scispace - formally typeset
Search or ask a question
Institution

Amazon.com

CompanySeattle, Washington, United States
About: Amazon.com is a company organization based out in Seattle, Washington, United States. It is known for research contribution in the topics: Service (business) & Service provider. The organization has 13363 authors who have published 17317 publications receiving 266589 citations.


Papers
More filters
Patent
30 Sep 2010
TL;DR: In this article, a customer of a virtual resource provider may specify that particular virtual resources are to be implemented with implementation resources that are dedicated to the customer, and the customer can specify the costs corresponding to active and inactive implementation resources in a dedicated pools associated with a particular customer.
Abstract: Virtual resources may be provisioned in a manner that is aware of, and respects, underlying implementation resource boundaries. A customer of the virtual resource provider may specify that particular virtual resources are to be implemented with implementation resources that are dedicated to the customer. Dedicating an implementation resource to a particular customer of a virtual resource provider may establish one or more information barriers between the particular customer and other customers of the virtual resource provider. Implementation resources may require transition procedures, including custom transition procedures, to enter and exit dedicated implementation resource pools. Costs corresponding to active and inactive implementation resources in a dedicated pools associated with a particular customer may be accounted for, and presented to, the customer in a variety of ways including explicit, adjusted per customer and adjusted per type of virtual resource and/or implementation resource.

66 citations

Proceedings ArticleDOI
16 Nov 2020
TL;DR: This work presents Distream, a distributed live video analytics system based on the smart camera-edge cluster architecture that is able to adapt to the workload dynamics to achieve low-latency, high-throughput, and scalable live video Analytics.
Abstract: Video cameras have been deployed at scale today. Driven by the breakthrough in deep learning (DL), organizations that have deployed these cameras start to use DL-based techniques for live video analytics. Although existing systems aim to optimize live video analytics from a variety of perspectives, they are agnostic to the workload dynamics in real-world deployments. In this work, we present Distream, a distributed live video analytics system based on the smart camera-edge cluster architecture, that is able to adapt to the workload dynamics to achieve low-latency, high-throughput, and scalable live video analytics. The key behind the design of Distream is to adaptively balance the workloads across smart cameras and partition the workloads between cameras and the edge cluster. In doing so, Distream is able to fully utilize the compute resources at both ends to achieve optimized system performance. We evaluated Distream with 500 hours of distributed video streams from two real-world video datasets with a testbed that consists of 24 cameras and a 4-GPU edge cluster. Our results show that Distream consistently outperforms the status quo in terms of throughput, latency, and latency service level objective (SLO) miss rate.

66 citations

Proceedings ArticleDOI
01 Jun 2021
TL;DR: Wang et al. as discussed by the authors proposed Domain Consensus Clustering (DCC), which exploits the domain consensus knowledge to discover discriminative clusters on both common samples and private ones.
Abstract: In this paper, we investigate Universal Domain Adaptation (UniDA) problem, which aims to transfer the knowledge from source to target under unaligned label space. The main challenge of UniDA lies in how to separate common classes (i.e., classes shared across domains), from private classes (i.e., classes only exist in one domain). Previous works treat the private samples in the target as one generic class but ignore their intrinsic structure. Consequently, the resulting representations are not compact enough in the latent space and can be easily confused with common samples. To better exploit the intrinsic structure of the target domain, we propose Domain Consensus Clustering (DCC), which exploits the domain consensus knowledge to discover discriminative clusters on both common samples and private ones. Specifically, we draw the domain consensus knowledge from two aspects to facilitate the clustering and the private class discovery, i.e., the semantic-level consensus, which identifies the cycle-consistent clusters as the common classes, and the sample-level consensus, which utilizes the cross-domain classification agreement to determine the number of clusters and discover the private classes. Based on DCC, we are able to separate the private classes from the common ones, and differentiate the private classes themselves. Finally, we apply a class-aware alignment technique on identified common samples to minimize the distribution shift, and a prototypical regularizer to inspire discriminative target clusters. Experiments on four benchmarks demonstrate DCC significantly outperforms previous state-of-the-arts.

