Amazon Technologies, Inc.

Jonathan Hedley

Vasant Manohar

Vivek Bhadauria

Gowtham Jeyabalan

Stefano Stefani

Andrea Olgiati

Wei Xia

Ranju Das

Shubham Chandra Gupta

Nitin Singhal

Warren Vincent Barkley

Meng Wang

Gaurav D Ghare

Hao Chen

Roman Goldenberg

Dylan Chandler Thomas

Joseph Patrick Tighe

Siddharth Vivek Joshi

Rakesh Madhavan Nambiar

Fedor Zhdanov

James Andrew Trenton Lipscomb

Stephen Gould

Anuj Gupta

Kunwar Yashraj Singh

Prateek Sharma

Sindhu Chejerla

Christopher Mark Paola

Christopher William Holt

Jiazhi Ou

Kriti Bharti

Jon I Turow

Jonathan Thomas Greenlee

Praveen Kumar Udayakumar

Cory Beer-Cunningham

Yi He

Mark Hawley Yang

Keith Young Johnson

Venkatesh Bagaria

Praveenkumar Udayakumar

Pranav Sachdeva

Sean R Flynn

Palak Mehta

Binglei Du

Kuang Han

Renjun Zheng

A request is received associated with reviewing content. As part of the request, one or more conditions are received and the content is analyzed to identify a first field of interest and a second field of interest. The first field of interest and the second field of interest represent fields of interest associated with the review of the content. At least one of the first field of interest or the second field of interest may not satisfy the one or more conditions and the content, or a portion thereof, may be sent for review.

Determining content to present for human review

Techniques for analyzing stored video upon a request are described. For example, a method of receiving a first application programming interface (API) request to analyze a stored video, the API request to include a location of the stored video and at least one analysis action to perform on the stored video; scheduling a job for the first API request using a global scheduler, the global scheduler to schedule, based at least in part on available bandwidth of processing components including a segmenter, a chunk processor, and a reducer, at least one job queue associated at least one of the processing components; accessing the location of the stored video to retrieve the stored video; segmenting the accessed video into chunks; processing each chunk with a chunk processor to perform the at least one analysis action, each chunk processor to utilize at least one machine learning model in performing the at least one analysis action; joining the results of the processing of each chunk to generate a final result; storing the final result; and providing the final result to a requestor in response to a second API request is described.

Per component schedulers making global scheduling decision

Objects detected in data may be filtered from an object recognition index. Data for object detection may be received. An object detection technique may be applied to the data to detect an object. If the object does not satisfy indexing criteria for the object recognition index, then the detected object may be excluded from the object recognition index.

Filtering detected objects from an object recognition index according to extracted features

The present disclosure provides for customizable content moderation using neural networks with fine-grained and dynamic image classification ontology. A content moderation system of the present disclosure may provide a plurality of image categories in which a subset of of image categories may be designated as restricted categories. The restricted categories may be chosen by a content provider or an end-user. The content moderation system may utilize a neural network to classify image data (e.g., still images, video, etc.) into one or more of the plurality of image categories, and determine that an image is a restricted image upon classifying the image into one of the restricted categories. The restricted image may by flagged, rejected, removed, or otherwise filtered upon being classified as a restricted image.

Fine-grain content moderation to restrict images

A method and system for capturing an image of a portion of an environment including an object of interest and uploading of the image to a service for further image analysis. The system captures a first image of an environment or scene using a first sensor of an image capture device. A region of interest is detected within the first image using an object detection model. A set of coordinates corresponding to the portion of the first image is identified and used to position a second sensor. The second sensor captures a second image including the targeted region of interest, wherein the second image has a higher resolution than the first image. The second image is uploaded to an object detection service for the further image analysis.

Multiple image processing and sensor targeting for object detection

Techniques are described for automatically scaling (or 'auto scaling') compute resources&#x2014;for example, virtual machine (VM) instances, containers, or standalone servers&#x2014;used to support execution of service-oriented software applications and other types of applications that may process heterogeneous workloads. The resource requirements for a software application can be approximated by measuring 'worker pool' utilization of instances of each service, where a worker pool represents a number of requests that the service can process concurrently. A scaling service can thus be configured to scale the compute instances provisioned for a service in proportion to worker pool utilization, that is, compute instances can be added as the fleet's worker pools become more &#x201c;busy,&#x201d; while compute instances can be removed when worker pools become inactive.

Automatically scaling compute resources for heterogeneous workloads

Techniques for analyzing stored video upon a request are described. For example, a method of receiving a first application programming interface (API) request to analyze a stored video, the API request to include a location of the stored video and at least one analysis action to perform on the stored video; accessing the location of the stored video to retrieve the stored video; segmenting the accessed video into chunks; processing each chunk with a chunk processor to perform the at least one analysis action, each chunk processor to utilize at least one machine learning model in performing the at least one analysis action; joining the results of the processing of each chunk to generate a final result; storing the final result; and providing the final result to a requestor in response to a second API request is described.

Analysis of video content

Approaches are described for a client (e.g., an application executing on a computing device) requiring a particular storage format to provide information describing its storage format to a service, such as a multi-tenant computing environment. The service contains data that the client desires to acquire, but in various embodiments, the data on the service is in a different storage format than the format required by the client. The service receives the information describing the storage format and processes the data accordingly, and then provides the processed data to the client in the format required by the client.

Approaches for preparing and delivering bulk data to clients

A technology is described for managing a temperature of a media device. An example method may include obtaining a current temperature of a media device configured to execute a media application and historical temperature data for the media device for a defined time period. A processing workload strategy may be calculated for the media application that causes a temperature of the media device to stay within a target temperature range for the media device using in part the target temperature range for the media device and the current temperature of the media device to determine a target temperature error, and the historical temperature data for the media device to determine a rate in change of the processing workload strategy based in part on the target temperature error that contains the temperature of the media device within the target temperature range. The media application may then be instructed to manage execution of media using the processing workload strategy.

Media device temperature management

Growing community of inventors

Seattle, WA, United States of America

Jonathan Hedley