Article

Consensus style centralizing auto-encoder for weak style classification

Authors:

Chengcheng Jia,

Yun FuAuthors Info & Claims

AAAI'16: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence

Pages 1223 - 1229

Published: 12 February 2016 Publication History

Abstract

Style classification (e.g., architectural, music, fashion) attracts an increasing attention in both research and industrial fields. Most existing works focused on low-level visual features composition for style representation. However, little effort has been devoted to automatic mid-level or high-level style features learning by reorganizing low-level descriptors. Moreover, styles are usually spread out and not easy to differentiate from one to another. In this paper, we call these less representative images as weak style images. To address these issues, we propose a consensus style centralizing auto-encoder (CSCAE) to extract robust style features to facilitate weak style classification. CSCAE is the ensemble of several style centralizing auto-encoders (SCAEs) with consensus constraint. Each SCAE centralizes each feature of certain category in a progressive way. We apply our method in fashion style classification and manga style classification as two example applications. In addition, we collect a new dataset, Online Shopping, for fashion style classification evaluation, which will be publicly available for vision based fashion style research. Experiments demonstrate the effectiveness of SCAE and CSCAE on both public and newly collected datasets when compared with the most recent state-of-the-art works.

References

[1]

Agostinelli, F.; Anderson, M. R.; and Lee, H. 2013. Adaptive multi-column deep neural networks with application to robust image denoising. In Advances in Neural Information Processing Systems, 1493-1501.

[2]

Bengio, Y. 2009. Learning deep architectures for ai. Foundations and trends� in Machine Learning 2(1):1-127.

[3]

Bossard, L.; Dantone, M.; Leistner, C.; Wengert, C.; Quack, T.; and Van Gool, L. 2013. Apparel classification with style. In Asian Conference on Computer Vision. Springer. 321-335.

[4]

Chang, Y.-C.; Chuang, M.-C.; Hung, S.-H.; Shen, S.-J. C.; and Chu, B. 2003. A kansei study on the style image of fashion design. In the 6th Asian Design Conference.

[5]

Chao, X.; Huiskes, M. J.; Gritti, T.; and Ciuhu, C. 2009. A framework for robust feature selection for real-time fashion style recommendation. In International workshop on Interactive multimedia for consumer electronics, 35-42. ACM.

[6]

Chapelle, O.; Scholkopf, B.; Zien, A.; et al. 2006. Semi-supervised learning.

[7]

Chu, W.-T., and Chao, Y.-C. 2014. Line-based drawing style description for manga classification. In ACM International Conference on Multimedia, 781-784. ACM.

[8]

Czapiewski, P.; Forczmański, P.; Frejlichowski, D.; and Hofman, R. 2015. Clustering-based retrieval of similar outfits based on clothes visual characteristics. In Image Processing & Communications Challenges 6. Springer. 29-36.

[9]

Dalal, N., and Triggs, B. 2005. Histograms of oriented gradients for human detection. In IEEE Conference on Computer Vision and Pattern Recognition, 886-893. IEEE.

[10]

Di, W.; Wah, C.; Bhardwaj, A.; Piramuthu, R.; and Sundaresan, N. 2013. Style finder: Fine-grained clothing style detection and retrieval. In IEEE Conference on Computer Vision and Pattern Recognition Workshops, 8-13. IEEE.

[11]

Ding, Z.; Shao, M.; and Fu, Y. 2015. Deep low-rank coding for transfer learning. In International Joint Conference on Artificial Intelligence, 3453-3459.

[12]

Goel, A.; Juneja, M.; and Jawahar, C. 2012. Are buildings only instances?: exploration in architectural style categories. In Indian Conference on Computer Vision, Graphics and Image Processing. ACM.

[13]

Herlands, W.; Der, R.; Greenberg, Y.; and Levin, S. 2014. A machine learning approach to musically meaningful homogeneous style classification. In AAAI Conference on Artificial Intelligence, 276-282.

