Abstract: A computer-implemented method of using video viewer interaction data as input to a measurement engine which then calculates: demographic level and aggregate level (a) household reach for advertisements and video content based on user defined reach periods, (b) One-minute, Thirty-minute, and Sixty-minute channel viewing metrics, and (c) One-minute, Thirty-minute, and Sixty-minute aggregate viewing metrics, all based on second-by-second household level viewing activity. Also shows creation of Commercial Schedule Cumulative Audience, Impressions for Reach Periods, Demographic Group Impressions, Average Audience, Average Audience Share, Average Rating, Households Using Television, and Households Using Television Percent using household level data. Works with IP and linear video delivery. Together these metrics provide detailed information on customer viewing behavior which can be used to drive business decisions for service providers, advertisers, and content producers.

Abstract: Concepts and technologies disclosed herein are directed to image classification attack mitigation. According to one aspect of the concepts and technologies disclosed herein, a system can obtain an original image and reduce a resolution of the original image to create a reduced resolution image. The system can classify the reduced resolution image and output a first classification. The system also can classify the original image via deep learning image classification and output a second classification. The system can compare the first classification and the second classification. In response to determining that the first classification and the second classification match, the system can output the second classification of the original image. In response to determining that the first classification and the second classification do not match, the system can output the first classification of the original image.

Abstract: Systems and methods are provided herein for identifying a playlist of highlights to use for refreshing a user on a plot related to a media asset the user has requested to access based on how long it has been since the user last saw related programming. The media guidance application may receive a request from a user to access a media asset and may determine whether the user previously consumed a related media asset to the media asset. The media guidance application may determine whether a period of time between receiving the request and a time when the user previously consumed the related media asset exceeds a threshold period of time. If the period of time does not exceed the threshold, the media guidance application may play back a predefined playlist of highlights, and if it exceeds the threshold, the media guidance application may play back a customized playlist of highlights.

Abstract: Example methods, apparatus, systems and articles of manufacture to implement calibration of convenience panel data to reduce behavioral bias are disclosed. Disclosed example apparatus include a distribution estimator to determine a first behavioral distribution for first convenience panel data associated with a first market and a measurement period, determine a second behavioral distribution for second convenience panel data associated with a second market and the measurement period, and determine a third behavioral distribution for probabilistic panel data associated with the second market and the measurement period.

Abstract: The present disclosure relates to systems and methods for group-watching video streams. In one aspect the disclosed systems and methods may generate a multi-panel display of the viewers during viewing of the video streams. In another aspect, the systems and methods may capture and create one or more digital asset from viewer-generated content, such as a physical reaction, captured during the to the video stream. The system may generate the digital assets for subsequent use on social media.

Abstract: A media rendering device and method for generation of a simplified user interface are provided. The media rendering device determines a user profile of a user of the media rendering device. The media rendering device includes a plurality of user interface modes including a specific user interface mode associated with a plurality of user interface elements. The media rendering device determines a first user interface mode based on the user profile. The first user interface mode may be associated with a first subset of user interface elements of the plurality of user interface elements. The media rendering device generates a graphical user interface (GUI) based on the first subset of user interface elements. The media rendering device controls a display device to display the generated GUI.

Abstract: The present disclosure provides a method and Internet of Things system for controlling a public landscape live broadcast in a smart city. The method includes: obtaining a landscape image; transmitting the landscape image to a user platform; determining a general user will through the user platform; the user will including an adjustment advice for the landscape image; determining camera parameters according to the general user will; transmitting the camera parameters to a camera device, which is configured to collect the landscape image; and obtaining a new landscape image according to camera parameters. The IoT system includes the user platform, the service platform, the management platform, the sensing network platform, and an object platform. The method may be implemented by a device for controlling the public landscape live broadcast in a smart city. The method may be operated after reading a computer instruction stored in the computer-readable storage medium.

