Microsoft Technology Licensing, LLC

Amazon Technologies, Inc.

Rensselaer Polytechnic Institute

Yongjun Wu

Shyam Sadhwani

Gary Joseph Sullivan

Charles Benjamin Franklin Waggoner

Naveen Thumpudi

Lihua Zhu

Lei Li

Amarsingh Buckthasingh Winston

Hai Wei

Abhishek Kumar

Weidong Zhao

Sitaraman Ganapathy

Ravindra Ganti

Sudhakar Visweswara Prabhu

Eric Christoffersen

Mairo Pedrini

Kyle Alexander Woo

Vasanthakumar Soundararajan

Marc Joliveau

Gang Ji

Sandeep Kanumuri

Stefan Christian Richter

Matthew Richard Wozniak

Kyle Bradley Koceski

Parminder Singh

Glenn Frederick Evans

Ilya Vladimirovich Brailovskiy

Gaurav Saxena

Wenbo Zhang

Yang Yang

John F X Gaquin

Sriram Sethuraman

B Anil Kumar

Yueshi Shen

Srikanth Kiran Kotagiri

Qi Keith Wang

Wenfeng Gao

Brian Manuel Alvarez

Chih-Lung Lin

Shijun Sun

Patrik Schnell

Simon John Baker

Juan Carlos Arevalo Baeza

Brian Patrick Evans

Sridhar Sankuratri

William Chen

Yifu Zhang

Bakkama Srinath Reddy

Sean M Callahan

Daniel Dinu

Ziyad Ibrahim

Kevin A Chin

Leon Bottou

Timothy B Prins

Haoyun Wu

Firoz Dalal

Manivel Sethu

Yuechuan Li

Ahmed Aly Saad Ahmed

Naushirwan Navroze Patuck

Tarek Amara

Lokesh Amarnath Ravindranathan

Samuel John Wenker

Hany Farag

Yash Chaturvedi

Satheesh Ramalingam

Kim-Chyan Gan

Ming-Chieh Lee

Henrique Sarmento Malvar

Peisong Chen

Khawaja Salman Shams

Muhammad Raffay Hamid

Costin Hagiu

Stephen Estrop

Andrew Stuart Glass

Charles Benjamin Waggoner

Zongyi Liu

Barry Friemel

Mei-Hsuan Lu

Matthew Brinkley

Nicholas James Benson

Michael Vidyadhar Kale

Shankaranand Arunachalam

Alex Xiaoye Zhang

Xiaohan Nie

Michael Reddick Coleman

Robert A Cohen

Shir Aharon

Tzong-Jhy Wang

Florin Folta

Saswata Mandal

Mushegh Malkhasyan

Jeroen E Van Eesteren

Nikhil Sharma

Lucia Darsa

Yash Pandya

Dag Henriksson

Euan McLeod

Viriya Ratanasangpunth

Amit Santosh Jain

Systems and methods for audio and video content stitching are provided. an example method may include receiving a first video fragment and a second video fragment included within primary video content, the first video fragment and the second video fragment including one or more video frames, wherein the first video fragment is a first time duration, wherein the second video fragment is a second time duration, and wherein the first time duration and the second time duration are different. The example method may also include receiving a third video fragment associated with secondary video content. The example method may also include determining a first cue point within the primary video content, wherein the first cue point is located at a first time between a starting time of the first video fragment and a second time corresponding to a sum of the first time and a duration of the first time duration. The example method may also include adding the secondary video content to the primary video content at the first cue point. The example method may also include presenting the secondary video content at the first cue point within the primary video content.

Systems and methods for audio and video content stitching

Linear playout provides media content according to a schedule. Live events and video on demand (VOD) assets may be provided as part of linear playout. The linear playout process may be optimized to improve quality of experience for users and decrease the costs in providing such content.

Cost and efficiency optimization in channel playout

Adaptive bitrate techniques are used to select bitrates of segments to download when streaming video content. Different bitrate paths may be evaluated to optimize an objection function. Filtering bitrate paths that are unlikely to be optimal increases the computational speed, facilitating deployment.

Adaptive video streaming algorithm for optimized model predictive control

Techniques are described for training and use of machine learning models to determine objective video quality scores. Video quality scores predict the quality of video content perceived by viewers. Quality scores have various uses, including the selection of encoding profiles and determination of encoding ladders. A core model and residual model may be used to determine quality scores.

Objective video quality assessment models based on bitstream, and additional pixel domain features

Techniques for combining dynamic metadata for multiple view (multiview) video displaying are described. According to some examples, a computer-implemented method includes receiving, by a client device, a first video comprising a first set of dynamic metadata including a corresponding first color value histogram for a plurality of frames of the first video, and a second video comprising a second set of dynamic metadata including a corresponding second color value histogram for a plurality of frames of the second video; combining the first video and the second video into a combined video; generating a first combined color value histogram for a first frame of the combined video based on a first color value histogram of the first set of dynamic metadata for a first frame of the first video and a second color value histogram of the second set of dynamic metadata for a first frame of the second video, and a second different combined color value histogram for a second frame of the combined video based on a third color value histogram of the first set of dynamic metadata for a second frame of the first video and a fourth color value histogram of the second set of dynamic metadata for a second frame of the second video; performing, by a tone mapper of the client device, a tone mapping of the combined video based on the first combined color value histogram and the second different combined color value histogram to generate an output video with multiple views; and sending the output video to a display or storage.

