Toward large-scale face recognition using social network context

Proceedings of the IEEE

Volumn 98, Issue 8, 2010, Pages 1408-1415

  Stone, Zak ^a   Zickler, Todd ^a   Darrell, Trevor ^b  

^a HARVARD UNIVERSITY   (United States)

^b UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

Face recognition; Graphical models; Social network context; Structured prediction

Indexed keywords

IMAGE ENHANCEMENT; PHOTOGRAPHY; SOCIAL NETWORKING (ONLINE);

AUTOMATIC FACE RECOGNITION; COMPUTATIONAL TOOLS; FACE RECOGNITION RATES; GRAPHICAL MODEL; ON-LINE SOCIAL NETWORKS; PHOTO COLLECTIONS; SOCIAL NETWORK CONTEXTS; STRUCTURED PREDICTION;

FACE RECOGNITION;

EID: 77954864048     PISSN: 00189219     EISSN: None     Source Type: Journal    
DOI: 10.1109/JPROC.2010.2044551     Document Type: Conference Paper

References (61)

1. R. Scoble, Mark Zuckerberg, Founder of Facebook, and Jet Li, Famous Martial Arts Star. [Online]. Available: http://www.flickr. com/photos/ scobleizer/3238530126/
2. Z. Stone, T. Zickler, and T. Darrell, BAutotagging Facebook: Social network context improves photo annotation, [in Proc. 1st IEEE Workshop Internet Vis., 2008, DOI: 10.1109/CVPRW.2008.4562956.
3. J. P. Phillips, T. W. Scruggs, A. J. O'Toole, P. J. Flynn, K. W. Bowyer, C. L. Schott, and M. Sharpe, BFRVT 2006 and ICE 2006 large-scale results, [Nat. Inst. Standards Technol., Gaithersburg, MD, Tech. Rep., Mar. 2007.
4. G. Huang, V. Jain, and E. Learned-Miller, BUnsupervised joint alignment of complex images, [in Proc. IEEE Int. Conf. Comput. Vis., 2007, DOI: 10.1109/ICCV.2007.4408858.
5. M. Everingham, J. Sivic, and A. Zisserman, BHello! my name is.. Buffy-automatic naming of characters in TV video, [in Proc. British Mach. Vis. Conf., 2006, pp. 899-908.
6. N. Kumar, A. Berg, P. Belhumeur, and S. Nayar, BAttribute and simile classifiers for face verification, [in Proc. IEEE Int. Conf. Comput. Vis., 2009, DOI: 10.1109/ICCV. 2009.5459250.
7. L. Wolf, T. Hassner, and Y. Taigman, BDescriptor based methods in the wild, [in Proc. Faces in Real-Life Images Workshop, Oct. 2008. [Online]. Available: http://hal. inria.fr/inria-00326729/en/
8. Y. Taigman, L. Wolf, T. Hassner, and I. Tel-Aviv, BMultiple one-shots for utilizing class label information, [in Proc. British Mach. Vis. Conf., 2009. [Online]. Available: http://www.bmva.org/bmvc/2009/Papers/Paper391/Paper391.pdf
9. M. Guillaumin, J. Verbeek, C. Schmid, I. Lear, and L. Kuntzmann, BIs that you? Metric learning approaches for face identification, [in Proc. IEEE Int. Conf. Comput. Vis., 2009, DOI: 10.1109/ICCV.2009.5459197.
10. G. Huang, M. Ramesh, T. Berg, and E. Learned-Miller, BLabeled faces in the wild: A database for studying face recognition in unconstrained environments Univ. Massachusetts, Amherst, MA, Tech. Rep. 07-49, Oct. 2007.
11. T. Berg, A. Berg, J. Edwards, M. Maire, R. White, Y. Teh, E. Learned-Miller, and D. Forsyth, BNames and faces in the news, [in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2004, vol. 2, pp. II-848-II-854.
12. T. Berg, A. Berg, J. Edwards, and D. Forsyth, BWho's in the picture?[in Proc. Adv. Neural Inf. Process. Syst., 2004, pp. 137-144.
13. S. Satoh and T. Kanade, BName-it: Association of face and name in video, [in IEEE Conf. Comput. Vis. Pattern Recognit., 1997, pp. 368-373.
14. J. Yagnik and A. Islam, BLearning people annotation from the web via consistency learning, [in Proc. Int. Workshop Multimedia Inf. Retrieval, 2007, pp. 285-290.
15. M. Zhao and J. Yagnik, BLarge scale learning and recognition of faces in web videos, [in Proc. 8th Int. Conf. Autom. Face Gesture Recognit., 2008, DOI: 10.1109/AFGR.2008. 4813381.
16. M. Naaman, R. Yeh, H. Garcia-Molina, and A. Paepcke, BLeveraging context to resolve identity in photo albums, [in Proc. 5th ACM/IEEE-CS Joint Conf. Digit. Libraries, 2005, pp. 178-187.