Abstract: A system and method for searching and displaying multimedia search results is disclosed herein. An embodiment operates by determining that an interface including one or more previously saved searches is displayed, each of the previously saved searches corresponding to a set of one or more search terms. An updated plurality of search results is received for each of the previously saved searches from a remote server. A grouping of the plurality of search results for each of a plurality of different search terms is displayed across a plurality of individual time periods.

Abstract: In some embodiments, a method inputs a sequence of historical behaviors for a plurality of instances of content into a prediction network to generate a sequence of values that model the sequence of historical behaviors. A restriction on an operation performed by the prediction network is based on a characteristic of an viewing behavior. A sequence of attention scores is generated based on a similarity of a current behavior for a first instance of content to respective instances of historical behaviors in the sequence of historical behaviors. The method adjusts respective values based on corresponding attention scores to generate an adjusted sequence of values. The adjusted sequence of features are sampled to generate an output from the prediction network that models the sequence of historical behaviors based on the current behavior. The output for determining a prediction if the current behavior is indicative of the viewing behavior.

Abstract: Disclosed is a display apparatus comprising: a display; a user input unit; and a processor configured to identify a user's viewing time based on a user's viewing history, create a list of content to be provided within the identified viewing time based on the viewing history and display the created content list on the display, and select at least one piece of content in the content list for viewing schedule based on a user input through the user input unit.

Abstract: Systems and methods are described herein for providing content item recommendations based on a video. Using feature vectors corresponding to at least one frame of a video (e.g., generated based on texture and shape intensity of a frame), a recommendation system improves content recommendation using analytic and quantitative characteristics derived from a frame of a content item rather than merely manually labeled bibliographic data (e.g., a genre or producer). The recommendation system may generate a feature vector based on a texture, a shape intensity (e.g., generated from a Generalized Hough Transform), and temporal data corresponding to at least one frame of a video. The feature vector is analyzed using a machine learning model (e.g., a neural network) to produce a machine learning model output. The recommendation system causes a recommended content item to be provided based on the machine learning model output.

Abstract: Example methods, apparatus, systems and articles of manufacture to implement calibration of convenience panel data to reduce behavioral bias are disclosed. Disclosed example apparatus include a distribution estimator to determine a first behavioral distribution for first convenience panel data associated with a first market and a measurement period, determine a second behavioral distribution for second convenience panel data associated with a second market and the measurement period, and determine a third behavioral distribution for probabilistic panel data associated with the second market and the measurement period.

Abstract: A projection device having an information input unit, a storage unit, a scaling unit, an image processing unit and a projection unit is provided. The information input unit receives the image file corresponded to a compressed personalized startup image file. The storage unit has a first storage block storing a preset startup image file and a second storage block. The scaling unit generates a projected image signal according to the compressed personalized startup image file, and the scaling unit stores the compressed personalized startup image file in the at least one second storage block. The image processing unit generates a projection control signal according to the projected image signal. The projection unit generates an image beam according to the projection control signal, and projects the image beam on a projection surface to form the startup image screen. The disclosure further provides a personalized startup image setting method.

Abstract: Relevancy information describing a relevance of a digital content item to a user is received. The relevancy information is used to determine whether to notify the user of the digital content item. If it is determined to notify the user, it is inferred from activities of the user a time when the user is favorably disposed to consume the digital content item. A message is sent to a client device used by the user at the time when the user is favorable disposed to consume the digital content item.

Abstract: Embodiments relate to systematic explanation of neural model behavior and effective deduction of its vulnerabilities. Input data is received for the neural model and applied to the model to generate output data. Accuracy of the output data is evaluated with respect to the neural model, and one or more neural model vulnerabilities are identified that correspond to the output data accuracy. An explanation of the output data and the identified one or more vulnerabilities is generated, wherein the explanation serves as an indicator of alignment of the input data with the output data.