[14]

Kiapour, M. H.; Yamaguchi, K.; Berg, A. C.; and Berg, T. L. 2014. Hipster wars: Discovering elements of fashion styles. In European Conference on Computer Vision. Springer. 472-488.

[15]

Liu, S.; Feng, J.; Song, Z.; Zhang, T.; Lu, H.; Xu, C.; and Yan, S. 2012a. Hi, magic closet, tell me what to wear! In ACM international conference on Multimedia, 619-628. ACM.

[16]

Liu, S.; Song, Z.; Liu, G.; Xu, C.; Lu, H.; and Yan, S. 2012b. Street-to-shop: Cross-scenario clothing retrieval via parts alignment and auxiliary set. In IEEE Conference on Computer Vision and Pattern Recognition, 3330-3337. IEEE.

[17]

Ngiam, J.; Coates, A.; Lahiri, A.; Prochnow, B.; Le, Q. V.; and Ng, A. Y. 2011. On optimization methods for deep learning. In International Conference on Machine Learning, 265-272.

[18]

Nocedal, J. 1980. Updating quasi-newton matrices with limited storage. Mathematics of computation 35(151):773-782.

[19]

Rumelhart, D. E.; Hinton, G. E.; and Williams, R. J. 1988. Learning representations by back-propagating errors. Cognitive modeling 5:696-699.

[20]

Shao, M.; Li, L.; and Fu, Y. 2013. What do you do? occupation recognition in a photo via social context. In IEEE International Conference on Computer Vision, 3631-3638. IEEE.

[21]

Song, Z.; Wang, M.; Hua, X.-s.; and Yan, S. 2011. Predicting occupation via human clothing and contexts. In IEEE International Conference on Computer Vision, 1084-1091. IEEE.

[22]

Van Gemert, J. C. 2011. Exploiting photographic style for category-level image classification by generalizing the spatial pyramid. In ACM International Conference on Multimedia Retrieval, 1-8. ACM.

[23]

Varma, M., and Zisserman, A. 2005. A statistical approach to texture classification from single images. International Journal of Computer Vision 62(1-2):61-81.

[24]

Vincent, P.; Larochelle, H.; Bengio, Y.; and Manzagol, P.-A. 2008. Extracting and composing robust features with de-noising autoencoders. In International Conference on Machine learning, 1096-1103. ACM.

[25]

Vincent, P.; Larochelle, H.; Lajoie, I.; Bengio, Y.; and Manzagol, P.-A. 2010. Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. The Journal of Machine Learning Research 11:3371-3408.

[26]

Wang, H.; Zhou, Z.; Xiao, C.; and Zhang, L. 2015. Content based image search for clothing recommendations in e-commerce. In Multimedia Data Mining and Analytics. Springer. 253-267.

[27]

Xu, Z.; Tao, D.; Zhang, Y.; Wu, J.; and Tsoi, A. C. 2014. Architectural style classification using multinomial latent logistic regression. In European Conference on Computer Vision. Springer. 600-615.

[28]

Yamaguchi, K.; Kiapour, M. H.; Ortiz, L. E.; and Berg, T. L. 2012. Parsing clothing in fashion photographs. In IEEE Conference on Computer Vision and Pattern Recognition, 3570-3577. IEEE.

[29]

Yamaguchi, K.; Kiapour, M. H.; and Berg, T. L. 2013. Paper doll parsing: Retrieving similar styles to parse clothing items. In IEEE International Conference on Computer Vision, 3519-3526. IEEE.

[30]

Yang, Y., and Ramanan, D. 2011. Articulated pose estimation with flexible mixtures-of-parts. In IEEE Conference on Computer Vision and Pattern Recognition, 1385-1392. IEEE.

