Abstract: A method for targeted content insertion in real-time streaming. The method leverages the different ordered signals available on a multi-step process that clients follow when subscribing to a real-time media (video and/or audio) stream including selecting a region, connecting to a control channel, and subscribing to a stream to guide a multi-stage process of content selection, transcoding, and insertion in a real-time media stream. A system is also specified for implementing the described method on a real-time streaming architecture.

Abstract: A method and system for auto-curating a media are provided. Media content is received over the network interface. A set of markers is identified for the media content, each marker corresponding to one of a plurality of visible and audible cues in the media content. Segments in the media content are identified based on the identified set of markers. An excitement score is computed for each segment based on the identified markers that fall within the segment. A highlight clip is generated by identifying segments having excitement scores greater than a threshold.

Abstract: Example methods, apparatus, systems, and articles of manufacture are disclosed to estimate population reach for different unions based on marginal ratings. An example method includes performing first parallel computations to determine first multipliers corresponding to a total number of panelists exposed to media at (a) a first margin of time, (b) a second margin of time, and (c) a union corresponding to the first and second margins of time, keeping a subset of the first multipliers corresponding to unknown census data; performing second parallel computation to determine second multipliers corresponding to a total audience exposed to the media at the first margin of time and the second margin of time, the second parallel computations to be performed by solving second equations corresponding to a tree association; and determining an estimate for a population reach of the union based on the second multipliers.

Abstract: Techniques are described for expanding and/or improving the Advanced Television Systems Committee (ATSC) 3.0 television protocol in robustly delivering the next generation broadcast television services. A receiver, to automatically switch from presenting a service on a first frequency to a second frequency such as when a mobile receiver is moving through a boundary region between two broadcasters, can temporarily use a satellite link or 5G wireless telephony or other over the top (OTT) source to acquire a service until an OTA link satisfies quality requirements.

Abstract: Systems and methods include machine learning models operating at different frequencies. An example method includes obtaining images at a threshold frequency from one or more image sensors positioned about a vehicle. Location information associated with objects classified in the images is determined based on the images. The images are analyzed via a first machine learning model at the threshold frequency. For a subset of the images, the first machine learning model uses output information from a second machine learning model, the second machine learning model being performed at less than the threshold frequency.

Abstract: Systems and methods for modifying audio events in video content that correspond to one or more defined audio event types. A request is received to modify audio events in video corresponding to an audio event type. Video content to be presented on a display device is obtained that includes visual and audio content. An occurrence of a defined audio event corresponding to a defined audio event type is identified in the audio content. The defined audio event is modified according to a modification operation to generate modified audio content. The modified audio content is associated with a segment of the visual content that corresponds to the occurrence of the defined audio event. The modified audio content is provided in association with the segment of visual content for display on the display device.

Abstract: A media playout system receives a broadcast log transmitted from a media scheduling system. The broadcast log includes a restricted show, and the media playout system makes a first determination a blackout period assigned to the restricted show. The blackout period indicates a period of time associated with the restricted show during which at least one media item is prohibited from being scheduled. The media player also determines that the broadcast log indicates that the at least one media item has been improperly scheduled during the blackout period. In response to determining that the at least one media item has been improperly scheduled during the blackout period, the media playout system transmits, to the media scheduling system, a message requesting a replacement media item to replace the at least one media item that has been improperly scheduled during the blackout period.

Abstract: Aspects of the present disclosure involve a system comprising a computer-readable storage medium storing a program and method for inserting ads into a video. The program and method provide for receiving a request to play a video, the video comprising plural shots separated by breakpoints, each shot of the plural shots corresponding to a contiguous sequence of video frames that is free of cuts or transitions; initiating, in response to receiving the request, playback of the video from a selected shot of the plural shots; receiving indication of an ad to present at a breakpoint following the selected shot; determining, in response to receiving the indication, that a first threshold amount of time has passed since initiating the playback of the video; and inserting, based on the determining, the ad at the breakpoint following the selected shot.

Abstract: A method and system for controlling whether to have a content-presentation device dynamically replace a modifiable content segment, such as a replaceable ad, that is upcoming on a channel being received by the content-presentation device. An example method includes a computing system determining, based on objectionable-content data established from user input and/or channel-changing history, whether the modifiable content segment is objectionable as to the content-presentation device. And the example method then includes, based at least on the determination of whether the determined modifiable content segment is objectionable as to the content-presentation device, the computing system controlling whether to have the content-presentation device dynamically replace the modifiable content segment with a replacement content segment.

Abstract: Methods, apparatus, systems and articles of manufacture to determine media exposure of a panelist are disclosed. An example apparatus include memory; computer readable instructions; and processor circuitry to execute the computer readable instructions to: determine an anonymized identifier from media monitoring data corresponding to a personal people meter of a panelist; filter anonymized census data from a plurality of media devices based on the anonymized identifier; when second media data different than first media data is included in the media monitoring data during a same time duration, tag the time duration as corresponding to multiple media exposure; and credit exposure to media for the panelist based on the tag.