Abstract: According to one configuration, a content management resource receives feedback indicating playback commands applied to different portions of a given content stream (such as video content) played back by multiple viewers. The feedback can include video playback commands (such as fast forward commands, rewind commands, play commands, etc.) applied by the multiple users to the different portions of the given content stream. The content management resource aggregates the feedback to produce playback control information indicating playback commands applied by users of the multiple playback devices to the different portions of the given content stream. The content management resource uses the playback control information (aggregated feedback) to produce via timing information, locations of desirable segments and/or undesirable segments in the given stream as indicated by the previously applied commands. The content management resource inserts the aggregated feedback into the content metadata.

Abstract: In aspects of manage a video conference session in a multi-tasking environment, a computing device has a display screen to display a user interface of a foreground active application, such as a device application or a video conference session. The computing device implements a content control module that determines a user is designated as a participant of the video conference session, detects that a remote user connects to the video conference session from a remote device, and determines the device application is the foreground active application with the user interface of the device application displayed on the display screen. The content control module can then initiate to surface the user interface of the video conference session for display on the display screen responsive to the remote user connecting to the video conference session and the video conference session not being the foreground active application.

Abstract: When a content item is initially served to a client device, the content item may result in an impression effect. As time elapses, the initial impression may fade. Such a decay of the impression effect may be predicted through the use of a predictive model. In some implementations, one or more impression effect parameters may be accessed and used with the predictive model to determine a decay factor or predicted value that incorporates the impression effect decay for a content item. A value, such as a score, may be determined based on the decay factor or the predicted value and a bid associated with a content item. A content item may be selected based on the determined value and data to effect presentation of the content item may be provided.

Abstract: An information processing apparatus, an information processing method, and a program that are capable of providing a particular feedback in a displayed image in response to a predetermined operation by a plurality of users at matched timing. The information processing apparatus includes a control unit for recognizing a plurality of users, detecting operation, by each user, on a display surface where an image is being displayed, and outputting feedback on the image displayed on the display surface according to timing of detected operations by the plurality of users.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for dynamically transitioning a digital video file between encoding states of video data encodings. For example, upon receiving an uploaded digital video file, the disclosed systems can generate an initial set of video data encodings for the digital video file in an initial state. The disclosed systems further determine a virality score associated with the digital video file. Based on the virality score, the disclosed systems determine the virality score satisfies a threshold for transitioning the digital video file from the initial state to the upgraded state and generate premium encodings for the digital video file. Similarly, based on an updated virality score or a time-based trigger, the disclosed systems can transition the digital video file from the upgraded state (or the initial state) to the maintenance state by purging one or more video data encodings.

Abstract: Systems, methods, devices, instructions, and media are described for generating suggestions for connections between accounts in a social media system. One embodiment involves storing connection graph information for a plurality of user accounts, and identifying, by one or more processors of the device, a first set of connection suggestions based on a first set of suggestion metrics. A second set of connection suggestions is then identified based on a second set of suggestion metrics, wherein the second set of connection suggestions and the second set of suggestion metrics are configured to obscure the first set of connection suggestions, and a set of suggested connections is generated based on the first set of connection suggestions and the second set of connection suggestions. The set of connection suggestions is then communicated to a client device method associated with the first account.

Abstract: A system is disclosed for promoting a talent of a user. The system includes one or more application servers accessible over a wireless network, and a plurality of mobile clients configured to access the one or more application servers over the wireless network. The application servers and the mobile clients cooperate to execute a profiler mode of operation in which details of talents of profiler users are entered at respective mobile clients and uploaded to the application servers, each of the plurality of profiler users having a corresponding rank. The application servers and mobile clients also cooperate to execute a supporter mode of operation in which supporter users, using respective mobile clients, access the details of the talents and corresponding ranks of the profiler users. The supporter mode of operation facilitates advancement of a profiler user to a higher rank through receipt of endorsements.

Abstract: A system and method provides for the use of a proprietary platform to predict impressions and to predict and design ad campaigns. Specifically, a proprietary programmatic advertisement platform correlates television programming asset sources with actual viewing behavior of broadcasts associated with the television programming assets and ad content associated with the ad campaign. The correlation produces a predicted performance value used to generate an ad campaign. For instance, the invention enables television programming asset sources and viewership information providers to communicate with the programmatic advertisement platform in a way that adds value to or otherwise facilitates the valuation of the television programming asset sources in context of the particular ad.

