Abstract: A mobile device responds in real time to media content presented on a media device, such as a television. The mobile device captures temporal fragments of audio-video content on its microphone, camera, or both and generates corresponding audio-video query fingerprints. The query fingerprints are transmitted to a search server located remotely or used with a search function on the mobile device for content search and identification. Audio features are extracted and audio signal global onset detection is used for input audio frame alignment. Additional audio feature signatures are generated from local audio frame onsets, audio frame frequency domain entropy, and maximum change in the spectral coefficients. Video frames are analyzed to find a television screen in the frames, and a detected active television quadrilateral is used to generate video fingerprints to be combined with audio fingerprints for more reliable content identification.

Abstract: A method for playing a video includes: playing a first video; displaying a first plot development selection interface in response to end of playing of the first video, wherein the first plot development selection interface includes a first plot prompt message including a plurality of prompt messages, each prompt message corresponding to a plot development direction of the first video; determining a target prompt message, wherein the target prompt message includes the prompt message selected on the first plot development selection interface; and acquiring a second video based on the target prompt message; and playing the second video.

Abstract: Systems and methods for identifying, assembling, and transmitting content are described in the illustrative context of electronic program guides and program channels. Data is received over a network from a first user terminal that enables identification of the first user. Program information for a digital program is accessed. A determination is made as to how many interstitials are to be presented during a playback of the digital program. A prediction model is selected and executed to generate predictions of user responses to one or more placements of program interstitials. The user response predictions are used to determine positioning of interstitials with respect to the program. The interstitials are enabled to be displayed on the first user terminal in accordance with the determined positioning.

Abstract: Systems and methods are described herein for inserting emoticons within a media asset based on an audio portion of the media asset. Each audio portion of a media asset is associated with a respective part of speech, and an emotion corresponding to the audio portion for the media asset is determined. A corresponding emoticon is identified based on the determined emotion in the audio portion and causing to be presented at the location within the media asset.

Abstract: Systems and methods are described herein for inserting emoticons within a media asset based on an audio portion of the media asset. Each audio portion of a media asset is associated with a respective part of speech, and an emotion corresponding to the audio portion for the media asset is determined. A corresponding emoticon is identified based on the determined emotion in the audio portion and presented in the subtitles.

Abstract: At least three uses of the technology disclosed are immediately recognized. First, a video stream classifier can be trained that has multiple uses. Second, a trained video stream classifier can be applied to monitor a live network. It can be extended by the network provider to customer relations management or to controlling video bandwidth. Third, a trained video stream classifier can be used to infer bit rate switching of codecs used by video sources and content providers. Bit rate switching and resulting video quality scores can be used to balance network loads and to balance quality of experience for users, across video sources. Balancing based on bit rate switching and resulting video quality scores also can be used when resolving network contention.

Abstract: A content recording and sharing method is applied to a computing device. The method includes: obtaining a video in real time, the video capturing a physical scene for a time duration; generating supplemental contents synchronized with the video; receiving user information from a first user terminal device; determining first selected supplemental content according to the user information and a first selection rule, and sending the first selected supplemental content to the first user terminal device; determining second selected supplemental content according to a second selection rule; and sharing the video and the second selected supplemental content with one or more second user terminal devices.

Abstract: Example implementations described herein are directed to systems, methods, and computer programs for the management of live or streaming broadcasts for policy violations, which can include buffering a live stream broadcast, processing the buffered live stream broadcast with one or more processors configured with a machine learning algorithm for detecting a policy violation, and for the processing indicative of the policy violation existing in the buffered live stream broadcast, causing the buffered live stream broadcast to be modified. Such policy violations can include nudity, hate speech, copyright infringement, age inappropriate content and other violations in accordance with the desired implementation.

Abstract: In this application, methods of facilitating serving advertisements to users are described. Methods of the inventive subject matter allow for delivery of advertisement videos, both in the form of commercials and in the form of product placement, such that users can interact with one or more buttons that are included in an interactive overlay on the advertisement video. Buttons in an interactive overlay can prompt a user to provide an input to a client to bring about a desired effect, e.g., to make a purchase or to request more information. Interaction with a button does not cause an interruption in any video content that includes an interactive overlay prompting a user for input.

Abstract: Systems, computer program products, and methods are described herein for generation of data content based on learning reinforcement. The present invention is configured to receive a video file demonstrating regulatory compliance requirements; display the video file in one or more interactive application environments stored thereon; initiate a reinforcement learning algorithm on the video file; initiate an optimization policy generation engine on the user inputs to generate an optimization policy, wherein the optimization policy generation engine is configured to encode the one or more user inputs into shaping rewards; initiate an implementation of the optimization policy on the video file to generate a modified video file based on at least the optimization policy; initiate a validation engine on the modified video file to validate one or more changes implemented on the video file; and initiate a deployment of the modified video file to the one or more users.

