AT&T Intellectual Property I, LP

Wemovie Technologies

At&t Mobility II LLC

Sbc Knowledge Ventures, L.p.

Xidong Wu

Jin Wang

Zhengye Liu

Xiubo Wu

Baofeng Jiang

Mark H Brady

Chen-Yui Yang

David H Lu

Raghvendra Savoor

Paritosh Bajpay

Bo Han

Mario Kosseifi

Anthony Mark Srdar

John Porter Van Slyke

Balaji R Puli

Stephen Albert Sposato

Jim Tidashi Otsuka

Kapil Vishwas Shrikhande

Stuart Blackburn

Jerold Osato

Gabriel Bourge

Giuseppe De Rosa

Yali Liu

Sun-Uk Park

Joseph Thomas

Ronald Kiefer

Ganesh Krishnamurthi

Xiaojun Tang

Kaiyan Chen

Richard J Mountford

Amit Rele

Donggen Zhang

Xiaochuan Yi

Haibo Zhang

Feiling Jia

Raghbendra G Savoor

Zhi Li

Monowar Hossain

Richard Dennis Hart

Thiru Ilango

Andre Fuetsch

Mengfeng Tsai

Keith Cambron

Ganesh Krishnamuthi

Jim Tadashi Otsuka

Methods, apparatus and systems related to post-production stage of a multimedia content are described. In one example aspect, a method for performing automated post-production editing includes receiving one or more machine-readable scripts corresponding to one or more scenes of a storyline. The one or more machine-readable scripts include information about multimodal data and editing instructions for each of the one or more scenes. The method also includes identifying, based on the multimodal data for each of the one or more scenes, at least one change in an audio or video feature in the multiple streams of multimedia content corresponding to the one or more scenes, editing the multiple streams of multimedia content based on the editing instructions and selectively based on the identified change, and generating a final stream of multimedia content based on the edited multiple streams.

Fully automated post-production editing for movies, tv shows and multimedia contents

Methods, apparatus and systems related to packaging a multimedia content for distribution are described. In one example aspect, a method includes receiving media files comprising video or audio data captured at a production stage and determining a hierarchical structure of the multimedia content based on production stage information of the multimedia content. The hierarchical structure indicates that the multimedia content comprises multiple scenes, each of which comprises multiple shots produced with corresponding devices and cast. The method also includes identifying characteristics associated with the individual scenes based on the production stage information, generating multiple copies of the multimedia content at different compression levels, and dividing each of the multiple copies of the multimedia content into segments based on the hierarchical structure. The compression levels and a length of a segment are adaptively adjusted based on the characteristics associated with the individual scenes.

Content structure aware multimedia streaming service for movies, TV shows and multimedia contents

Methods, apparatus and systems related to automated production of multimedia contents are described. In one example aspect, an automated production system includes a directing server configured to store production-stage information in a machine-readable script and manage production of a multimedia content according to the script. The system also includes a device management server configured to coordinate one or more shooting locations for the production of the multimedia content. The device management server is configured to receive a portion of the production-stage information extracted from the script based on its location. The system further includes end devices connected to the device management server. The device management server is configured to track activities of the end devices and to provide status of the end devices at a production time to the directing server to enable the directing server to dynamically update the script for subsequent shooting activities at the production time.

Automated coordination in multimedia content production

Methods, apparatus and systems related to packaging a multimedia content for distribution are described. In one example aspect, a method for performing post-production editing includes receiving one or more footages of an event from at least one user. The method includes constructing, based on information about the event, a script to indicate a structure of multiple temporal units of the one or more footages, and extracting semantic meaning from the one or more footages based on a multimodal analysis comprising at least an audio analysis and a video analysis. The method also includes adding editing instructions to the script based on the structure of the multiple temporal units and the semantic meaning extracted from the one or more footages and performing editing operations based on the editing instructions to generate an edited multimedia content based on the one or more footages.

Automated post-production editing for user-generated multimedia contents

Methods, apparatus and systems related to automated evaluation of acting performance are disclosed. In one example aspect, a system for an automated evaluation of performance activities includes a user interface configured to allow a user to create a customized automated evaluation service. The user can select a subset of machine learning engines from one or more available machine learning engines to create such service. The user interface is further configured to receive a set of input data of a performance performed by a performer. The system includes the one or more available machine learning engines each configured to generate a sub-score in a specific area using the set of input data received from the user interface. The system also includes an aggregator configured to produce an output indicating a quality of the performance.

