Publications
-
Video Object Co-Segmentation by Regulated Maximum Weight Cliques
In this paper, we propose a novel approach for object cosegmentation in arbitrary videos by sampling, tracking and matching object proposals via a Regulated Maximum Weight Clique (RMWC) extraction scheme.
-
Augmented Reality Binoculars on the Move
We present our latest improvements and additions to our pose estimation pipeline and demonstrate stable registration of objects on the real world scenery while the binoculars are undergoing significant amount…
-
Conceptual Models of Energy Transfer and Regulation
We consider a representation of energy transfer and regulation for biological processes, and consider several example questions that can be answered using this representation.
-
Content Matching for Short Duration Speaker Recognition
We show how content matching can be effectively done at the statistics level to enable the use of standard veriļ¬cation backends. While no signiļ¬cant improvements were observed for the general…
-
A Review of the Bill & Melinda Gates Foundation Postsecondary Success Portfolio: Lessons from Five Years of Funding Digital Courseware (Executive Summary)
The Bill & Melinda Gates Foundationās Postsecondary Success initiative seeks to understand what is required for technology applications to produce positive student impacts at scale.
-
NMR Characterization of an Oligonucleotide Model of the MiR-21 Pre-Element
We have used NMR spectroscopy to characterize an oligonucleotide stem loop structure based on the pre-element of an oncogenic microRNA, miR-21.
-
Representing Roles in a Biology Textbook
In this paper, we consider the roles in a biology textbook, adapt a definition of roles based on upper ontologies, and relate it to the corresponding notions in linguistics and…
-
Spoken Language Recognition Based on Senone Posteriors
This paper explores in depth a recently proposed approach to spoken language recognition based on the estimated posteriors for a set of senones representing the phonetic space of one or…
-
Partially Ordered Knowledge Sharing and Fractionated Systems in the Context of Other Models for Distributed Computing
Traditional models based on strong computing primitives, such as atomic transactions, should be replaced by weaker models such as theĀ partially ordered knowledge sharing model, which we motivate in this paper…
-
Evaluation of the Human Resources Pilot: Final Report
SRI Education conducted longitudinal case studies of the three pilot districts, examining changes in policy and practices under key levers and factors shaping variation in implementation, including leadership, labor management…
-
Recent Improvements in SRIās Keyword Detection System for Noisy Audio
We present improvements to a keyword spotting (KWS) system that operates in highly adverse channel conditions with very low signal-to-noise ratio levels.Ā
-
A Deep Neural Network Speaker Veriļ¬cation System Targeting Microphone Speech
We recently proposed the use of deep neural networks (DNN) in place of Gaussian Mixture models (GMM) in the i-vector extraction process for speaker recognition.Ā