• Publications
  • Influence
Mapping and localization with RFID technology
TLDR
We analyze whether radio frequency identification (RFID) technology can be used to improve the localization of mobile robots and persons in their environment. Expand
A Long-Term Evaluation of Sensing Modalities for Activity Recognition
TLDR
We study activity recognition using 104 hours of annotated data collected from a person living in an instrumented home. Expand
Fine-grained activity recognition by aggregating abstract object usage
TLDR
We present a sequence of increasingly powerful probabilistic graphical models for activity recognition. Expand
MCDNN: An Approximation-Based Execution Framework for Deep Stream Processing Under Resource Constraints
TLDR
We consider applying computer vision to video on cloud-backed mobile devices using Deep Neural Networks (DNNs). Expand
Live Video Analytics at Scale with Approximation and Delay-Tolerance
TLDR
We describe VideoStorm, a video analytics system that processes thousands of video analytics queries on live video streams over large clusters. Expand
Focus: Querying Large Video Datasets with Low Latency and Low Cost
TLDR
We build Focus, a system for low-latency and low-cost querying on large video datasets. Expand
A Scalable Approach to Activity Recognition based on Object Use
TLDR
We present a dynamic Bayesian network model which combines RFID and video data to jointly infer the most likely activity and object labels. Expand
Inferring activities from interactions with objects
TLDR
A new paradigm for ADL inferencing leverages radio-frequency-identification technology, data mining, and a probabilistic inference engine to recognize ADLs, based on the objects people use. Expand
Unsupervised Activity Recognition Using Automatically Mined Common Sense
TLDR
We show that models so extracted are sufficient to automatically produce labeled segmentations of activity data with an accuracy of 42% over 26 activities, well above the 3.89% baseline. Expand
DyC: an expressive annotation-directed dynamic compiler for C
TLDR
We present the design of DyC, a dynamic-compilation system for C based on run-time specialization. Expand
...
1
2
3
4
5
...