66 citations

Book ChapterDOI
10 Sep 2018
TL;DR: The CLEF-2018 CheckThat! Lab on Automatic Identification and Verification of Political Claims as mentioned in this paper was the first edition of the CLEF task, which focused on predicting which potential claims in a political debate should be prioritized for fact-checking; in particular, given a debate or a political speech, the goal was to produce a ranked list of sentences based on their worthiness for fact checking.
Abstract: We present an overview of the CLEF-2018 CheckThat! Lab on Automatic Identification and Verification of Political Claims. In its starting year, the lab featured two tasks. Task 1 asked to predict which (potential) claims in a political debate should be prioritized for fact-checking; in particular, given a debate or a political speech, the goal was to produce a ranked list of its sentences based on their worthiness for fact-checking. Task 2 asked to assess whether a given check-worthy claim made by a politician in the context of a debate/speech is factually true, half-true, or false. We offered both tasks in English and in Arabic. In terms of data, for both tasks, we focused on debates from the 2016 US Presidential Campaign, as well as on some speeches during and after the campaign (we also provided translations in Arabic), and we relied on comments and factuality judgments from factcheck.org and snopes.com, which we further refined manually. A total of 30 teams registered to participate in the lab, and 9 of them actually submitted runs. The evaluation results show that the most successful approaches used various neural networks (esp. for Task 1) and evidence retrieval from the Web (esp. for Task 2). We release all datasets, the evaluation scripts, and the submissions by the participants, which should enable further research in both check-worthiness estimation and automatic claim verification.

66 citations

Proceedings ArticleDOI
01 Oct 2019
TL;DR: A new module for event sequence embedding is introduced, which is the first learning-based stereo method for an event-based camera and the only method that produces dense results on the Multi Vehicle Stereo Event Camera Dataset (MVSEC).
Abstract: Today, a frame-based camera is the sensor of choice for machine vision applications. However, these cameras, originally developed for acquisition of static images rather than for sensing of dynamic uncontrolled visual environments, suffer from high power consumption, data rate, latency and low dynamic range. An event-based image sensor addresses these drawbacks by mimicking a biological retina. Instead of measuring the intensity of every pixel in a fixed time-interval, it reports events of significant pixel intensity changes. Every such event is represented by its position, sign of change, and timestamp, accurate to the microsecond. Asynchronous event sequences require special handling, since traditional algorithms work only with synchronous, spatially gridded data. To address this problem we introduce a new module for event sequence embedding, for use in difference applications. The module builds a representation of an event sequence by firstly aggregating information locally across time, using a novel fully-connected layer for an irregularly sampled continuous domain, and then across discrete spatial domain. Based on this module, we design a deep learning-based stereo method for event-based cameras. The proposed method is the first learning-based stereo method for an event-based camera and the only method that produces dense results. We show that large performance increases on the Multi Vehicle Stereo Event Camera Dataset (MVSEC), which became the standard set for benchmarking of event-based stereo methods.

66 citations


Authors

Showing all 13498 results

NameH-indexPapersCitations
Jiawei Han1681233143427
Bernhard Schölkopf1481092149492
Christos Faloutsos12778977746
Alexander J. Smola122434110222
Rama Chellappa120103162865
William F. Laurance11847056464
Andrew McCallum11347278240
Michael J. Black11242951810
David Heckerman10948362668
Larry S. Davis10769349714
Chris M. Wood10279543076
Pietro Perona10241494870
Guido W. Imbens9735264430
W. Bruce Croft9742639918
Chunhua Shen9368137468
Network Information
Related Institutions (5)
Microsoft
86.9K papers, 4.1M citations

89% related

Google
39.8K papers, 2.1M citations

88% related

Carnegie Mellon University
104.3K papers, 5.9M citations

87% related

ETH Zurich
122.4K papers, 5.1M citations

82% related

University of Maryland, College Park
155.9K papers, 7.2M citations

82% related

Performance
Metrics
No. of papers from the Institution in previous years
YearPapers
20234
2022168
20212,015
20202,596
20192,002
20181,189