Spatial-Aware multimodal location estimation for social images

Cao, Jiewei, Huang, Zi and Yang, Yang (2015). Spatial-Aware multimodal location estimation for social images. In: Proceedings of the 23rd ACM Multimedia Conference. 23rd ACM International Conference on Multimedia 2015, Brisbane, QLD, Australia, (119-128). 26-30 October, 2015. doi:10.1145/2733373.2806249

Author Cao, Jiewei
Huang, Zi
Yang, Yang
Title of paper Spatial-Aware multimodal location estimation for social images
Conference name 23rd ACM International Conference on Multimedia 2015
Conference location Brisbane, QLD, Australia
Conference dates 26-30 October, 2015
Convener ACM
Proceedings title Proceedings of the 23rd ACM Multimedia Conference
Journal name MM 2015 - Proceedings of the 2015 ACM Multimedia Conference
Series Proceedings of the ACM Multimedia Conference
Publisher Association for Computing Machinery, Inc
Publication Year 2015
Sub-type Fully published paper
DOI 10.1145/2733373.2806249
Open Access Status Not Open Access
ISBN 9781450334594
Volume 23
Start page 119
End page 128
Total pages 10
Collection year 2016
Language eng
Abstract/Summary Nowadays the locations of social images play an important role in geographic knowledge discovery. However, most social images still lack the location information, driving location estimation for social images to have recently become an active research topic. With the rapid growth of social images, new challenges have been posed: 1) data quality of social images is an issue because they are often associated with noises and error-prone user-generated content, such as junk comments and misspelled words; and 2) data sparsity exists in social images despite the large volume, since most of them are unevenly distributed around the world and their contextual information is often missing or incomplete. In this paper, we propose a spatial-aware multimodal location estimation (SMLE) framework to tackle the above challenges. Specifically, a spatial-aware language model (SLM) is proposed to detect the high quality location-indicative tags from large datasets. We also design a spatial-aware topic model, namely spatial-aware regularized latent semantic indexing (SRLSI), to discover geographic topics and alleviate the data sparseness problem existing in language modeling. Taking multi-modalities of social images into consideration, we employ the learning to rank approach to fuse multiple evidences derived from textual features represented by SLM and SRLSI, and visual features represented by bag-of-visual-words (BoVW). Importantly, an ad hoc method is introduced to construct the training dataset with spatial-aware relevance labels for learning to rank training. Finally, given a query image, its location is estimated as the location of its most relevant image returned from the learning to rank model. The proposed framework is evaluated on a public benchmark provided by MediaEval 2013 Placing Task, which contains more than 8.5 million images crawled from Flickr. Extensive experiments on this dataset demonstrate the superior performance of the proposed methods over the state-of-the-art approaches.
Keyword Geotagging
Location Estimation
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status UQ

Version Filter Type
Citation counts: Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Tue, 26 Apr 2016, 03:27:59 EST by System User on behalf of Learning and Research Services (UQ Library)