Abstract: A neural network-based classifier system can receive a query including a media signal and, in response, provide an indication that a particular received query corresponds to a known media type or media class. The neural network-based classifier system can select and apply various models to facilitate media classification. In an example embodiment, classifying a media query includes accessing digital media data and a context parameter from a first device. A model for use with the network-based classifier system can be selected based on the context parameter. In an example embodiment, the network-based classifier system provides a media type probability index for the digital media data using the selected model and spectral features corresponding to the digital media data. In an example embodiment, the digital media data includes an audio or video signal sample.

Abstract: A client device accesses a video input stream from an intermediate device for display. The client device analyzes the video input stream to determine that the video input stream matches a template indicating a change of speed. In some example embodiments, the analysis is performed while the client device is generating a video output stream that replaces video content received from a content source via the intermediate device. Based on the video input stream matching the template, the client device modifies the video output stream to show the change of speed. For example, commercials transmitted from a national content provider to a smart TV via a set-top box may be replaced with targeted commercials. During the replacement, fast-forwarding of the commercial may be detected by matching a template with the video input stream. While the video input stream is being fast-forwarded, the smart TV fast-forwards the targeted commercial.

Abstract: Techniques of providing an interactive programming guide with a personalized lineup are disclosed. In some embodiments, a profile is accessed, and a personalized lineup is determined based on the profile. The personalized lineup may include a corresponding media content identification assigned to each one of a plurality of sequential time slots, where each media content identification identifies media content for the corresponding time slot. A first interactive programming guide may be caused to be displayed on a first media content device associated with the profile, where the first interactive programming guide includes the personalized lineup.

Abstract: Techniques of content unification are disclosed. In some example embodiments, a computer-implemented method comprises: determining clusters based a comparison of a plurality of audio content using a first matching criteria, each cluster of the plurality of clusters comprising at least two audio content from the plurality of audio content; for each cluster of the plurality of clusters, determining a representative audio content for the cluster from the at least two audio content of the cluster; loading the corresponding representative audio content of each cluster into an index; matching the query audio content to one of the representative audio contents using a first matching criteria; determining the corresponding cluster of the matched representative audio content; and identifying a match between the query audio content and at least one of the audio content of the cluster of the matched representative audio content based on a comparison using a second matching criteria.

Abstract: A computing system identifies a media stream being received by a client, based on fingerprint matching conducted with query fingerprints generated by the client at a frame rate. The computing system then causes the client to increase the frame rate, in order to facilitate establishment by the computing system of synchronous lock between true time within the media stream and client time according to a clock of the client. The computing system then uses the established synchronous lock as a basis to map a true-time point at which a content revision should be performed in the media stream to a client-time point at which the client should perform the content revision. And the computing system causes the client to perform the content revision at the determined client-time point.

Abstract: Techniques of providing motion video content along with audio content are disclosed. In some example embodiments, a computer-implemented system is configured to perform operations comprising: receiving primary audio content; determining that at least one reference audio content satisfies a predetermined similarity threshold based on a comparison of the primary audio content with the at least one reference audio content; for each one of the at least one reference audio content, identifying motion video content based on the motion video content being stored in association with the one of the at least one reference audio content and not stored in association with the primary audio content; and causing the identified motion video content to be displayed on a device concurrently with a presentation of the primary audio content on the device.

Abstract: Example methods and systems for displaying actionable elements over playing content, such as video content, are described. In some example embodiments, the methods and systems identify video content currently playing within a display environment provided by a playback device, and display an actionable element within the display environment provided by the playback device that is based on the identified video content and includes one or more user-selectable options to perform an action associated with the identified video content. Further, in some example embodiments, the methods and systems may perform an action (e.g., present supplemental content and/or information) in response to a selection of one or more of the user-selectable options.

Abstract: A computing system identifies a media stream being received by a client, based on fingerprint matching conducted with query fingerprints generated by the client at a frame rate. The computing system then causes the client to increase the frame rate, in order to facilitate establishment by the computing system of synchronous lock between true time within the media stream and client time according to an clock of the client. The computing system then uses the established synchronous lock as a basis to map a true-time point at which a content revision should be performed in the media stream to a client-time point at which the client should perform the content revision. And the computing system causes the client to perform the content revision at the determined client-time point.

Abstract: A computing system identifies multiple matching points between (i) query fingerprints representing a media stream being received by a client and (ii) reference fingerprints, each identified matching point defining a respective match between a query fingerprint timestamped with client time defined according to a clock of the client and a reference fingerprint timestamped with true time defined according to a timeline within a known media stream. Further, the computing system performs linear regression based on the timestamps of the matching points, to establish a mapping between true time and client time. The computing system then uses the mapping to determine a client-time point at which the client should perform a content revision or other action with respect to the media stream being received by the client. And the computing system causes the client to perform the content revision or other action at the determined client-time point.

Abstract: In an example implementation, a method is described. The implementation accesses a plurality of media clips including a first video clip and a second video clip, matches a first fingerprint of the first video clip with a second fingerprint of the second video clip. The implementation also matches a first event location of the first video clip with a second event location of the second video clip, determines an overlap of the first video clip with the second video clip based at least in part on the match of the first fingerprint with the second fingerprint and the match of the first event location with the second event location, merges the first and second video clips into a group of overlapping video clips based on the overlap, and generates a presentation that includes the group formed by merging the first and second video clips based on the overlap.

