). doi: 10.1145/3486635.3491068

Conflation of Geospatial POI Data and Ground-level Imagery via Link Prediction on Joint Semantic Graph

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this