M
Matthai Philipose
Researcher at Microsoft
Publications - 122
Citations - 10623
Matthai Philipose is an academic researcher from Microsoft. The author has contributed to research in topics: Activity recognition & Dynamic compilation. The author has an hindex of 45, co-authored 122 publications receiving 9790 citations. Previous affiliations of Matthai Philipose include Intel & University of Washington.
Papers
More filters
Journal ArticleDOI
Inferring activities from interactions with objects
Matthai Philipose,Kenneth P. Fishkin,Mike Perkowitz,Donald J. Patterson,Dieter Fox,Henry Kautz,Dirk Hähnel +6 more
TL;DR: The key observation is that the sequence of objects a person uses while performing an ADL robustly characterizes both the ADL's identity and the quality of its execution.
Proceedings ArticleDOI
Mapping and localization with RFID technology
TL;DR: A probabilistic measurement model for RFID readers that allow us to accurately localize RFID tags in the environment and demonstrates how such maps can be used to localize a robot and persons in their environment.
Patent
Inertially controlled switch and RFID tag
TL;DR: One or more inertially controlled switches may be coupled to a radio frequency identification (RFID) tag, so that the response of the RFID tag indicates the state of the switch as discussed by the authors.
Proceedings ArticleDOI
Fine-grained activity recognition by aggregating abstract object usage
TL;DR: A sequence of increasingly powerful probabilistic graphical models for activity recognition are presented that can reason tractably about aggregated object instances and gracefully generalizes from object instances to their classes by using abstraction smoothing.
Journal ArticleDOI
Real-Time Video Analytics: The Killer App for Edge Computing
Ganesh Ananthanarayanan,Paramvir Bahl,Peter Bodik,Krishna Chintalapudi,Matthai Philipose,Lenin Ravindranath,Sudipta N. Sinha +6 more
TL;DR: A geographically distributed architecture of public clouds and edges that extend down to the cameras is the only feasible approach to meeting the strict real-time requirements of large-scale live video analytics.