Tensor Representation for Image Annotation with Collective Groups
Pages 422 - 426
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.
Index Terms
- Tensor Representation for Image Annotation with Collective Groups
Recommendations
A review on the application of structured sparse representation at image annotation
The increasing number of images on the Web and other information environments, needs efficient management and suitable retrieval especially by computers. Image annotation is a process which produces words for a digital image based on its content. Users ...
Automatic Image Annotation Based on Sparse Representation and Multiple Label Learning
ICVRV '12: Proceedings of the 2012 International Conference on Virtual Reality and VisualizationAutomatic image annotation has emerged as an important research topic due to its potential application on both image understanding and web image search. Due to the inherent ambiguity of image-label mapping, the annotation task has become a challenge to ...
Heritage image annotation via collective knowledge
AbstractThe automatic image annotation can provide semantic illustrations to understand image contents, and builds a foundation to develop algorithms that can search images within a large database. However, most current methods focus on solving the ...
Comments
Information & Contributors
Information
Published In
July 2014
430 pages
ISBN:9781450328104
DOI:10.1145/2632856
- General Chairs:
- Hanzi Wang,
- Larry Davis,
- Program Chairs:
- Wenwu Zhu,
- Stephan Kopf,
- Yanyun Qu,
- Publications Chairs:
- Jun Yu,
- Jitao Sang,
- Tao Mei
Copyright © 2014 ACM.
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
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ICIMCS '14
ICIMCS '14: International Conference on Internet Multimedia Computing and Service
July 10 - 12, 2014
Xiamen, China
Acceptance Rates
Overall Acceptance Rate 163 of 456 submissions, 36%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 51Total 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
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in