Automated evaluation of acting performance using cloud services

Methods, apparatus and systems related to pre-production stage of a movie, a TV show or a multimedia content are described. In one example aspect, a pre-production system for producing a multimedia digital content including a movie includes a user interface operable to receive information about a storyline, cameras, cast, and other assets for the movie from a user, a processor, and a memory including processor executable code. The processor executable code upon execution by the processor configures the processor to determine one or more scenes based on the storyline, generate one or more machine-readable scripts corresponding to the one or more scenes, and automatically update the one or more machine-readable scripts to satisfy one or more constraints for producing the multimedia digital content.

Pre-production systems for making movies, tv shows and multimedia contents

Methods, apparatus and systems related to production of a movie, a TV show or a multimedia content are described. In one example aspect, a system for producing a movie includes a pre-production subsystem configured to receive information about a storyline, cameras, cast, and other assets for the movie from a user. The pre-production subsystem is configured to generate one or more machine-readable scripts corresponding to one or more scenes. The system includes a production subsystem configured to receive the scripts from the pre-production system to determine constraints among the scenes. The production subsystem is further configured to determine actions for the cameras and the cast for obtaining footages according to the storyline. The system includes a device management subsystem configured to control the cameras and the cast based on the determined actions by the production system and a post-production editing system configured to receive the footages from the production subsystem for performing video and audio editing.

Systems and methods for producing digital multimedia contents including movies and tv shows

Methods, apparatus and systems related to production of a movie, a TV show or a multimedia content are described. In one example aspect, a system for producing a multimedia digital content includes a pre-production subsystem configured to receive information about a storyline, cameras, cast, and other assets for the content from a user. The pre-production subsystem is configured to generate one or more machine-readable scripts that include information about one or more advertisements. The system includes a production subsystem configured to receive the one or more machine-readable scripts from the pre-production system to obtain a footage according to the storyline. The production subsystem is further configured to embed one or markers corresponding to the one or more advertisements in the footage. The system also includes a post-production editing subsystem configured to detect the one or more markers embedded in the footage and replace each of the one or more markers with a corresponding advertising target.

Adaptive marketing in cloud-based content production

Example methods and systems are disclosed to facilitate detection and identification of devices connected to a cellular network and that are causing interference to the cellular network. An example method may include receiving, by a serving base station of the device, a first set of information associated with data communications of a device utilizing a cellular network. The method may further include determining the device is an interfering device based on the first set of information associated with the data communication substantially corresponding with an interfering device profile, and in response tracking the device. During the tracking of the device, a second set of information associated with the data communications from the device may be obtained, and an interfering device type of the device may be determined based on the second set of information. An action may be performed on the interfering device based on its interfering device type.

Interfering device identification

Aspects of the subject disclosure may include, for example, a method comprising: obtaining media content, such as video; receiving a request from a user and/or user equipment (UE) to view the media content; identifying a predicted field of view of the user; sending the predicted field of view to the equipment of the user at a normal priority; monitoring a line of sight (or actual field of view) of the user; determining a field of view error as a difference between the line of sight and the predicted field of view; and sending the field of view error to the equipment of the user at a higher priority. Other embodiments are disclosed.

Active network support on adaptive virtual reality video transmission

Devices, computer-readable media, and methods for selecting a type of packet loss protection for a network-based communication based upon a latency estimate are disclosed. For example, a processing system including at least one processor may obtain a latency estimate for a network-based communication, determine whether the latency estimate exceeds a latency threshold for selecting a type of packet loss protection, and select, the type of packet loss protection for the network-based communication from among a first type of packet loss protection and a second type of packet loss protection based upon the determining. When the latency estimate is determined to not exceed the latency threshold, the first type of packet loss protection is selected. When the latency estimate is determined to exceed the latency threshold, the second type of packet loss protection is selected.

Optimizing delay-sensitive network-based communications with latency guidance

Aspects of the subject disclosure may include, for example, a machine-readable storage medium, including executable instructions that, when executed by a processing system including a processor, facilitate performance of operations that include assuming control of a video content transfer between a video server and a video client for HTTP traffic responsive to determining the HTTP traffic is for video content, generating a video transfer rate selection and a video transfer resolution selection for a requested video chunk of a time slot of the video content, generating an optimized manifest file for the requested video chunk, and publishing the optimized manifest file to the video client, wherein the video client request the requested video chunk from the video server based on the optimized manifest. Other embodiments are disclosed.

Video optimization proxy system and method

Growing community of inventors

San Ramon, CA, United States of America

Xidong Wu