GPS2Vec: Pre-Trained Semantic Embeddings for Worldwide GPS Coordinates
- 22 February 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 24 (15209210), 890-903
- https://doi.org/10.1109/tmm.2021.3060951
Abstract
GPS coordinates are fine-grained location indicators that are difficult to be effectively utilized by classifiers in geo-aware applications. Previous GPS encoding methods concentrate on generating hand-crafted features for small areas of interest. However, many real world applications require a machine learning model, analogous to the pre-trained ImageNet model for images, that can efficiently generate semantically-enriched features for planet-scale GPS coordinates. To address this issue, we propose a novel two-level grid-based framework, termed GPS2Vec, which is able to extract geo-aware features in real-time for locations worldwide. The Earth’s surface is first discretized by the Universal Transverse Mercator (UTM) coordinate system. Each UTM zone is then considered as a local area of interest that is further divided into fine-grained cells to perform the initial GPS encoding. We train a neural network in each UTM zone to learn the semantic embeddings from the initial GPS encoding. The training labels can be automatically derived from large-scale geotagged documents such as tweets, check-ins, and images that are available from social sharing platforms. We conducted comprehensive experiments on three geo-aware applications, namely place semantic annotation, geotagged image classification, and next location prediction. Experimental results demonstrate the effectiveness of our approach, as prediction accuracy improves significantly based on a simple multi-feature early fusion strategy with deep neural networks, including both CNNs and RNNs.Keywords
Funding Information
- Singapore Ministry of Education Academic Research Fund Tier 2
- MOEs official (MOE2018-T2-1-103)
This publication has 40 references indexed in Scilit:
- NationTelescope: Monitoring and visualizing large-scale collective behavior in LBSNsJournal of Network and Computer Applications, 2015
- Tag Features for Geo-Aware Image ClassificationIEEE Transactions on Multimedia, 2015
- Content vs. ContextACM Transactions on Multimedia Computing, Communications, and Applications, 2015
- SplitterProceedings of the VLDB Endowment, 2014
- World-wide scale geotagged image dataset for automatic image annotation and reverse geotaggingPublished by Association for Computing Machinery (ACM) ,2014
- Location recommendation in location-based social networks using user check-in dataPublished by Association for Computing Machinery (ACM) ,2013
- Tagging photos using users' vocabulariesNeurocomputing, 2013
- Fusing concept detection and geo context for visual searchPublished by Association for Computing Machinery (ACM) ,2012
- NUS-WIDEPublished by Association for Computing Machinery (ACM) ,2009
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004