17. L. Zhang, L. Chen, M. Li, and H. Zhang, BAutomated annotation of human faces in family albums, [in Proc. ACM Int. Conf. Multimedia, 2003, pp. 355-358.
18. D. Anguelov, K. Lee, S. Gokturk, and B. Sumengen, BContextual identity recognition in personal photo albums, [in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2007, DOI: 10.1109/CVPR.2007.383057.
19. J. Sivic, C. Zitnick, and R. Szeliski, BFinding people in repeated shots of the same scene, [in Proc. British Mach. Vis. Conf., 2006, pp. 909-918.
20. A. Gallagher, P. Pittsburgh, and T. Chen, BUsing group prior to identify people in consumer images, [in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2007, DOI: 10.1109/CVPR.2007.383492.
21. A. Gallagher, P. Pittsburgh, and T. Chen, BUnderstanding images of groups of people, [in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2009, pp. 256-263.
22. A. Gallagher and T. Chen, BEstimating age, gender, and identity using first name priors, [in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2008, DOI: 10.1109/CVPR.2008. 4587609.
23. K. Rodden and K. Wood, BHow do people manage their digital photographs?[in Proc. SIGCHI Conf. Human Factors Comput. Syst., 2003, pp. 409-416.
24. L. Weiiyin, S. Dumais, Y. Sun, H. Zhang, M. Czerwinski, and B. Field, BSemi-automatic image annotation, [in Human-Computer Interaction-Interact '01. Amsterdam, The Netherlands: IOS Press, 2001.
25. B. Shneiderman and H. Kang, BDirect annotation: A drag and drop strategy for labeling photos, [in Proc. Int. Conf. Inf. Vis., 2000, pp. 88-95.
26. A. Kuchinsky, C. Pering, M. Creech, D. Freeze, B. Serra, and J. Gwizdka, BFotoFile: A consumer multimedia organization and retrieval system, [in Proc. SIGCHI Conf. Human Factors Comput. Syst., 1999, pp. 496-503.
27. C. Marlow, M. Naaman, D. Boyd, and M. Davis, BHT06, tagging paper, taxonomy, Flickr, academic article, to read, [in Proc. Conf. Hypertext Hypermedia, 2006, pp. 31-40.
28. M. Ames and M. Naaman, BWhy we tag: Motivations for annotation in mobile and online media, [in Proc. SIGCHI Conf. Human Factors Comput. Syst., 2007, pp. 971-980.
29. O. Nov, M. Naaman, and C. Ye, BWhat drives content tagging: The case of photos on Flickr, [in Proc. SIGCHI Conf. Human Factors Comput. Syst., 2008, pp. 1097-1100.
30. O. Nov, M. Naaman, and C. Ye, BMotivational, structural and tenure factors that impact online community photo sharing, [in Proc. AAAI Int. Conf. Weblogs Social Media, 2009. [Online]. Available: http://www.aaai.org/ocs/index. php/ICWSM/09/paper/view/206/426.
31. Facebook Statistics. [Online]. Available: http://www.facebook.com/press/ info.php?statistics
32. Engineering @ Facebook's Notes. [Online]. Available: http://www.facebook. com/note. php?note-id=76191543919
33. Open Source Computer Vision Library (OpenCV). [Online]. Available: http://www.intel.com/research/mrl/research/opencv/
34. P. A. Viola and M. J. Jones, BRapid object detection using a boosted cascade of simple features, [in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2001, pp. 511-518.
35. K. R. Harsha, My Grandparents and Me! [Online]. Available: http://www.flickr.com/photos/mynameisharsha/3286864307/
36. J. Lafferty, A. McCallum, and F. Pereira, BConditional random fields: Probabilistic models for segmenting and labeling sequence data, [in Proc. 18th Int. Conf. Mach. Learn., 2001, pp. 282-289.
37. M. Collins, BDiscriminative training methods for hidden Markov models, [in Proc. Conf. Empirical Methods Natural Lang. Process., 2002, DOI: 10.3115/1118693.1118694.
38. B. Taskar, C. Guestrin, and D. Koller, BMaximum-margin Markov networks, [in Proc. Adv. Neural Inf. Process. Syst., 2003. [Online]. Available: http://books.nips.cc/nips16.html