Abstract: Systems and methods are provided herein for performing an action based on a feature in a media asset. In many media assets, specific features appear at portions of a program that users find interesting. These features can be compared with a database of stored objects that commonly appear in media assets to determine the object corresponding to the feature. The context of the object in the media asset then may be determined so that an appropriate action is selected for the system to take.

Abstract: An example client device for retrieving media data includes a memory configured to store media data; and one or more processors implemented in circuitry and configured to execute a plurality of video decoders; determine a complexity value for the media data including a plurality of encoded video streams, the complexity value representing complexity of an aggregation of the encoded video streams; retrieve the media data including the encoded video streams in response to determining that the client device is capable of decoding the encoded video streams using the complexity value; and distribute the encoded video streams and synchronization information to corresponding video decoders of the plurality of video decoders to cause the video decoders to decode the corresponding video streams and to output decoded video data from the video streams in a synchronized fashion.

Abstract: Correlating information associated with playback of video segments is disclosed. Information associated with playback of a first video segment is obtained. Information associated with playback of a second video segment is obtained. The information associated with playback of the first video segment is correlated with the information associated with playback of the second video segment based at least in part on at least one of a client application identifier, a video session identifier, and a set of timestamps. Output is provided based at least in part on the correlating.

Abstract: A system and method for making reservations in a hospitality establishment are disclosed. In one embodiment of the system, a database includes multiple the media source files relative to guest room spaces within a room. A server which handles reservations renders a map view of the hospitality establishment based on obtained map data. The map view includes a graphical representation of the room as well as other rooms. In response to the room being selected, the graphical representation of the selected room is annotated with room reservation data and at least one of the media source files of the selected room. The server may execute a reservation for the selected room.

Abstract: The present invention discloses techniques for generating and presenting subtitles. The disclosed techniques comprise extracting target audio information from a video; converting the target audio information to first text information, wherein the target audio information and the first text information are in a first language; translating the first text information to at least one second text information, wherein the at least one second text information is in at least one second language; generating a first subtitle based on the first text information; generating at least one second subtitle based on the at least one second text information; obtaining a first target subtitle and at least one second target subtitle by implementing a sensitive word processing to the first subtitle and the at least one second subtitle, respectively; and presenting at least one of the first target subtitle or the at least one second target subtitle in response to user input.

Abstract: A video generation system is configured to provide streaming video as a cloud processed service to viewers over a computing network. In response to a request from a viewer, a video source is configured to provide video and an identifier source is configured to provide an identifier for inclusion in the video. A video encoder is configured to convert the video from a first format to a second format, apply the identifier to the video, and otherwise encode the video in real-time while streaming the encoded video to the viewer. The identifier may be stored in association with the account information of the viewer and used for identifying the viewer a source of an unauthorized video copy.

Abstract: An automated method is provided for identifying candidate locations in video content for inserting advertisement (ad) breaks. Each candidate location is a different offset time from the beginning of the video content. Different distinct characteristics of the video content are identified at offset times. Certain characteristics are desirable and certain other characteristics are not desirable. Candidate locations are identified which have the most desirable characteristics at particular offset times, but which do not have any of the undesirable characteristics at any of the offset times.

Abstract: An information processing apparatus includes: a storage that stores templates defining a display form of a ticker; a selection unit that selects a template stored in the storage; a material data acquisition unit that acquires material data to be displayed on the ticker; a production unit that produces ticker data by applying the template selected by the selection unit to the material data acquired by the material data acquisition unit; and a provision unit that provides provision data including the ticker data produced by the production unit.

Abstract: A processing load on a reception side when subtitle graphics data is superimposed on video data is alleviated. A video stream including video data is generated. A subtitle stream including bitmap data is generated, the bitmap data being obtained by converting subtitle graphics data. A container having a predetermined format containing the video stream and the subtitle stream is transmitted. The subtitle stream includes a bitmap conversion table containing conversion information of a color gamut and/or a luminance. On the reception side, subtitle graphics data having characteristics matched with those of target video data of a superimposition destination can be easily obtained by just converting the bitmap data to the subtitle graphics data by using the bitmap conversion table.

Abstract: A computer-implemented method for providing cinematic content to a user via a computer-controlled media player includes accessing by a processor a content package including a targeted emotional arc and a collection of digital objects each associated with codes indicating an emotional profile of the each digital object, playing digital objects selected from the content package thereby outputting an audio-video signal for display by an output device; receiving sensor data from at least one sensor positioned to sense a biometric feature of a user watching the output device; determining a value of one or more emotional state variables, based on the sensor data; and selecting the digital objects for the playing based on the one or more emotional state variables, a recent value of the targeted emotional arc, and the one or more codes indicating an emotional profile. An apparatus is configured to perform the method using hardware, firmware, and/or software.