Abstract: A system, apparatus and method for synchronizing distributed adaptive streaming transcoders or packagers includes a plurality of distributed transcoders having one or more processors configured to perform the functions of identifying the output track timescale, identifying from an input signal a frame time information and optionally adjusting it for the output track timescale, calculating the frame time information of the frame relative to a time anchor by adjusting it with a synchronization time stamp, identifying a fixed segment duration by reading it from a memory, computing an earliest presentation time of a next media segment as an integer multiple of the fixed segment duration times the output track timescale, generating the next media segment with the fixed segment duration and the earliest presentation time of the next media segment, and transmitting the next media segment using an HTTP Request or a receiver.

Abstract: Storage and delivery distinct media segmentation is performed by receiving a request from a network device for a media asset, retrieving a plurality of first packets from an object storage, each first packet of the plurality of first packets including a segment of the media asset of a first length, preparing, as the plurality of first packets are retrieved from the object storage, a plurality of second packets, each second packet of the plurality of second packets including a segment of the media asset of a second length, the second length being shorter than the first length, and transmitting, as the plurality of second packets are prepared, the plurality of second packets to the network device.

Abstract: An object model for a real-world object is constructed using a parameter-based object generator, where the parameters for the object model are determined using sensor data such as photographic images, radar images, or LIDAR images obtained from the real-world object. Conversion of the sensor data to appropriate object parameters is accomplished using a machine learning system. The machine learning system is calibrated by generating a plurality of object parameters, generating a corresponding plurality of learning objects from the plurality of object parameters, generating a plurality of simulated sensor return data for the learning objects, and then providing the simulated sensor return data and object parameters to the machine learning system.

Abstract: In various embodiments, a function build application compiles source code to generate an executable version of a function that has a first function signature. The function build application then replaces a first data type of a first parameter included in the first function signature with a second data type to generate a second function signature for a client stub function. Subsequently, the function build application generates a remote procedure call (RPC) client that includes the client stub function. Notably, the RPC client causes the function to execute when the client stub function is invoked. Advantageously, unlike conventional techniques that require manual generation of strongly typed functions, the function build application automatically customizes the RPC client for the function.

Abstract: Detection of whether a video is a fake video derived from an original video and altered is undertaken using a block chain that either forbids adding to the block chain copies of original videos that have been altered or indicating in the block chain that an altered video has been altered. Image fingerprinting techniques are described for determining whether video sought to be added to block chain has been altered.

Abstract: A multimedia content selection system includes at least one processor executing instructions for performing operations. The operations include receiving a playback request from a playback unit, including a content identifier, providing, to the playback unit, a manifest with at least a set of content segment identifiers based on the content identifier, each content segment identifier identifying a content segment associated with a content stream, receiving a content stream request comprising one of the content segment identifiers, and selecting a segment for playback from the content segment associated with the received content segment identifier, determined using a set of content selection rules.

Abstract: A system for providing audience estimation for digital media display sessions displayed on a mobile vehicle, including storage media, a processing system, an interface system including a communications interface, one or more neural networks, and program instructions that the processing system to receive object sensor data, apply an entity classifier thereto to determine a type of each unique audience entity, determine a presence duration of the entity during the digital media display session, and transmit each unique audience entity to an online dashboard.

Abstract: A descriptor generation unit 81 uses a first template prepared in advance to generate a feature descriptor, which generates a feature that may affect a prediction target from a first table including a variable of the prediction target and a second table. A feature generation unit 82 generates the feature by applying the feature descriptor to the first and second tables. A feature explanation generation unit 83 generates a feature explanation about the feature descriptor or the feature on the basis of a second template. An accepting unit 84 accepts values to be assigned to the first and second templates. The descriptor generation unit 81 generates the feature descriptor by assigning the accepted values to the first template, and the feature explanation generation unit 83 generates the feature explanation by assigning the values assigned to the first template to the second template.

Abstract: While an assistant-enabled device is playing back media content, a method includes receiving a contextual signal from an environment of the assistant-enabled device and executing an event recognition routine to determine whether the received contextual signal is indicative of an event that conflicts with the playback of the media content from the assistant-enabled device. When the event recognition routine determines that the received contextual signal is indicative of the event that conflicts with the playback of the media content, the method also includes adjusting content playback settings of the assistant-enabled device.

Abstract: The present application discloses techniques for playback of live broadcast content. The techniques comprise receiving a request of playing live broadcast content from a client computing device, wherein the request comprises information indicating a first address associated with the live broadcast content, and the request further comprises a playback time parameter indicating a playback time length; generating a second address based on a current system time parameter, the first address, and the playback time parameter; obtaining live broadcast content based on the second address and transmitting the live broadcast content to the client computing device.