Abstract: Systems and methods are described herein for providing content item recommendations based on a video. Using feature vectors corresponding to at least one frame of a video (e.g., generated based on texture and shape intensity of a frame), a recommendation system improves content recommendation using analytic and quantitative characteristics derived from a frame of a content item rather than merely manually labeled bibliographic data (e.g., a genre or producer). The recommendation system may generate a feature vector based on a texture, a shape intensity (e.g., generated from a Generalized Hough Transform), and temporal data corresponding to at least one frame of a video. The feature vector is analyzed using a machine learning model (e.g., a neural network) to produce a machine learning model output. The recommendation system causes a recommended content item to be provided based on the machine learning model output.

Abstract: A system for collecting data from different sources is described. In one example embodiment, the system obtains content-related data from a plurality of source computer systems, automatically identifies, based on the content-related data, content items having respective popularity values greater than a predetermined threshold value as popular content items, and automatically generates a list of popular content items based on the popular content items.

Abstract: A method for distributing media content and tracking viewer impressions in an out-of-home context includes: a mobile computing device receiving an identifier of a first media content item; causing display of the first media content item to a first viewer; sensing image data of the first viewer during display of the first media content item; determining a location of the mobile computing device during display of the first media content item to the first viewer; sending the image data of the first viewer, and an impression-reporting message including: the identifier of the first media content item and the location of the mobile computing device during display of the first media content item to the first viewer.

Abstract: A system and method for adaptive advertisement management for the serving of product description pages and an integrated customer user engagement thereof. The system is a cloud-based network containing a campaign database, an adaptive advertisement management, a short message service server, and user mobile and compute devices that transmit a product description page associated with an advertisement campaign embedded with a communication initiator for display on a customer computing device. Taken together or in part, said system optimizes advertising campaigns across multiple platforms, provides strong analytics for all advertising types while allowing users to engage with advertising quickly and easily through various call to action types.

Abstract: A processing device receives set-top box data, sales data, and advertising data. The processing device associates set-top boxes from the set-top box data with viewers and calculates advertising exposure events for advertisements. The processing device further calculates, for each viewer, an advertising weight as a function of number of exposures of the advertisement as applied to the viewer based on the advertising exposure events. The processing device further calculates, for each viewer, a score representing a degree-of-targetedness between an advertisement campaign and the viewer. The processing device manages the advertisement campaign based on the advertising weight and the degree-of-targetedness.

Abstract: Methods and systems are described for a media guidance application that enhances the viewing experiences of users consuming a sequence of media. In particular, the media guidance application may enhance the viewing experiences of users consuming a sequence of media by removing portions of redundant media that were previously consumed by the user.

Abstract: An information processing apparatus includes an acquisition unit and a changing unit. The acquisition unit acquires character information input by a viewer to content including an image or sound. The changing unit changes a representation form of a frequent word which is character information with a high appearance frequency among character information input by multiple viewers to the content.

Abstract: Methods and systems are described for downloading media assets efficiently and quickly before loss of network connectivity. The method may allow a user to download portions of a media asset in different versions to download a maximum portion of the media asset before loss of network connectivity. Certain versions of media assets may be downloaded more quickly than other versions of media assets. The method may also allow a user to view partially downloaded media assets without network connectivity. The method may also replace portions of media assets downloaded in a first version with portions of the media assets in a second version once network connectivity is restored.

Abstract: Systems and methods are disclosed herein for identifying users based on voice data and media consumption data. A media guidance application may generate a voice signature from the user's input and based on that signature identify some demographic characteristics of the user (e.g., age, gender, and other suitable characteristics). The media guidance application may retrieve user data for users that are associated with a household of the user and attempt to identify which of the users spoke the command. If multiple users are identified, based on the demographic characteristics, the media guidance application may use the content of the voice command (e.g., a type of media requested) to identify the user.

