Customer-obsessed science
![Alexa woman with Echo Buds in ear.jpg](https://webcf.waybackmachine.org/web/20211215154326im_/https://assets.amazon.science/dims4/default/57334fd/2147483647/strip/true/crop/1383x1200+36+0/resize/400x347!/quality/90/?url=http%3A%2F%2Famazon-topics-brightspot.s3.amazonaws.com%2Fscience%2Fe1%2F97%2F977105544cee92c9cea14b00f85a%2Falexa-woman-with-echo-buds-in-ear.jpg)
![Fulfillment Center OAK4 in Tracy, CA](https://webcf.waybackmachine.org/web/20211215154326im_/https://assets.amazon.science/dims4/default/ce44a4e/2147483647/strip/true/crop/1254x1091+191+0/resize/200x174!/quality/90/?url=http%3A%2F%2Famazon-topics-brightspot.s3.amazonaws.com%2Fscience%2Fc4%2F27%2F5a870d8546fb978bd3b36d0e57ef%2F20161019fulfillmentcenteroak4-09.jpg)
-
December 14, 2021Two NeurIPS papers examine the assignment of the same label to multiple categories, fast training of Transformer-based models.
-
December 07, 2021Synthetic data produced by perturbing test inputs identify error classes and provide additional data for retraining.
-
December 03, 2021Learn how you can help the university teams competing to develop agents that will assist customers with completing tasks requiring multiple steps.
-
-
December 13 - 17, 2021
-
January 4 - 8, 2022
-
-
December 06, 2021Scientists are working to address assortment optimization and inventory planning challenges for fashion products.
-
December 02, 2021Amazon Science hosts a conversation with Amazon Scholars Michael I. Jordan and Michael Kearns and Amazon distinguished scientist Bernhard Schölkopf.
-
November 24, 2021The 2001 paper was awarded for “foundational work initiating a long and fruitful line of work in approximately revenue-optimal auction design in prior free settings”.
-
November 17, 2021The paper by Özer and his co-authors examines the role of earmarking and transparency on donors and their donations.
![quantum panel promo](https://webcf.waybackmachine.org/web/20211215154326/https://assets.amazon.science/dims4/default/d32ed15/2147483647/strip/true/crop/1429x810+11+0/resize/1200x680!/quality/90/?url=http%3A%2F%2Famazon-topics-brightspot.s3.amazonaws.com%2Fscience%2F05%2F1d%2Ffbf0ed0c4f389aea1220383cc65d%2Fquantum-promo.jpg)
The challenge and promise of quantum computing
Join seven Amazon scientists, Scholars and Visiting Academics as they discuss the current and future challenges of quantum computing.
-
2022Learning to identify similar products in the e-commerce domain has widespread applications such as ensuring consistent grouping of the products in the catalog, avoiding duplicates in the search results, etc. Here, we address the problem of learning product similarity for highly challenging real-world data from the Amazon catalog. We define it as a metric learning problem, where similar products are projected
-
2022Recent advances in deep learning and computer vision have set new state of the art in logo recognition [2, 9, 36]. Logo recognition has mostly been approached as a closed-set object recognition problem and more recently as an open-set retrieval problem. Current approaches suffer from distinguishing visually similar logos, especially in open-set retrieval for very large-scale applications with thousands
-
2022In the world of action recognition research, one primary focus has been on how to construct and train networks to model the spatial-temporal volume of an input video. These methods typically uniformly sample a segment of an input clip (along the temporal dimension). However, not all parts of a video are equally important to determine the action in the clip. In this work, we focus instead on learning where
-
2022Temporal action segmentation is a task to classify each frame in the video with an action label. However, it is quite expensive to annotate every frame in a large corpus of videos to construct a comprehensive supervised training dataset. Thus in this work we propose an unsupervised method, namely SSCAP, that operates on a corpus of unlabeled videos and predicts a likely set of temporal segments across the
-
4th Symposium on Advances in Approximate Bayesian Inference2022Bayesian inference is intractable for most practical problems and requires approximation schemes with several trade-offs. Variational inference provides one of such approximations which, while powerful, has thus far seen limited use in high-dimensional applications due to its complexity and computational cost. This paper introduces a scalable, theoretically grounded, and simple-to-implement algorithm for
-
December 13, 2021Amazon Research Award recipient Éva Tardos studies complex theoretical questions that have far-ranging practical consequences.
-
December 09, 2021Gari Clifford, the chair of the Department of Biomedical Informatics at Emory University and an Amazon Research Award recipient, wants to transform healthcare.
-
December 08, 2021With the support of an Amazon Research Award, Papoian’s team is deciphering the dynamics of intrinsically disordered proteins.
Working at Amazon
View allMeet the people driving the innovation essential to being the world’s most customer-centric company.
View all
-
November 15, 2021The computer scientist recently finished her second internship at Amazon, where she worked on a new way to estimate the human expression on faces in images.
-
November 10, 2021Being able to understand and relate to the needs of working scientists is key to her success.
-
October 12, 2021Today she's helping Amazon to better formulate how to more efficiently transport packages through the middle mile of its complex delivery network.