Institution
Amazon.com
Company•Seattle, 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: Computer science & Service (business). The organization has 13363 authors who have published 17317 publications receiving 266589 citations.
Topics: Computer science, Service (business), Service provider, Context (language use), Virtual machine
Papers published on a yearly basis
Papers
More filters
••
TL;DR: In this paper, an alternative unified index is proposed that assigns explicit weights to the interests of different generations. But, unlike the zero discount rate used by the Intergovernmental Panel on Climate Change (IPCC), the generationally weighted index forces policy makers to face the moral assumptions that underlie their choices related to global warming.
111 citations
••
14 Jun 2020TL;DR: A novel architecture for STR is introduced, named Selective Context ATtentional Text Recognizer (SCATTER), that utilizes a stacked block architecture with intermediate supervision during training, that paves the way to successfully train a deep BiLSTM encoder, thus improving the encoding of contextual dependencies.
Abstract: Scene Text Recognition (STR), the task of recognizing text against complex image backgrounds, is an active area of research. Current state-of-the-art (SOTA) methods still struggle to recognize text written in arbitrary shapes. In this paper, we introduce a novel architecture for STR, named Selective Context ATtentional Text Recognizer (SCATTER). SCATTER utilizes a stacked block architecture with intermediate supervision during training, that paves the way to successfully train a deep BiLSTM encoder, thus improving the encoding of contextual dependencies. Decoding is done using a two-step 1D attention mechanism. The first attention step re-weights visual features from a CNN backbone together with contextual features computed by a BiLSTM layer. The second attention step, similar to previous papers, treats the features as a sequence and attends to the intra-sequence relationships. Experiments show that the proposed approach surpasses SOTA performance on irregular text recognition benchmarks by 3.7% on average.
111 citations
••
TL;DR: An extension of the iterative closest point (ICP) algorithm that simultaneously registers multiple 3D scans by using the averaging of relative motions, resulting in a 3D registration method that is both efficient and accurate.
Abstract: In this paper, we present an extension of the iterative closest point (ICP) algorithm that simultaneously registers multiple 3D scans. While ICP fails to utilize the multiview constraints available, our method exploits the information redundancy in a set of 3D scans by using the averaging of relative motions. This averaging method utilizes the Lie group structure of motions, resulting in a 3D registration method that is both efficient and accurate. In addition, we present two variants of our approach, i.e., a method that solves for multiview 3D registration while obeying causality and a transitive correspondence variant that efficiently solves the correspondence problem across multiple scans. We present experimental results to characterize our method and explain its behavior as well as those of some other multiview registration methods in the literature. We establish the superior accuracy of our method in comparison to these multiview methods with registration results on a set of well-known real datasets of 3D scans.
111 citations
•
01 Jan 2018TL;DR: This work proposes a multi-task adaptive Bayesian linear regression model for transfer learning in BO, whose complexity is linear in the function evaluations: one Bayesianlinear regression model is associated to each black-box function optimization problem (or task), while transfer learning is achieved by coupling the models through a shared deep neural net.
Abstract: Bayesian optimization (BO) is a model-based approach for gradient-free black-box function optimization, such as hyperparameter optimization. Typically, BO relies on conventional Gaussian process (GP) regression, whose algorithmic complexity is cubic in the number of evaluations. As a result, GP-based BO cannot leverage large numbers of past function evaluations, for example, to warm-start related BO runs. We propose a multi-task adaptive Bayesian linear regression model for transfer learning in BO, whose complexity is linear in the function evaluations: one Bayesian linear regression model is associated to each black-box function optimization problem (or task), while transfer learning is achieved by coupling the models through a shared deep neural net. Experiments show that the neural net learns a representation suitable for warm-starting the black-box optimization problems and that BO runs can be accelerated when the target black-box function (e.g., validation loss) is learned together with other related signals (e.g., training loss). The proposed method was found to be at least one order of magnitude faster that methods recently published in the literature.
110 citations
••
TL;DR: Examination of county-level data suggests that deforestation in already heavily cleared areas was falling due to lack of suitable uncleared land, while little-cleared areas were experiencing rapid deforestation, and clearing rates declined in the recent frontiers.
Abstract: Controlling deforestation in Brazil's Amazon region has long been illusive despite repeated efforts of government authorities to slow the process. From 1997 to 2000, deforestation rates in Brazil's 9-state "Legal Amazon" region continually crept upward. Now, a licensing and enforcement program for clearing by large farmers and ranchers in the state of Mato Grosso appears to be having an effect. The deforestation rate in Mato Grosso was already beginning to slacken before initiation of the program in 1999, but examination of county-level data suggests that deforestation in already heavily cleared areas was falling due to lack of suitable uncleared land, while little-cleared areas were experiencing rapid deforestation. Following initiation of the program, the clearing rates declined in the recent frontiers. Areas with greater enforcement effort also appear to have experienced greater declines. Demonstration of government ability to enforce regulations and influence trends is important to domestic and international debates regarding use of avoided deforestation to mitigate global warming.
110 citations
Authors
Showing all 13498 results
Name | H-index | Papers | Citations |
---|---|---|---|
Jiawei Han | 168 | 1233 | 143427 |
Bernhard Schölkopf | 148 | 1092 | 149492 |
Christos Faloutsos | 127 | 789 | 77746 |
Alexander J. Smola | 122 | 434 | 110222 |
Rama Chellappa | 120 | 1031 | 62865 |
William F. Laurance | 118 | 470 | 56464 |
Andrew McCallum | 113 | 472 | 78240 |
Michael J. Black | 112 | 429 | 51810 |
David Heckerman | 109 | 483 | 62668 |
Larry S. Davis | 107 | 693 | 49714 |
Chris M. Wood | 102 | 795 | 43076 |
Pietro Perona | 102 | 414 | 94870 |
Guido W. Imbens | 97 | 352 | 64430 |
W. Bruce Croft | 97 | 426 | 39918 |
Chunhua Shen | 93 | 681 | 37468 |