Cited By

Jiang SFu Y(2017)Fashion style generatorProceedings of the 26th International Joint Conference on Artificial Intelligence10.5555/3172077.3172409(3721-3727)Online publication date: 19-Aug-2017
https://dl.acm.org/doi/10.5555/3172077.3172409
Wu YLiu HLi JFu YWu WYang JTian QZimmermann R(2017)Deep Face Recognition with Center Invariant LossProceedings of the on Thematic Workshops of ACM Multimedia 201710.1145/3126686.3126693(408-414)Online publication date: 23-Oct-2017
https://dl.acm.org/doi/10.1145/3126686.3126693
Gu XWong YPeng PShou LChen GKankanhalli MLiu QLienhart RWang HChen SBoll SChen PFriedland GLi JYan S(2017)Understanding Fashion Trends from Street Photos via Neighbor-Constrained Embedding LearningProceedings of the 25th ACM international conference on Multimedia10.1145/3123266.3123441(190-198)Online publication date: 23-Oct-2017
https://dl.acm.org/doi/10.1145/3123266.3123441
Show More Cited By

Recommendations

Learning Consensus Representation for Weak Style Classification
Style classification (e.g., Baroque and Gothic architecture style) is grabbing increasing attention in many fields such as fashion, architecture, and manga. Most existing methods focus on extracting discriminative features from local patches or patterns. ...
Style language: creating words for sharing diverse ways of doing
PLoP '18: Proceedings of the 25th Conference on Pattern Languages of Programs

This paper presents style language as a new method for sharing various ways of conducting a specific activity, with support for designing your own activity. A style language describes the elements of style as a type of approach and implementation. By ...
Conditional Fast Style Transfer Network
ICMR '17: Proceedings of the 2017 ACM on International Conference on Multimedia Retrieval

In this paper, we propose a conditional fast neural style transfer network. We extend the network proposed as a fast neural style transfer network by Johnson et al. [1] so that the network can learn multiple styles at the same time. To do that, we add a ...

Comments

Information & Contributors

Information

Published In

cover image Guide Proceedings

AAAI'16: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence

February 2016

4406 pages

Sponsors

Association for the Advancement of Artificial Intelligence

Publisher

AAAI Press

Publication History

Published: 12 February 2016

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

5
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 16 Oct 2024

Other Metrics

View Author Metrics

Citations

Cited By

Jiang SFu Y(2017)Fashion style generatorProceedings of the 26th International Joint Conference on Artificial Intelligence10.5555/3172077.3172409(3721-3727)Online publication date: 19-Aug-2017
https://dl.acm.org/doi/10.5555/3172077.3172409
Wu YLiu HLi JFu YWu WYang JTian QZimmermann R(2017)Deep Face Recognition with Center Invariant LossProceedings of the on Thematic Workshops of ACM Multimedia 201710.1145/3126686.3126693(408-414)Online publication date: 23-Oct-2017
https://dl.acm.org/doi/10.1145/3126686.3126693
Gu XWong YPeng PShou LChen GKankanhalli MLiu QLienhart RWang HChen SBoll SChen PFriedland GLi JYan S(2017)Understanding Fashion Trends from Street Photos via Neighbor-Constrained Embedding LearningProceedings of the 25th ACM international conference on Multimedia10.1145/3123266.3123441(190-198)Online publication date: 23-Oct-2017
https://dl.acm.org/doi/10.1145/3123266.3123441
Jiang SDing ZFu YLiu QLienhart RWang HChen SBoll SChen PFriedland GLi JYan S(2017)Deep Low-rank Sparse Collective Factorization for Cross-Domain RecommendationProceedings of the 25th ACM international conference on Multimedia10.1145/3123266.3123361(163-171)Online publication date: 23-Oct-2017
https://dl.acm.org/doi/10.1145/3123266.3123361
Jiang SWu YFu YHanjalic ASnoek CWorring MBulterman DHuet BKelliher AKompatsiaris YLi J(2016)Deep Bi-directional Cross-triplet Embedding for Cross-Domain Clothing RetrievalProceedings of the 24th ACM international conference on Multimedia10.1145/2964284.2967182(52-56)Online publication date: 1-Oct-2016
https://dl.acm.org/doi/10.1145/2964284.2967182

View Options

View options

Media

Figures

Other

Tables

View Table of Contents