Abstract: Described herein are systems and methods for inserting breakpoints and reference links into a multimedia file. A method may comprise receiving breakpoint information from a content provider, wherein the breakpoint information is specific to a first digital media file of a plurality of digital media files, inserting a plurality of breakpoints into the first digital media file based on the breakpoint information, wherein the plurality of breakpoints designate at least one clip within the first digital media file, receiving a user share request from a user device to share the at least one clip within the first digital media file, and providing the user device with a sharable reference link to the at least one clip.

Abstract: Systems and methods are described to address shortcomings in conventional media systems via a novel technique to prevent corruption of a user's viewing profile. In some aspects, a user of an interactive media guidance application may select a media asset for viewing on a user device. The interactive media guidance application may receive a user viewing profile for the user from a remote server. If the media asset is determined to not be consistent with the user viewing profile, the interactive media guidance application may retrieve another user viewing profile for another user of the user device. If the media asset is determined to be consistent with the other user viewing profile, the interactive media guidance application may update the other user viewing profile based on the media asset.

Abstract: Aggregating viewership data is disclosed. Initially, household viewership data assigned to a tuning event in multiple households is accessed. Then, the household viewership data for the tuning event in the multiple households representing the same episode is aggregated to generate episode viewership data. Next, episode viewership data representing multiple episodes of the same program is aggregated to generate program viewership data. Next, the program viewership data for multiple programs of the same network is aggregated to generate network viewership data. Finally, the network viewership data for multiple commonly-owned networks is aggregated to generate entity viewership data.

Abstract: Novel tools and techniques to enable data to be tested on subscriber set-top boxes. Some solutions can connect a sever with a group of subscriber set-top boxes through a television distribution network. In some cases, a plurality of set-top boxes are selected, and at least one set-top box is determined to be inactive. In some cases, data are loaded and tested on the inactive set-top.

Abstract: An information processing apparatus includes an acquisition unit and a changing unit. The acquisition unit acquires character information input by a viewer to content including an image or sound. The changing unit changes a representation form of a frequent word which is character information with a high appearance frequency among character information input by multiple viewers to the content.

Abstract: A system and method is provided for using information broadcast by devices and resources in the immediate vicinity of a mobile device, or by sensors located within the mobile device itself, to ascertain and make a determination of the immediate environment and state of the mobile device. The sensor data is then used to identify situational profiles to target and determine the relevance of apps, advertisements, content, and recommendations.

Abstract: A system and method in which a TV signal reception device (e.g., set top box) receives a broadcast signal, sends the broadcast signal to a TV, and sends an event signal to a rating statistics information server or associated user terminal when a predetermined condition occurs, to ultimately cause an associated user terminal to generate fingerprint data of audio from the TV and to provide the fingerprint data to the server so as to facilitate channel identification and generation of ratings statistics.

Abstract: Methods and systems provide information products relating to past, present and future advertising transactions (i.e., contracts to place advertisements in various media) to enable a marketplace in advertising products. Information regarding a plurality of advertising transactions are gathered. Data is analyzed to determine its attributes. Some attribute values are transformed and the attribute values are stored in a database. Attributes are organized or indexed according to a taxonomy of attributes to provide indexes to advertising transaction records. Indexes and benchmarks for various selected types of advertising transactions can be generated by selecting certain records from the database and aggregating the data or otherwise synthesizing information products, such as benchmarks and market entities for the selected types of advertising transactions. Information products may be published and syndicated as market indexes and benchmarks.

Abstract: The present invention relates to a system and method for checking the viewing of content. The system includes: an operating computer including a means for storing at least one piece of combined content, in which first content and at least one piece of second content are combined, and a means for providing a benefit set for the combined content; and a user program including a content viewer means for playing back the combined content, and a signal input means for receiving at least one signal from a viewer when the second content is exposed in the combined content being played back via the content viewer means, and being executed on a user terminal; wherein the operating computer provides the benefit in connection with information of the viewer based on data generated based on the information of the signal transmitted from the user terminal and input to the signal input means.

