Abstract
Automatically linking faces in Web videos with their names scattered in the surrounding text (e.g., the user generated title and tags) is an important task for many applications. Traditionally, this task is accomplished either by jointly exploring visual-textual consistency under constraints, or by leveraging external resources, e.g., public facial images. This paper follows the second paradigm and implements the name-face association by matching faces appearing in Web videos with carefully collected Web facial images. Specially, given a Web video, we first identify the relevant and discriminative tags from its surrounding text. The tags are defined as Contextual Tags (CTags) as they roughly give the semantic context of the video (e.g., who are doing what at when and where). Then, facial images are retrieved by issuing a commercial search engine using the assembled text queries, where each query contains a detected name and one of the top CTags. By doing this, we crawl facial images that are highly relevant to the person in the video context, and thus the task of name-face association can be simply implemented by matching faces. Compared with traditional methods, our novelty lies in the exploration of both visual content of the video and crowdsourced text of the context that aims to find more specific facial images from the Web to facilitate the association. Experimental results on real-world Web videos containing faces and celebrity names show that the proposed method outperforms several existing methods in performance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In fact, his true name is Jan Kraus. He is recognized as Jana Krause since he is known as the host of a famous TV show named Jana Krause.
- 2.
References
Bu, J., Xu, B., Wu, C.: Unsupervised face-name association via commute distance. ACM Multimedia 2012, 219–228 (2012)
Chen, Z.N., Ngo, C.W., Zhang, W., Cao, J., Jiang, Y.G.: Name-face association in web videos: a large-scale dataset, baselines, and open issues. J. Comput. Sci. Technol. 29(5), 785–798 (2014)
Zhao, M., Yagnik, J.: Large-scale learning and recognition of faces in web videos. IEEE FGR 2008, 1–7 (2008)
Zhang, Y.F., Xu, C.S., Lu, H.Q.: Character identification in feature-length films using global face-name matching. IEEE Trans. Multimedia 11(7), 1276–1288 (2009)
Guillaumin, M., Mensink, T., Verbeek, J.: Face recognition from caption-based supervision. Int. J. Comput. Vis. 96(1), 64–82 (2012)
Chen, Z.N., Ngo, C.W., Cao, J., Zhang, W.: Community as a connector: associating faces with celebrity names in web videos. ACM Multimedia 2012, 809–812 (2012)
Chen, Z.N., Feng, B.L., Ngo, C.W., Jia, C.Y., Huang, X.S.: Improving automatic name-face association using celebrity images on the web. ICMR 2015, 623–626 (2015)
Pang, L., Ngo, C.W.: Unsupervised celebrity face naming in web videos. IEEE Trans. Multimedia 17(6), 854–866 (2015)
Zhao, W.L., Wu, X., Ngo, C.W.: On the annotation of web videos by efficient near-duplicate search. IEEE Trans. Multimedia 12(5), 448–461 (2010)
Siersdorfer, S., Pedro, J.S., Sanderson, M.: Content redundancy in YouTube and its application to video tagging. ACM Trans. Inf. Syst. 29(3), 301–331 (2011)
Liu, D., Yan, S.C., Hua, X.S., Zhang, H.J.: Image retagging using collaborative tag propagation. IEEE Trans. Multimedia 13(4), 702–712 (2011)
Chen, Z.N., Cao, J., Xia, T., Song, Y.C., Zhang, Y.D., Li, J.T.: Web video retagging. Multimedia Tools Appl. 55(1), 53–82 (2011)
Li, X., Snoek, C.G.M., Worring, M.: Learning social tag relevance by neighbor voting. IEEE Trans. Multimedia 11(7), 1310–1322 (2009)
Chen, Z.N., Cao, J., Song, Y.C., Guo, J.B., Zhang, Y.D., Li, J.T.: Context-oriented web video tag recommendation. WWW 2010, 1079–1080 (2010)
Chen, Z.N., Cao, J., Song, Y.C., Zhang, Y.D., Li, J.T.: Web video categorization based on Wikipedia categories and content-duplicate open resources. In: ACM Multimedia 2010, pp. 1107–1110 (2010)
Chen, Z., Feng, B., Xie, H., Zheng, R., Xu, B.: Video to article hyperlinking by multiple tag property exploration. In: Gurrin, C., Hopfgartner, F., Hurst, W., Johansen, H., Lee, H., O’Connor, N. (eds.) MMM 2014, Part I. LNCS, vol. 8325, pp. 62–73. Springer, Heidelberg (2014)
Cao, J., Zhang, Y.D., Song, Y.C., Chen, Z.N., Zhang, X., Li, J.T.: MCG-WEBV: a benchmark dataset for web video analysis, Technical report, pp. 1–10 (2009)
Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: DeepFace: closing the gap to human-level performance in face verification. CVPR 2014, 1701–1708 (2014)
Acknowledgements
This research is supported by National Nature Science Foundation of China (Grant No. 61303175, 61303171).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Chen, Z., Zhang, W., Xie, H., Feng, B., Gu, X. (2016). Context-Oriented Name-Face Association in Web Videos. In: Chen, E., Gong, Y., Tie, Y. (eds) Advances in Multimedia Information Processing - PCM 2016. PCM 2016. Lecture Notes in Computer Science(), vol 9917. Springer, Cham. https://doi.org/10.1007/978-3-319-48896-7_62
Download citation
DOI: https://doi.org/10.1007/978-3-319-48896-7_62
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-48895-0
Online ISBN: 978-3-319-48896-7
eBook Packages: Computer ScienceComputer Science (R0)