Image annotation using personal calendars as context

Authors:
Andrew C. Gallagher;Carman G. Neustaedter;Liangliang Cao;Jiebo Luo;Tsuhan Chen
Affiliations:
Eastman Kodak Company, Rochester, USA;Eastman Kodak Company, Rochester, NY, USA;University of Illinois, Urbana, IL, USA;Eastman Kodak Company, Rochester, USA;Carnegie Mellon University, Pittsburgh, USA
Venue:
MM '08 Proceedings of the 16th ACM international conference on Multimedia
Year:
2008

Citing 4
Cited 7

Histograms of Oriented Gradients for Human Detection

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Leveraging geo-referenced digital photographs

Leveraging geo-referenced digital photographs
Domestic awareness and the role of family calendars

Domestic awareness and the role of family calendars
Automated event clustering and quality screening of consumer pictures for digital albuming

IEEE Transactions on Multimedia

Style modeling for tagging personal photo collections

Proceedings of the ACM International Conference on Image and Video Retrieval
Context dependent SVMs for interconnected image network annotation

Proceedings of the international conference on Multimedia
Tag refinement in an image folksonomy using visual similarity and tag co-occurrence statistics

Image Communication
Context-based support vector machines for interconnected image annotation

ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part I
Personalizing automated image annotation using cross-entropy

MM '11 Proceedings of the 19th ACM international conference on Multimedia
Tag suggestion on youtube by personalizing content-based auto-annotation

Proceedings of the ACM multimedia 2012 workshop on Crowdsourcing for multimedia
Object class detection: A survey

ACM Computing Surveys (CSUR)

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we introduce the idea of using the context of a personal calendar for labeling photo collections. Calendar event annotations are matched to images based on image capture time, and a Naïve Bayes model considers features from the calendar events as well as from computer vision-based image analysis to determine if the image actually matches the calendar event. This approach has the benefit that it requires no extra annotation from the consumer, since most people already keep calendars. In our test collections, 36% of personal images could be tagged with a label from a personal calendar. Note that our preliminary results represent a lower bound on the performance that is possible because all the system components are expected to improve over time. As people migrate toward digital calendars, we can also expect more consistency in their calendar labels, which should improve the annotation accuracy.