• Publications
  • Influence
Multi-PIE
TLDR
A close relationship exists between the advancement of face recognition algorithms and the availability of face databases varying factors that affect facial appearance. Expand
  • 1,173
  • 237
  • PDF
Information revelation and privacy in online social networks
TLDR
We analyze the online behavior of 4,000 Carnegie Mellon University students who have joined a popular social networking site catered to colleges and study their usage of the site's privacy settings. Expand
  • 2,291
  • 172
  • PDF
Imagined Communities: Awareness, Information Sharing, and Privacy on the Facebook
TLDR
We look for underlying demographic or behavioral differences between the communities of the network's members and non-members; we analyze the impact of privacy concerns on members' behavior; we compare members' stated attitudes with actual behavior; and we document changes in behavior subsequent to privacy-related information exposure. Expand
  • 1,825
  • 153
  • PDF
The CMU Motion of Body (MoBo) Database
TLDR
In March 2001 we started to collect the CMU Motion of Body database. Expand
  • 608
  • 76
  • PDF
Silhouette-based human identification from body shape and gait
TLDR
We present a viewpoint-dependent technique based on template matching of body silhouettes. Expand
  • 536
  • 32
  • PDF
Appearance-based face recognition and light-fields
TLDR
We propose an algorithm for face recognition across pose based on an algorithm to estimate the (eigen) light-field of a face from a set of images. Expand
  • 297
  • 22
  • PDF
An Image Preprocessing Algorithm for Illumination Invariant Face Recognition
TLDR
We propose a new image preprocessing algorithm that compensates for illumination variations in images. Expand
  • 385
  • 20
  • PDF
Generic vs. person specific active appearance models
TLDR
We present an empirical evaluation that shows that Person Specific AAMs are, as expected, both easier to build and more robust to fit than Generic AAMS. Expand
  • 182
  • 15
Integrating Utility into Face De-identification
TLDR
We introduce a formal privacy protection schema based on k-anonymity that provably protects privacy and preserves data utility in face images. Expand
  • 112
  • 15
  • PDF
Silent Listeners: The Evolution of Privacy and Disclosure on Facebook
TLDR
We use profile data from a longitudinal panel of 5,076 Facebook users to understand how their privacy and disclosure behavior changed between 2005---the early days of the network---and 2011. Expand
  • 291
  • 13
  • PDF
...
1
2
3
4
5
...