39. I. Tsochantaridis, T. Joachims, T. Hofmann, and Y. Altun, BLarge margin methods for structured and interdependent output variables, [J. Mach. Learn. Res., vol. 6, pp. 1453-1484, Sep. 2005.
40. G. Bakir, T. Hofmann, B. Scḧolkopf, A. Smola, B. Taskar, and S. Vishwanathan, Predicting Structured Data. Cambridge, MA: MIT Press, 2007.
41. S. Wasserman and K. Faust, Social Network Analysis: Methods and Applications. Cambridge, U.K.: Cambridge Univ. Press, 1994.
42. D. Liben-Nowell and J. Kleinberg, BThe link prediction problem for social networks, [in Proc. 12th Int. Conf. Inf. Knowl. Manage., 2003, pp. 556-559.
43. A. Clauset, M. Newman, and C. Moore, BFinding community structure in very large networks, [Phys. Rev. E, Stat. Phys. Plasmas Fluids Relat. Interdiscip. Top., vol. 70, no. 6, 2004, DOI: 10.1103/PhysRevE.70.066111.
44. A. Mayer and S. Puller, BThe old boy (and girl) network: Social network formation on university campuses, [J. Public Econom., vol. 92, no. 1-2, pp. 329-347, 2008.
45. K. Lewis, J. Kaufman, M. Gonzalez, A. Wimmer, and N. Christakis, BTastes, ties, and time: A new social network dataset using Facebook.com, [Social Netw., vol. 30, no. 4, pp. 330-342, 2008.
46. V. Kolmogorov, BConvergent tree-reweighted message passing for energy minimization, [IEEE Trans. Pattern Anal. Mach. Intell., vol. 28, no. 10, pp. 1568-1583, Oct. 2006.
47. P. Kohli, A. Shekhovtsov, C. Rother, V. Kolmogorov, and P. Torr, BOn partial optimality in multi-label MRFs, [in Proc. 25th Int. Conf. Mach. Learn., 2008, pp. 480-487.
48. T. Finley and T. Joachims, BTraining structural SVMs when exact inference is intractable, [in Proc. Int. Conf. Mach. Learn., 2008, pp. 304-311.
49. SVMstruct. Support vector machine for complex outputs. [Online]. Available: http://svmlight.joachims.org/svm
50. A. Gallagher and T. Chen, BEstimating age, gender and identity using first name priors, [in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2008, DOI: 10.1109/CVPR.2008. 4587609.
51. A. Friedman, BFraming pictures: The role of knowledge in automatized encoding and memory for gist, [J. Exp. Psychol., Gen., vol. 108, pp. 316-355, 1979.
52. A. Oliva and A. Torralba, BModeling the shape of a scene: A holistic representation of the spatial envelope, [Int. J. Comput. Vis., vol. 42, no. 3, pp. 145-175, 2001.
53. S. Lazebnik, C. Schmid, and J. Ponce, BBeyond bags of features: Spatial pyramid matching for recognizing natural scene categories, [in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2006, pp. 2169-2178.
54. L. Fei-Fei and P. Perona, BA Bayesian hierarchical model for learning natural scene categories, [in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2005, vol. 2, pp. 524-531.
55. A. Bosch, A. Zisserman, and X. Munoz, BScene classification via pLSA, [in Proc. Eur. Conf. Comput. Vis., 2006, vol. 4, pp. 517-530.
56. Y. Song and T. Leung, BContext-aided human recognition-clustering, [in Proc. Eur. Conf. Comput. Vis., 2006, pp. 382-395.
57. T. Joachims, T. Finley, and C.-N. Yu, BCutting-plane training of structural SVMs, [Mach. Learn., vol. 77, pp. 27-59, 2009.
58. C. Teo, A. Smola, S. Vishwanathan, and Q. Le, BA scalable modular convex solver for regularized risk minimization, [in Proc. 13th ACM SIGKDD Int. Conf. Knowl. Disc. Data Mining, 2007, pp. 727-736.
59. D. Sontag and T. Jaakkola, BNew outer bounds on the marginal polytope, [Proc. Adv. Neural Inf. Process. Syst., vol. 21, pp. 1393-1400, 2007.
60. N. Komodakis, N. Paragios, and G. Tziritas, BMRF optimization via dual decomposition: Message-passing revisited, [in Proc. IEEE Int. Conf. Comput. Vis., 2007, DOI: 10.1109/ICCV.2007.4408890.
61. N. Komodakis and N. Paragios, BBeyond loose LP-relaxations: Optimizing MRFs by repairing cycles, [in Proc. Eur. Conf. Comput. Vis. III, 2008, pp. 806-820.