Show simple item record

dc.contributor.authorCastro, Daniel
dc.contributor.authorHickson, Steven
dc.contributor.authorBettadapura, Vinay
dc.contributor.authorThomaz, Edison
dc.contributor.authorAbowd, Gregory D.
dc.contributor.authorChristensen, Henrik
dc.contributor.authorEssa, Irfan
dc.date.accessioned2016-04-20T13:52:54Z
dc.date.available2016-04-20T13:52:54Z
dc.date.issued2015
dc.identifier.citationCastro, D., Hickson, S., Bettadapura, V., Thomaz, E., Abowd, G., Christensen, H., & Essa, I. (2015). Predicting Daily Activities from Egocentric Images Using Deep Learning. Proceedings of the 2015 ACM International Symposium on Wearable Computers (ISWC '15), pp. 75-82.en_US
dc.identifier.isbn978-1-4503-3578-2
dc.identifier.urihttp://hdl.handle.net/1853/54747
dc.descriptionCopyright ©2015 ACMen_US
dc.descriptionDOI: 10.1145/2802083.2808398
dc.description.abstractWe present a method to analyze images taken from a passive egocentric wearable camera along with the contextual information, such as time and day of week, to learn and predict everyday activities of an individual. We collected a dataset of 40,103 egocentric images over a 6 month period with 19 activity classes and demonstrate the benefit of state-of-the-art deep learning techniques for learning and predicting daily activities. Classification is conducted using a Convolutional Neural Network (CNN) with a classification method we introduce called a late fusion ensemble. This late fusion ensemble incorporates relevant contextual information and increases our classification accuracy. Our technique achieves an overall accuracy of 83.07% in predicting a person's activity across the 19 activity classes. We also demonstrate some promising results from two additional users by fine-tuning the classifier with one day of training data.en_US
dc.language.isoen_USen_US
dc.publisherGeorgia Institute of Technologyen_US
dc.subjectActivity predictionen_US
dc.subjectConvolutional neural networksen_US
dc.subjectDeep learningen_US
dc.subjectEgocentric visionen_US
dc.subjectHealthen_US
dc.subjectLate fusion ensembleen_US
dc.subjectWearable computingen_US
dc.titlePredicting Daily Activities From Egocentric Images Using Deep Learningen_US
dc.typeProceedingsen_US
dc.contributor.corporatenameGeorgia Institute of Technology. Institute for Robotics and Intelligent Machinesen_US
dc.contributor.corporatenameGeorgia Institute of Technology. College of Computingen_US
dc.contributor.corporatenameGeorgia Institute of Technology. School of Interactive Computingen_US
dc.publisher.originalAssociation for Computing Machinery
dc.identifier.doi10.1145/2802083.2808398
dc.embargo.termsnullen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record