Abstract
Photos are an important information carrier for implicit relationships. In this article, we introduce an image based social network, called CelebrityNet, built from implicit relationships encoded in a collection of celebrity images. We analyze the social properties reflected in this image-based social network and automatically infer communities among the celebrities. We demonstrate the interesting discoveries of the CelebrityNet. We particularly compare the inferred communities with human manually labeled ones and show quantitatively that the automatically detected communities are highly aligned with that of human interpretation. Inspired by the uniqueness of visual content and tag concepts within each community of the CelebrityNet, we further demonstrate that the constructed social network can serve as a knowledge base for high-level visual recognition tasks. In particular, this social network is capable of significantly improving the performance of automatic image annotation and classification of unknown images.
- S. Bakhshi, D. A. Shamma, and E. Gilbert. 2014. Faces engage us: Photos with faces attract more likes and comments on Instagram. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. ACM, New York, 965--974. Google Scholar
Digital Library
- M. A. Beauchamp. 1965. An improved index of centrality. Behav. Sci. 10, 2, 161--163.Google Scholar
Cross Ref
- M. R. Boutell, J. Luo, X. Shen, and C. M. Brown. 2004. Learning multi-label scene classification. Patt. Recog. 37, 9, 1757--1771.Google Scholar
Cross Ref
- S. Brin and L. Page. 1998. The anatomy of a large-scale hypertextual Web search engine. Comput. Netw. ISDN Syst. 30, 1, 107--117. Google Scholar
Digital Library
- L. Cao, J. Yu, J. Luo, and T. S. Huang. 2009. Enhancing semantic and geographic annotation of web images via logistic canonical correlation regression. In Proceedings of the 17th ACM International Conference on Multimedia (MM'09). ACM, New York, 125--134. DOI:http://dx.doi.org/10.1145/1631272.1631292 Google Scholar
Digital Library
- Y.-Y. Chen, W. H. Hsu, and H.-Y. M. Liao. 2012. Discovering informative social subgraphs and predicting pairwise relationships from group photos. In Proceedings of the 20th ACM International Conference on Multimedia (MM'12). ACM, New York, 669--678. DOI:http://dx.doi.org/10.1145/2393347.2393439 Google Scholar
Digital Library
- N. Dalal and B. Triggs. 2005. Histograms of oriented gradients for human detection. In Proceedings of CVPR. 886. Google Scholar
Digital Library
- J. Deng, A. Berg, K. Li, and L. Fei-Fei. 2010. What does classifying more than 10,000 image categories tell us? In Proceedings of ECCV'10. 71--84. Google Scholar
Digital Library
- I. Derényi, G. Palla, and T. Vicsek. 2005. Clique percolation in random networks. Phys. Rev. Lett. 94.Google Scholar
Cross Ref
- L. Ding and A. Yilmaz. 2010. Learning relations among movie characters: A social network perspective. In Proceedings of ECCV'10. 410--423. Google Scholar
Digital Library
- Rong-En Fan, Kai-Wei Chang, Cho-Jui Hsieh, Xiang-Rui Wang, and Chih-Jen Lin. 2008. LIBLINEAR: A library for large linear classification. J. Mach. Learn. Res. 9, 1871--1874. Google Scholar
Digital Library
- P. Felzenszwalb, R. Girshick, D. McAllester, and D. Ramanan. 2007. Object detection with discriminatively trained part based models. J. Art. Intell. Res. 29.Google Scholar
- L. C. Freeman. 1977. A set of measures of centrality based on betweenness. Sociometry 35--41.Google Scholar
- W. Gao and K. Wong. 2006. Natural document clustering by clique percolation in random graphs. In Proceedings of the 3rd Asia Conference on Information Retrieval Technology. Springer, 119--131. Google Scholar
Digital Library
- N. Ghamrawi and A. McCallum. 2005. Collective multi-label classification. In Proceedings of CIKM. 195--200. Google Scholar
Digital Library
- M. C. Gonzaléz, H. J. Herrmann, J. Kertész, and T. Vicsek. 2007. Community structure and ethnic preferences in school friendship networks. Phys. A 379, 1, 307--316.Google Scholar
Cross Ref
- P. R. Gould. 1967. On the geographical interpretation of eigenvalues. Trans. Instit. British Geog. 53--86.Google Scholar
Cross Ref
- P. Jaccard. 1901. Étude comparative de la distribution florale dans une portion des Alpes et des Jura. Bulletin del la Société Vaudoise des Sciences Naturelles.Google Scholar
- F. Kang, R. Jin, and R. Sukthankar. 2006. Correlated label propagation with application to multi-label learning. In Proceedings of CVPR. 1719--1726. Google Scholar
Digital Library
- H.-N. Kim, J.-G. Jung, and A. El Saddik. 2010. Associative face co-occurrence networks for recommending friends in social networks. In Proceedings of 2nd ACM SIGMM Workshop on Social Media (WSM'10). ACM, New York, 27--32. DOI:http://dx.doi.org/10.1145/1878151.1878160 Google Scholar
Digital Library
- I. Konstas, V. Stathopoulos, and J. M. Jose. 2009. On social networks and collaborative recommendation. In Proceedings of SIGIR. ACM, 195--202. Google Scholar
Digital Library
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems, 1097--1105.Google Scholar
- J. Leskovec, K. J. Lang, and M. Mahoney. 2010. Empirical comparison of algorithms for network community detection. In Proceedings of the 19th International Conference on World Wide Web. ACM, 631--640. Google Scholar
