Amazon Technologies, Inc.

Lei Li

Amarsingh Buckthasingh Winston

Yongjun Wu

Hai Wei

Joshua B Barnard

Abhishek Kumar

Andrew J Watts

Stefan Christian Richter

Nicholas James Benson

Yang Yang

Brian Manuel Alvarez

Patrik Schnell

Marc Joliveau

James Marvin Freeman, Ii

Vijay Sen

Wesley Shawn Davis

Stephen A Slotnick

Deepthi Nandakumar

Gregory Scott Benjamin

Abhishek Dubey

Mairo Pedrini

Ravindra Ganti

Mushegh Malkhasyan

Aaron Michael Bromberg

Richard Judd Winograd

Bryant F Herron-Patmon

Nush Karmacharya

Peter Wei-Chih Chen

Li Tong

Andrew Ma

Avisar Ten-Ami

Patrick Joseph Lewis

Srinivas Rajagopalan

Gurpreet Singh Ahluwalia

Sachin Shah

Prateek Rameshchandra Shah

Cody Wayne Maxwell Powell

Meltem Celikel

Darryl Hudgin

Samuel James Van Pelt

Pankaj Sethi

Charles Benjamin Franklin Waggoner

Gaurav Saxena

Michael Flynn

Lars Christian Ulness

Girish Bansilal Bajaj

Srikanth Kiran Kotagiri

Joshua Danovitz

Parminder Singh

Kent Haakan Karlsson

Bernhard Wolkerstorfer

Nathaniel Stewart

Umut Utkan

Narendra S Parihar

Andrew Stuart Glass

Charles Benjamin Waggoner

Zongyi Liu

Quais Taraki

Tapani Juha Otala

Sreeram Raju Chakrovorthy

Kyle Bradley Koceski

Dor Naveh

Rakesh Tangirala

David Wayne Bourgoyne

Christopher Steven Mark Pringle

Avinash Kumar

Nicholas Lovejoy

Daniel Robert Graham

Michael Robert Starr

Techniques are described for fulfilling an utterance request for an item represented within a video rendered at a client device. In some implementations, a user account associated with the request is identified, enabling a video stream transmitted in association with the user account at the time that the request was uttered to be identified. In one technique, a timestamp associated with the request is used to identify the relevant portion of the video stream. The item represented within the portion of the video stream can be identified using various techniques and/or information such as image recognition, metadata within the video, subtitles, closed captions, and/or a database mapping between the item and a video content item transmitted in the video stream.

Utterance request of items as seen within video

Techniques are described for creating and using playback-conditions-adaptive live video encoding ladders.

Content delivery of live streams with playback-conditions-adaptive encoding

Techniques for content-adaptive video sampling for automated video quality monitoring are described. As one example, a computer-implemented method includes receiving a request to train a machine learning model on a training video file comprising at least one labeled defect, performing an encode on the training video file to generate one or more compression features for each compressed frame of the training video file, training the machine learning model to identify a proper subset of candidate defect frames of the training video file based at least in part on the one or more compression features for each compressed frame of the training video file and the at least one labeled defect, receiving an inference request for an input video file, performing an encode on the input video file to generate one or more compression features for each compressed frame of the input video file, generating, by the machine learning model, a proper subset of candidate defect frames of the input video file based at least in part on the one or more compression features for each compressed frame of the input video file, and determining a defect in the input video file based at least in part on the proper subset of candidate defect frames of the input video file.

Content-adaptive video sampling for cost-effective quality monitoring

Techniques for resolution-based manifest generation for adaptive bitrate video streaming are described. As one example, a computer-implemented method includes performing a first, convex hull optimization on a video file for a first device resolution, performing a second, convex hull optimization on the video file for a second, lower device resolution, generating a first video representation for a point on both the first, convex hull optimization and the second, convex hull optimization for the first device resolution and the second, lower device resolution, generating a second video representation for a point only on the second, convex hull optimization for the second, lower device resolution, receiving a request for a manifest for the video file from a client device at the second, lower device resolution, generating the manifest for the client device that identifies the first video representation and the second video representation, and sending the manifest to the client device.

Resolution-based manifest generator for adaptive bitrate video streaming

Techniques are described for adjusting parameter settings for bitrate selection algorithms for different segments of a population of devices streaming content. Streaming sessions are identified according to session characteristics. Within each segment of sessions, control parameter settings are sent to devices corresponding to a subset of each segment. Test parameter settings are sent to devices corresponding to another subset of each segment. If the test parameter settings result in better playback performance relative to the control parameter settings, the test parameter settings become the new control parameter settings, and new test parameter settings are generated.

Adjusting parameter settings for bitrate selection algorithms

Techniques are described for server-side fragment insertion and delivery of media content. After receiving a request to play back media content, a manifest is generated that includes fragments associated with the requested media content and fragments associated with different media content. A client device requests fragments from a media server according to the manifest, and the media server provides the correct fragment in response to the request.

Server-side fragment insertion and delivery

Methods and apparatus are described for stitching independently encoded content streams together such that they appear to be part of a single streaming session.

Stitching content streams together

Techniques are described for optimizing event-adaptive live video encoding profiles.

Content delivery of live streams with event-adaptive encoding

Methods and apparatus are described for reducing subtitle information for just-after-broadcast (JAB) content. Redundant information in subtitle entries is removed so that some client devices with limited memory can handle the single subtitle file that is delivered with JAB content.

Subtitle processing for devices with limited memory

Techniques are described for encoding information in manifest data in a way that enables identification of a version of media content. Such a capability may be used to identify dynamic content inserted into the media content for the purpose of tracking the effect of the dynamic content on user generated feedback. This capability might also be used to identify a user or device associated with a particular copy of the media content for anti-piracy purposes.

Encoding identifiers into customized manifest data

An adaptive video compression system may receive video data to be compressed, such as for delivery to a user device by a video streaming service. For example the video data may be an entire video file or a segment of a video file. The adaptive video compression system determines a suitable encoding scheme for compressing the video data. In order to determine the encoding scheme, the video data may be analyzed to extract a plurality of features interests of the video data, which may represent one or more characteristics of the video data. The features may be concatenated and collectively expressed as a feature vector. The feature vector is then used to determine a classification for the video data. Accordingly, an encoding scheme is determined for the video data based on the classification of the video data, and applied to video data to compress the video data.

Adaptive video compression

The disclosure is related to allocation of bits in a media stream. In an example, a video stream is segmented into groups of pixels. A determination of a class type is made for individual ones of the groups of pixels. The determination can be based at least in part on semantic similarity of the class type and of a scene represented in the groups of pixels. A further determination occurs for sets of classified data associated with regions of interest (ROIs) according to the determined class type. Masking data associated with the sets of classified data is provided and confidence measures associated with the sets of classified data and the ROIs are determined. Bits are then allocated for groups of pixels based on the masking data and the confidence measures. Thereafter, a bit stream with the bits can be transmitted for playback on a computing device.

Confidence-based encoding

Growing community of inventors

Kirkland, WA, United States of America

Lei Li