Abstract: Systems and methods to select targeted advertising for display are disclosed. An example system to select a targeted advertisement includes an opportunity calculator to assign a household to a consumer segment based on (1) geodemographic characteristics of the household and (2) characteristics of the consumer segment.

Abstract: A smart playlist system is described. In one example embodiment, a collector module obtains content utilization data from a plurality of client devices associated with respective plurality of viewers. A hot list generator module generates a list of popular content items based on the obtained content utilization data. A customization module generates a customized playlist for a target viewer from the plurality of viewers, based on the list of popular content items and a profile of the target viewer. The communications module communicates the customized playlist to a client device of the target viewer.

Abstract: Systems and methods are described to address shortcomings in conventional conversation systems by executing a customized supplemental function for a natural language query based on the user's profile. In some aspects, the systems and methods receive a user query for a media asset, determine a query template in the user's profile matching the user's query, and identify and execute a supplemental function corresponding to the query template in addition to responding to the user's query. The user's profile is customized on the user's usage patterns of an interactive media guidance application. By monitoring the user's usage patterns and learning from the user's actions in conjunction with the user's natural language queries on which supplemental functions to execute, the interactive media guidance application may provide a smarter and more efficient user experience.

Abstract: An interaction method based on multimedia programs, a terminal device, a server and a system are disclosed, which belong to the field of network technologies. The method includes: acquiring at least one image clip information of a multimedia program in a process of playing back the multimedia program; sending the image clip information, the image clip information being used for matching corresponding multimedia program information; receiving interaction information corresponding to the multimedia program information; and outputting an interactive interface, to interact with the multimedia program based on an interaction operation on the interactive interface. The present disclosure is easy to operate, and improves interaction efficiency.

Abstract: A computing device includes program instructions to identify first communications by a first user about respective first media content items, each of the first communications made within a predetermined time preceding the first user's consumption of the respective first media content item. The computing device further includes instructions to identify a plurality of second users, each a party to one of the first communications. For the identified second users, the computing device determines a correlation between the respective second user and the consumption of the first media content items by the first user. Based at least in part on the correlation, the computing device includes further instructions to initiate a second communication between one of the second users and one of the first user and a third user concerning a second media content item.

Abstract: Methods and systems are described for a media guidance application that enhances the viewing experiences of users consuming a sequence of media. In particular, the media guidance application may enhance the viewing experiences of users consuming a sequence of media by removing portions of redundant media that were previously consumed by the user.

Abstract: Methods, systems, and computer program products for accessing data in a data structure are described. Data from a write data structure is read and aggregated into a plurality of data buckets, each data bucket corresponding to a time window. Each data bucket is stored in a read data structure.

Abstract: It is an object of the present invention to allow for appropriate control of how to present content during presentation of the content. An information processing apparatus obtains content identification information. Storage means stores operation logs each of which includes both the time at which an operation to control presentation of content was performed during presentation of the content and details of the operation. The information processing apparatus retrieves operation logs corresponding to the obtained content identification information from the storage means. Based on the retrieved operation logs, a tendency of operation changes is identified. In accordance with the tendency, the information processing apparatus generates control information for controlling how to present content. The control information includes details of control and a timing of the control. The information processing apparatus provides the control information.

Abstract: Examples described herein relate to apparatuses and methods for associating a first account with a second account, the first account being hosted by a first server, the second account being hosted by a second server, including but not limited to, authenticating, by the first server, first login credentials associated with the first account, wherein the first login credentials are received from a user device, receiving, by the first server from the user device, second login credentials associated with the second account, sending, by the first server, the second login credentials to the second server for authentication, in response to determining that the second login credentials are authenticated by the second server, associating, by the first server, the first account with the second account, and connecting, by the first server to the second server, to allow the user device to access services commensurate with the second account without prompting the user device for the second login credentials.