Abstract: A clustering machine can cluster descriptive vectors in a balanced manner. The clustering machine calculates distances between pairs of descriptive vectors and generates clusters of vectors arranged in a hierarchy. The clustering machine determines centroid vectors of the clusters, such that each cluster is represented by its corresponding centroid vector. The clustering machine calculates a sum of inter-cluster vector distances between pairs of centroid vectors, as well as a sum of intra-cluster vector distances between pairs of vectors in the clusters. The clustering machine calculates multiple scores of the hierarchy by varying a scalar and calculating a separate score for each scalar. The calculation of each score is based on the two sums previously calculated for the hierarchy. The clustering machine may select or otherwise identify a balanced subset of the hierarchy by finding an extremum in the calculated scores.

Abstract: A computing system obtains a fingerprint of video content being rendered by a video presentation device, including a first portion representing a pre-established video segment and a second portion representing a dynamically-defined video segment. While obtaining the query fingerprint, the computing system (a) detects a match between the first portion of the query fingerprint and a reference fingerprint that represents the pre-established video segment, (b) based on the detecting of the match, identifies the video content being rendered, (c) after identifying the video content being rendered, applies a trained neural network to at least the second portion of the query fingerprint, and (d) detects, based on the applying of the neural network, that rendering of the identified video content continues. And responsive to at least the detecting that rendering of the identified video content continues, the computing system then takes associated action.

Abstract: A computing system obtains a fingerprint of video content being rendered by a video presentation device, including a first portion representing a pre-established video segment and a second portion representing a dynamically-defined video segment. While obtaining the query fingerprint, the computing system (a) detects a match between the first portion of the query fingerprint and a reference fingerprint that represents the pre-established video segment, (b) based on the detecting of the match, identifies the video content being rendered, (c) after identifying the video content being rendered, applies a trained neural network to at least the second portion of the query fingerprint, and (d) detects, based on the applying of the neural network, that rendering of the identified video content continues. And responsive to at least the detecting that rendering of the identified video content continues, the computing system then takes associated action.

Abstract: Example methods and systems for displaying actionable elements over playing content, such as video content, are described. In some example embodiments, the methods and systems identify video content currently playing within a display environment provided by a playback device, and display an actionable element within the display environment provided by the playback device that is based on the identified video content and includes one or more user-selectable options to perform an action associated with the identified video content. Further, in some example embodiments, the methods and systems may perform an action (e.g., present supplemental content and/or information) in response to a selection of one or more of the user-selectable options.

Abstract: Example methods and systems for displaying actionable elements over playing content, such as video content, are described. In some example embodiments, the methods and systems identify video content currently playing within a display environment provided by a playback device, and display an actionable element within the display environment provided by the playback device that is based on the identified video content and includes one or more user-selectable options to perform an action associated with the identified video content. Further, in some example embodiments, the methods and systems may perform an action (e.g., present supplemental content and/or information) in response to a selection of one or more of the user-selectable options.

Abstract: Systems and methods are disclosed for tracking streaming of media content on a second computing device, detecting termination of the streaming of media content on the second computing device, determining when the streaming of the media content was terminated on the second computing device, and automatically resuming streaming of the media content on a first computing device, at a point where the streaming of the media content was terminated on the second computing device.

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed that involve a user profile based on clustering tiered descriptors. An example method includes grouping descriptors into a cluster of descriptors based on an association between the descriptors and each of a first item and a second item, accessing, via a user device, biometric data of a user, determining a first activity in which the user is engaged based on contextual data that correlates the cluster of descriptors with the biometric data of the user received from the user device via the network, generating a user profile based on the first activity of the user and the cluster of descriptors, and generating, in response to a second activity of the user matching the first activity associated with the cluster of descriptors within the user profile, a recommendation including a third item based on the user profile.

Abstract: Example methods and systems for inserting information into playing content are described. In some example embodiments, the methods and systems may identify a break in content playing via a playback device, select an information segment representative of information received by the playback device to present during the identified break, and insert the information segment into the content playing via the playback device upon an occurrence of the identified break.

Abstract: In an example implementation, a method is described. The implementation accesses a plurality of media clips including a first video clip and a second video clip. The implementation also matches a first fingerprint of at least a part of the first video clip with a second fingerprint of at least a part of the second video clip. The implementation also determines a temporal overlap of the first video clip with the second video clip based at least in part on the match. The implementation also, based on the temporal overlap of the first video clip with the second video clip, merges the first video clip and the second video clip into a group of overlapping video clips, and transmits, to a client computing device, data identifying the group of overlapping video clips and specifying a synchronization of the first video clip with the second video clip.

Abstract: Systems and methods are disclosed for dynamic content delivery based on vehicle navigational attributes. An example system includes at least one processor, and memory including instructions that, when executed, cause the at least one processor to determine a relevancy score for respective ones of a plurality of sporting event data items based on navigational attributes of a vehicle, determine whether the navigational attributes correspond to a driving condition, the driving condition indicative of a driving pattern of the vehicle in response to a condition external to the vehicle, and in response to determining that the navigational attributes correspond to the driving condition, present a first sporting event data item of the plurality of sporting event data items in response to a relevancy score of the first sporting event data item corresponding to the driving condition.