Digital Library
- L.-J. Li, X. Kong, and P. S. Yu. 2014. Visual recognition by exploiting latent social links in image collections. In MultiMedia Modeling, Springer, 121--132. Google Scholar
Digital Library
- Y. Lin, F. Lv, S. Zhu, M. Yang, T. Cour, K. Yu, L. Cao, and T. Huang. 2011. Large-scale image classification: Fast feature extraction and svm training. In Proceedings of CVPR. 1689--1696. Google Scholar
Digital Library
- X. Liu, Z. Shi, Z. Li, X. Wang, and Z. Shi. 2010. Sorted label classifier chains for learning images with multi-label. In Proceedings of the 18th ACM International Conference on Multimedia (MM'10). Google Scholar
Digital Library
- Y. Liu, R. Jin, and L. Yang. 2006. Semi-supervised multi-label learning by constrained non-negative matrix factorization. In Proceedings of AAAI. 421--426. Google Scholar
Digital Library
- Q. Lu and L. Getoor. 2003. Link-based classification. In Proceedings of ICML.Google Scholar
- Yong Luo, Dacheng Tao, Bo Geng, Chao Xu, and Stephen J. Maybank. 2013. Manifold regularized multitask learning for semi-supervised multilabel image classification. IEEE Trans. Image Process. 22, 2, 523--536. Google Scholar
Digital Library
- L. K. McDowell, K. M. Gupta, and D. W. Aha. 2007. Cautious inference in collective classification. In Proceedings of AAAI. 596--601. Google Scholar
Digital Library
- G. Palla, I. Derényi, I. Farkas, and T. Vicsek. 2005. Uncovering the overlapping community structure of complex networks in nature and society. Nature 435, 7043, 814--818.Google Scholar
- Guo-Jun Qi, Xian-Sheng Hua, Yong Rui, Jinhui Tang, Tao Mei, and Hong-Jiang Zhang. 2007. Correlative multi-label video annotation. In Proceedings of the 15th International Conference on Multimedia. ACM, 17--26. Google Scholar
Digital Library
- J. Read, B. Pfahringer, G. Holmes, and E. Frank. 2009. Classifier chains for multi-label classification. In Proceedings of ECML/PKDD. Google Scholar
Digital Library
- Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg, and Li Fei-Fei. 2014. ImageNet Large Scale Visual Recognition Challenge.Google Scholar
- Z. Stone, T. Zickler, and T. Darrell. 2008. Autotagging Facebook: Social network context improves photo annotation. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2008 (CVPRW'08). 1--8. DOI:http://dx.doi.org/10.1109/CVPRW.2008.4562956Google Scholar
- Z. Stone, T. Zickler, and T. Darrell. 2010. Toward large-scale face recognition using social network context. Proc. IEEE 98, 8, 1408--1415.Google Scholar
Cross Ref
- Pang-Ning Tan, Michael Steinbach, and Vipin Kumar. 2005. Introduction to Data Mining. Addison Wesley.Google Scholar
- S. V. N. Vishwanathan, Z. Sun, and N. Theera-Ampornpunt. 2010. Multiple kernel learning and the SMO algorithm. In Proceedings of NIPS. 2361--2369.Google Scholar
- G. Wang, A. Gallagher, J. Luo, and D. Forsyth. 2010. Seeing people in social context: Recognizing people and social relationships. In Proceedings of ECCV. Springer, 169--182. Google Scholar
Digital Library
- S. Wasserman and K. Faust. 1994. Social Network Analysis: Methods and Applications. Cambridge University Press.Google Scholar
- J. Weston, S. Bengio, and N. Usunier. 2010. Large scale image annotation: Learning to rank with joint word-image embeddings. Mach. Learn. 81, 1, 21--35. Google Scholar
Digital Library
- Zheng-Jun Zha, Xian-Sheng Hua, Tao Mei, Jingdong Wang, G.-J. Qi, and Zengfu Wang. 2008. Joint multi-label multi-instance learning for image classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2008 (CVPR'08). IEEE, 1--8.Google Scholar
- J. Zhuang, T. Mei, S. Hoi, X. Hua, and S. Li. 2011. Modeling social strength in social media community via kernel-based learning. In Proceedings of the 19th ACM International Conference on Multimedia (MM'11). Google Scholar
Digital Library
Index Terms
CelebrityNet: A Social Network Constructed from Large-Scale Online Celebrity Images
Recommendations
Building social capital with Facebook: Type of network, availability of other media, and social self-efficacy matter#
Highlights- Type of friends affects building social capital via Facebook and traditional media.
AbstractFindings about Facebook's effect on relationships are mixed, possibly due to lack of models that acknowledge differences across users, types of their friends, and use of competing media. To address this, we proposed and tested how ...
Social Multimedia Signals: Sense, Process, and Put Them to Work
Social media gives ordinary people the power to be content creators and information disseminators. This information is embedded in multimedia shared across social networks, containing valuable indications about various facets of human life–about ...
Media Lifecycle and Content Analysis in Social Media Communities
ICME '12: Proceedings of the 2012 IEEE International Conference on Multimedia and ExpoThis paper examines the role of content analysis in media-rich online communities. We highlight changes in the multimedia generation and consumption process that has occurred the past decade, and discuss several new angles this has brought to multimedia ...






Comments