Landmark Classification with Hierarchical Multi-Modal Exemplar Feature
Landmark image classification attracts increasing research attention due to its great importance in real applications, ranging from travel guide recommendation to 3-D modelling and visualization of geolocation. While large amount of efforts have been invested, it still remains unsolved by academia a...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2015
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/3205 https://ink.library.smu.edu.sg/context/sis_research/article/4206/viewcontent/LandmarkClassificationHierarchicalMulti_modalExemplar_2015.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-4206 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-42062017-03-23T00:49:28Z Landmark Classification with Hierarchical Multi-Modal Exemplar Feature ZHU, Lei SHEN, Jialie JIN, Hai XIE, Liang ZHENG, Ran Landmark image classification attracts increasing research attention due to its great importance in real applications, ranging from travel guide recommendation to 3-D modelling and visualization of geolocation. While large amount of efforts have been invested, it still remains unsolved by academia and industry. One of the key reasons is the large intra-class variance rooted from the diverse visual appearance of landmark images. Distinguished from most existing methods based on scalable image search, we approach the problem from a new perspective and model landmark classification as multi-modal categorization, which enjoys advantages of low storage overhead and high classification efficiency. Toward this goal, a novel and effective feature representation, called hierarchical multi-modal exemplar (HMME) feature, is proposed to characterize landmark images. In order to compute HMME, training images are first partitioned into the regions with hierarchical grids to generate candidate images and regions. Then, at the stage of exemplar selection, hierarchical discriminative exemplars in multiple modalities are discovered automatically via iterative boosting and latent region label mining. Finally, HMME is generated via a region-based locality-constrained linear coding (RLLC), which effectively encodes semantics of the discovered exemplars into HMME. Meanwhile, dimension reduction is applied to reduce redundant information by projecting the raw HMME into lower-dimensional space. The final HMME enjoys advantages of discriminative and linearly separable. Experimental study has been carried out on real world landmark datasets, and the results demonstrate the superior performance of the proposed approach over several state-of-the-art techniques. 2015-07-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/3205 info:doi/10.1109/TMM.2015.2431496 https://ink.library.smu.edu.sg/context/sis_research/article/4206/viewcontent/LandmarkClassificationHierarchicalMulti_modalExemplar_2015.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 Dimension reduction diverse visual contents exemplar selection hierarchical multi-modal exemplar feature (HMME) landmark classification region-based locality-constrained linear coding (RLLC) 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 |
Dimension reduction diverse visual contents exemplar selection hierarchical multi-modal exemplar feature (HMME) landmark classification region-based locality-constrained linear coding (RLLC) Computer Sciences Databases and Information Systems |
spellingShingle |
Dimension reduction diverse visual contents exemplar selection hierarchical multi-modal exemplar feature (HMME) landmark classification region-based locality-constrained linear coding (RLLC) Computer Sciences Databases and Information Systems ZHU, Lei SHEN, Jialie JIN, Hai XIE, Liang ZHENG, Ran Landmark Classification with Hierarchical Multi-Modal Exemplar Feature |
description |
Landmark image classification attracts increasing research attention due to its great importance in real applications, ranging from travel guide recommendation to 3-D modelling and visualization of geolocation. While large amount of efforts have been invested, it still remains unsolved by academia and industry. One of the key reasons is the large intra-class variance rooted from the diverse visual appearance of landmark images. Distinguished from most existing methods based on scalable image search, we approach the problem from a new perspective and model landmark classification as multi-modal categorization, which enjoys advantages of low storage overhead and high classification efficiency. Toward this goal, a novel and effective feature representation, called hierarchical multi-modal exemplar (HMME) feature, is proposed to characterize landmark images. In order to compute HMME, training images are first partitioned into the regions with hierarchical grids to generate candidate images and regions. Then, at the stage of exemplar selection, hierarchical discriminative exemplars in multiple modalities are discovered automatically via iterative boosting and latent region label mining. Finally, HMME is generated via a region-based locality-constrained linear coding (RLLC), which effectively encodes semantics of the discovered exemplars into HMME. Meanwhile, dimension reduction is applied to reduce redundant information by projecting the raw HMME into lower-dimensional space. The final HMME enjoys advantages of discriminative and linearly separable. Experimental study has been carried out on real world landmark datasets, and the results demonstrate the superior performance of the proposed approach over several state-of-the-art techniques. |
format |
text |
author |
ZHU, Lei SHEN, Jialie JIN, Hai XIE, Liang ZHENG, Ran |
author_facet |
ZHU, Lei SHEN, Jialie JIN, Hai XIE, Liang ZHENG, Ran |
author_sort |
ZHU, Lei |
title |
Landmark Classification with Hierarchical Multi-Modal Exemplar Feature |
title_short |
Landmark Classification with Hierarchical Multi-Modal Exemplar Feature |
title_full |
Landmark Classification with Hierarchical Multi-Modal Exemplar Feature |
title_fullStr |
Landmark Classification with Hierarchical Multi-Modal Exemplar Feature |
title_full_unstemmed |
Landmark Classification with Hierarchical Multi-Modal Exemplar Feature |
title_sort |
landmark classification with hierarchical multi-modal exemplar feature |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2015 |
url |
https://ink.library.smu.edu.sg/sis_research/3205 https://ink.library.smu.edu.sg/context/sis_research/article/4206/viewcontent/LandmarkClassificationHierarchicalMulti_modalExemplar_2015.pdf |
_version_ |
1770572978007834624 |