skip to main content
10.1145/2632856.2632882acmotherconferencesArticle/Chapter ViewAbstractPublication PagesicimcsConference Proceedingsconference-collections
research-article

Tensor Representation for Image Annotation with Collective Groups

Published: 10 July 2014 Publication History

Abstract

Image annotation based on visual features has been a difficult problem due to the semantic gap between visual features and human concepts. In this paper, we present a novel image annotation framework with the purpose of learning semantics from collective image groups which are loosely distributed in the whole visual world. Assuming that the contents of each image group are structurally restricted, we adopt tensor representation with a group of tensor structures which are used to describe the interactions of multiple factors inherent to image formation and encode the higher order statistics of these factors. Based on tensor representation, we propose a new method, group-based latent structural topic model (GLSTM), for automatic image annotation. Extensive experiments well validate the effectiveness of our proposed solution to the automatic image annotation problem.

References

[1]
Lowe, D., G. 1999. Object recognition from local scale-invariant features. In ICCV.
[2]
Tola, E., Lepetit, V., et al. 2010. DAISY: an efficient dense descriptor applied to wide-baseline stereo. IEEE Trans. PAMI. 32(5), 815--830.
[3]
Yan, S., Xu, D., et al. 2005. Discriminant analysis with tensor representation. In CVPR.
[4]
Lu, H., Plataniotis, K., N. et al. 2008. MPCA: Multilinear principal component analysis of tensor objects. IEEE Trans. Neural Networks. 19(1), 18--39.
[5]
Tomioka, R., Suzuki, T., et al. 2011. Statistical performance of convex tensor decomposition. In NIPS.
[6]
Ulges, A., and Breuel, T. 2011. Learning visual contexts for image annotation from Flickr groups. IEEE Trans. Multimedia. 13, 330--341.
[7]
Monay, F. and Gatica-Perez, D. 2007. Modeling semantic aspects for cross-media image indexing. IEEE Trans. PAMI. 29, 1802--1817.
[8]
Qi, G., J., Aggarwal, C., et al. 2011. Towards cross-category knowledge propagation for learning visual concepts. In CVPR.
[9]
Chen, Z., Fu, H., et al. 2012. An adaptive recognition model for image annotation. IEEE Trans. Systems, Man, and Cybernetics. 42, 1120--1127.
[10]
Negoescu, R., Adams, B., et al. 2009. Flickr hypergroups. In MM'09.
[11]
Lu, H., Plataniotis, K., N., and Venetsanopoulos, A., N. 2011. A survey of multilinear subspace learning for tensor data. Pattern Recognition. 44, 1540--1551.
[12]
Ma, W., Y., Manjunath, B., S. 2000. EdgeFlow: A technique for boundary detection and image segmentation. IEEE Trans. image processing. 9, 1375--1388.
[13]
Chua, T., S., Tang, J., et al. 2009. NUS-WIDE: A real-world web image database from national university of Singapore. In ACM International Conference on Image Video Retrieval.
[14]
Zhou, N., Cheung, W., K., et al. 2011. A hybrid probabilistic model for unified collaborative and content-based image tagging. IEEE Trans. PAMI. 33, 1281--1294.
[15]
Wu, L., Jin, R., and Jain, A., K. 2013. Tag completion for image retrieval. IEEE Trans. PAMI. 35, 716--727.
[16]
Makadia, A., Pavlovic, V., and Kumar, S. 2008. A new baseline for image annotation. In ECCV.
[17]
Guillaumin, M., Mensink, T., et al. 2009. TagProp: Discriminative metric learning in nearest neighbor nodels for image auto-annotation. In CVPR.

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
ICIMCS '14: Proceedings of International Conference on Internet Multimedia Computing and Service
July 2014
430 pages
ISBN:9781450328104
DOI:10.1145/2632856
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

  • NSF of China: National Natural Science Foundation of China
  • Beijing ACM SIGMM Chapter

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 10 July 2014

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. Image annotation
  2. group learning
  3. latent structural topic model
  4. tensor representation

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

ICIMCS '14

Acceptance Rates

Overall Acceptance Rate 163 of 456 submissions, 36%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 51
    Total Downloads
  • Downloads (Last 12 months)0
  • Downloads (Last 6 weeks)0
Reflects downloads up to 21 Dec 2024

Other Metrics

Citations

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media