Computer-implemented methods for combining dynamic metadata for multiple view (multiview) video displaying

Innovations for signaling state of a decoded picture buffer ('DPB') and reference picture lists (“RPLs”). In example implementations, rather than rely on internal state of a decoder to manage and update DPB and RPLs, state information about the DPB and RPLs is explicitly signaled. This permits a decoder to determine which pictures are expected to be available for reference from the signaled state information. For example, an encoder determines state information that identifies which pictures are available for use as reference pictures (optionally considering feedback information from a decoder about which pictures are available). The encoder sets syntax elements that represent the state information. In doing so, the encoder sets identifying information for a long-term reference picture (“LTRP”), where the identifying information is a value of picture order count least significant bits for the LTRB. The encoder then outputs the syntax elements as part of a bitstream.

Signaling of state information for a decoded picture buffer and reference picture lists

Techniques for a time synchronized switch across live feeds and channels in a media player application are described. According to some embodiments, a computer-implemented method includes displaying, on a client device, a first live stream of an event, that is still in progress, at a time-shifted time of the event relative to a known time of the event, receiving, from a user interface of the client device, a request to switch to a second live stream of the event, determining, by the client device, a time differential between the time-shifted time of the first live stream and the known time of the event, and displaying, on the client device, the second live stream beginning at a time that is time shifted by the time differential.

Computer-implemented methods for a time synchronized switch across live feeds and channels

Innovations in encoder-side search ranges having horizontal bias or vertical bias are described herein. For example, a video encoder determines a block vector ('BV') for a current block of a picture, performs intra prediction for the current block using the BV, and encodes the BV. The BV indicates a displacement to a region within the picture. When determining the BV, the encoder checks a constraint that the region is within a BV search range having a horizontal bias or vertical bias. The encoder can select the BV search range from among multiple available BV search ranges, e.g., depending at least in part on BV values of one or more previous blocks, which can be tracked in a histogram data structure.

Encoder-side search ranges having horizontal bias or vertical bias

Methods and apparatus are described for delivering streams of media content in ways that maintain compatibility among different streaming protocols for inserting secondary content into the streams of media content. This is accomplished by encoding media content the same for each streaming protocol but generating different output groups based on each streaming protocol.

Management of SCTE and contents in ad breaks for compatibility

Disclosed are various embodiments for seamless insertion of modified media content. In one embodiment, a modified portion of video content is received. The modified portion has a start cue point and an end cue point that are set relative to a modification to the video content to indicate respectively when the modification approximately begins and ends compared to the video content. A video coding associated with the video content is identified. The start cue point and/or the end cue point are dynamically adjusted to align the modified portion with the video content based at least in part on the video coding.

Seamless insertion of modified media content

A media processing tool adds custom data to an elementary media bitstream or media container. The custom data indicates nominal range of samples of media content, but the meaning of the custom data is not defined in the codec format or media container format. For example, the custom data indicates the nominal range is full range or limited range. For playback, a media processing tool parses the custom data and determines an indication of media content type. A rendering engine performs color conversion operations whose logic changes based at least in part on the media content type. In this way, a codec format or media container format can in effect be extended to support full nominal range media content as well as limited nominal range media content, and hence preserve full or correct color fidelity, while maintaining backward compatibility and conformance with the codec format or media container format.

Custom data indicating nominal range of samples of media content

Systems and methods described herein provide for novel boundary generation features for interleaving additional content into media content. Media content may be received which includes a video and audio portion. An unencrypted encode of the video portion may be generated. A first set of time stamps for the video portion may be generated using a computer vision algorithm. A second set of time stamps for the video portion may be generated for identifying IDR frames using a first algorithm. A third set of time stamps may be generated to serve as boundaries for interleaving additional content into the media content based on a priority algorithm that uses the first set of time stamps and the second set of time stamps. The video portion may be encoded using the third set of time stamps to determine the IDR frames for the media content.

Generating boundary points for media content

Some implementations include methods generating visualization emphasis object for players and may include receiving a video clip associated with a sporting event participated by a plurality of players using a playing field with a play object. The players in a frame of the video clip may be detected. Players who are on the playing field may be identified from the detected players. Each of the players identified to be on the playing field may be associated with a rectangular bounding box that provides an outline of each of the players. A player who has possession of the play object may be identified. A visualization emphasis object may be generated and placed on the player who has possession of the play object. The visual emphasis object may have a size proportional to height of a bounding box associated with the player having the possession of the play object.

Player spotlight

A system for utilizing media content reference point information to perform media content encoding, and supplemental content stitching and/or insertion. Media content can be encoded and packaged based on boundaries of the media content. The boundaries can be received from a third-party and/or generated via an automated process. Target boundaries can be selected based on accuracy levels associated with the received and/or generated boundaries. Supplemental content can be stitched and/or inserted into packaged media content based on audio and video content of the packaged media content being aligned.

Media content boundary-aware encoding

Techniques are described for facilitating client-side augmented reality overlay of secondary content during live events. Regions for overlaying secondary content are identified along with attributes for each region. A client device may then used the attributes to overlay secondary content in each region prior to playback.

Client side augmented reality overlay

Growing community of inventors

Bellevue, WA, United States of America

Yongjun Wu