Carnegie Mellon Robotics Institute
Fernando De la Torre Frade and Carlos Agell
International Conference on Multimedia and Expo, July, 2007.
| Download |
|
| Abstract |
| Time management is an important aspect of a successful professional life. In order to have a better understanding of where our time goes, we propose a system that summarizes the user's daily activity (e.g. sleeping, walking, working on the pc, talking, ...) using all-day multimodal data recordings. Two main novelties are proposed: 1) A system that combines both physical and contextual awareness hardware and software. It records synchronized audio, video, body sensors, GPS and computer monitoring data. 2) A semi-supervised temporal clustering (SSTC) algorithm that accurately and efficiently groups huge amounts of multimodal data into different activities.
The effectiveness and accuracy of our SSTC is demonstrated in synthetic and real examples of activity segmentation from multimodal data gathered over long periods of time. |
| Keywords |
| clustering, activity recognition, multimodal summarization |
| Notes |
Associated Center(s) / Consortia:
Vision and Autonomous Systems Center Associated Lab(s) / Group(s):
Component Analysis Associated Project(s):
Multimodal Diaries Note: associated project multimodal diaries |
| Text Reference |
| Fernando De la Torre Frade and Carlos Agell, "Multimodal Diaries," International Conference on Multimedia and Expo, July, 2007. |
| BibTeX Reference |
|
@inproceedings{De_la_Torre_Frade_2007_5734, author = "Fernando {De la Torre Frade} and Carlos Agell", title = "Multimodal Diaries", booktitle = "International Conference on Multimedia and Expo", month = "July", year = "2007", Notes = "associated project multimodal diaries" } |
| The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University. Contact Us | Update Instructions |