• Publications
  • Influence
Mapping and localization with RFID technology
TLDR
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.
A Long-Term Evaluation of Sensing Modalities for Activity Recognition
TLDR
A number of issues important for designing activity detection systems that may not have been as evident in prior work when data was collected under more controlled conditions are characterized.
Focus: Querying Large Video Datasets with Low Latency and Low Cost
TLDR
Focus, a system for low-latency and low-cost querying on large video datasets, uses cheap ingestion techniques to index the videos by the objects occurring in them and handles the lower accuracy of the cheap CNNs by judiciously leveraging expensive CNNs at query-time.
Live Video Analytics at Scale with Approximation and Delay-Tolerance
TLDR
VideoStorm is described, a video analytics system that processes thousands of video analytics queries on live video streams over large clusters, considering two key characteristics of video Analytics: resource-quality tradeoff with multi-dimensional configurations, and variety in quality and lag goals.
Fine-grained activity recognition by aggregating abstract object usage
TLDR
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.
MCDNN: An Approximation-Based Execution Framework for Deep Stream Processing Under Resource Constraints
TLDR
This work describes how several common DNNs, when subjected to state-of-the art optimizations, trade off accuracy for resource use such as memory, computation, and energy, and introduces two new and powerful DNN optimizations that exploit it.
A Scalable Approach to Activity Recognition based on Object Use
TLDR
It is demonstrated that it is possible to automatically learn object models from video of household activities and employ these models for activity recognition, without requiring any explicit human labeling.
Inferring activities from interactions with objects
TLDR
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.
Unsupervised Activity Recognition Using Automatically Mined Common Sense
TLDR
To the first human activity inferencing system shown to learn from sensed activity data with no human intervention per activity learned, even for labeling, this work shows that segmentation obtained is sufficient to bootstrap learning.
Nexus: a GPU cluster engine for accelerating DNN-based video analysis
TLDR
Nexus is a fully implemented system that includes cluster-scale resource management that performs detailed scheduling of GPUs, reasoning about groups of DNN invocations that need to be co-scheduled, and moving from the conventional whole-DNN execution model to executing fragments ofDNNs.
...
...