Learning compact visual representation with canonical views for robust mobile landmark search

Mobile Landmark Search (MLS) recently receives increasing attention. However, it still remains unsolved due to two important issues. One is high bandwidth consumption of query transmission, and the other is the huge visual variations of query images. This paper proposes a Canonical View based Compac...

Full description

Saved in:
Bibliographic Details
Main Authors: ZHU, Lei, SHEN, Jialie, LIU, Xiaobai, XIE, Liang, NIE, Liqiang
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2016
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/3544
https://ink.library.smu.edu.sg/context/sis_research/article/4545/viewcontent/LearningCompactVisualRepresentation_IJCAI_2016_557.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-4545
record_format dspace
spelling sg-smu-ink.sis_research-45452017-03-27T03:49:29Z Learning compact visual representation with canonical views for robust mobile landmark search ZHU, Lei SHEN, Jialie LIU, Xiaobai XIE, Liang NIE, Liqiang Mobile Landmark Search (MLS) recently receives increasing attention. However, it still remains unsolved due to two important issues. One is high bandwidth consumption of query transmission, and the other is the huge visual variations of query images. This paper proposes a Canonical View based Compact Visual Representation (2CVR) to handle these problems via novel three-stage learning. First, a submodular function is designed to measure visual representativeness and redundancy of a view set. With it, canonical views, which capture key visual appearances of landmark with limited redundancy, are efficiently discovered with an iterative mining strategy. Second, multimodal sparse coding is applied to transform multiple visual features into an intermediate representation which can robustly characterize visual contents of varied landmark images with only fixed canonical views. Finally, compact binary codes are learned on intermediate representation within a tailored binary embedding model which preserves visual relations of images measured with canonical views and removes noises. With 2CVR, robust visual query processing, low-cost of query transmission, and fast search process are simultaneously supported. Experiments demonstrate the superior performance of 2CVR over several state-of-the-art methods. 2016-07-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/3544 https://ink.library.smu.edu.sg/context/sis_research/article/4545/viewcontent/LearningCompactVisualRepresentation_IJCAI_2016_557.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Computer Sciences Databases and Information Systems
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Computer Sciences
Databases and Information Systems
spellingShingle Computer Sciences
Databases and Information Systems
ZHU, Lei
SHEN, Jialie
LIU, Xiaobai
XIE, Liang
NIE, Liqiang
Learning compact visual representation with canonical views for robust mobile landmark search
description Mobile Landmark Search (MLS) recently receives increasing attention. However, it still remains unsolved due to two important issues. One is high bandwidth consumption of query transmission, and the other is the huge visual variations of query images. This paper proposes a Canonical View based Compact Visual Representation (2CVR) to handle these problems via novel three-stage learning. First, a submodular function is designed to measure visual representativeness and redundancy of a view set. With it, canonical views, which capture key visual appearances of landmark with limited redundancy, are efficiently discovered with an iterative mining strategy. Second, multimodal sparse coding is applied to transform multiple visual features into an intermediate representation which can robustly characterize visual contents of varied landmark images with only fixed canonical views. Finally, compact binary codes are learned on intermediate representation within a tailored binary embedding model which preserves visual relations of images measured with canonical views and removes noises. With 2CVR, robust visual query processing, low-cost of query transmission, and fast search process are simultaneously supported. Experiments demonstrate the superior performance of 2CVR over several state-of-the-art methods.
format text
author ZHU, Lei
SHEN, Jialie
LIU, Xiaobai
XIE, Liang
NIE, Liqiang
author_facet ZHU, Lei
SHEN, Jialie
LIU, Xiaobai
XIE, Liang
NIE, Liqiang
author_sort ZHU, Lei
title Learning compact visual representation with canonical views for robust mobile landmark search
title_short Learning compact visual representation with canonical views for robust mobile landmark search
title_full Learning compact visual representation with canonical views for robust mobile landmark search
title_fullStr Learning compact visual representation with canonical views for robust mobile landmark search
title_full_unstemmed Learning compact visual representation with canonical views for robust mobile landmark search
title_sort learning compact visual representation with canonical views for robust mobile landmark search
publisher Institutional Knowledge at Singapore Management University
publishDate 2016
url https://ink.library.smu.edu.sg/sis_research/3544
https://ink.library.smu.edu.sg/context/sis_research/article/4545/viewcontent/LearningCompactVisualRepresentation_IJCAI_2016_557.pdf
_version_ 1770573299144720384