Abstract: Candidate brands are identified for an ad clip of a query video advertisement using two different techniques. Optical character recognition (OCR) is performed on a thumbnail of a plurality of different video ads in a curated database that includes brand-identifying metadata. In one technique, text vectorization is performed for each brand using all of the text that is extracted from each of the thumbnails for each brand, thereby providing a numerical brand embedding for each brand, a similar text vectorization is performed on the query video ad, and then a comparison is made between the embeddings to identify highest-ranking candidate brands based on brand-level identification. In another technique, a transformer-based model generates numerical embeddings for each ad clip in the curated database, and a comparison is made to these clip-based numerical embeddings to identify highest-ranking candidate brands based on clip-level identification.

Abstract: Automated methods are provided for identifying when a first advertisement (ad) is a likely match of either a second ad, or one or more variants of the second ad. The first ad, the second ad, and the one or more variants of the second ad each include a plurality of sequential segments of a predefined time length, wherein the second ad and the one or more variants of the second ad are each reference ads, and the first ad is a sample ad. Vectors of segment hits are created for the various ads and are compared to each other to identify matches that represent such variants.

Abstract: Systems and methods are provided for selectively replacing commercials that are in a video data stream with alternative commercials. Automatic content recognition (ACR) is performed on the video data stream to detect the identity of each of the commercials played in a commercial block during a commercial break. Commercials in the video data stream which are detected as being displayed on a video display device are stored in a first database, and commercials in the video data stream which are detected as not being displayed on the video display device are stored in a second database. A rules engine defines how commercials in the video data stream should be replaced with other commercials. Commercials in the video data stream that were previously detected as being displayed on the video display device are selectively replaced with commercials that were previously detected as not being displayed on the video display device.

Abstract: Ad break boundaries, which identify start and end points of a commercial break, are identified by detecting the absence of voices and/or facial images of one or more primary cast members of a currently scheduled program.

Abstract: A method and system are provided for assigning metadata candidates to a commercial by performing image analysis on a plurality of the video frames to identify video frames that include one or more of identifiable product-related logos, brand-related logos, product-related text, or brand-related text which appear in the video frames, capturing frame data for such video frames, categorizing a temporal position of the identified video frames within the commercial as being in either a beginning or ending portion of the commercial, or a middle portion of the commercial, and assigning to the commercial the identified products or brands as primary metadata candidates when the temporal position of the identified video frames within the commercial is in either the beginning or ending portion of the commercial.

Abstract: Automated methods are provided for identifying when a first advertisement (ad) is a likely variant of a second ad. The first and second ads each include a plurality of sequential segments of a predefined time length, wherein the second ad is a reference ad, and the first ad is a sample ad. In one embodiment, a vector of segment hits is created for the second ad, wherein the second ad is used as both the sample ad and the reference ad for creating the vector of segment hits for the second ad. A vector of segment hits is also created for the first ad, wherein the first ad is used as the sample ad and the second ad is used as the reference ad for creating the vector of segment hits for the first ad.

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: Black borders are detected in an image frame using a grey scale image of the image frame, and an edge image of the image frame. Candidate black borders are identified using maximum grey scale values associated with rows and columns of pixels of the grey scale image of the image frame, and then validated using a sum of grey scale values associated with rows and columns of pixels in the edge image of the image frame. If the validation fails, it is presumed that no black border exists.

Abstract: An automated method and apparatus are provided for identifying when a first video is a content-identical variant of a second video. The first and second video each include a plurality of image frames, and the image frames of either the first video or the second video include at least one black border. A plurality of variants are generated of selected image frames of the first video and the second video. The variants are then compared to each other, and the first video is identified as being a variant of the second video when at least one match is detected among the variants.

Abstract: Channel identifiers in electronic program guide (EPG) data are consolidated for one or more EPG providers, and the consolidated channel identifiers are used to automatically process audience measurement data.

Abstract: A closed loop attribution system may include a user location history storage system containing information indicative of user location history for a plurality of users based on location of a mobile device associated with a user; a user database storage system containing placement tracking information indicative of advertising content presented to the user; and a closed loop attribution processor responsive to said user location history storage system and said user database storage assessing correlations between a user's exposure and a user's location. The user database may include records indicative of user behavior and characteristics. The closed loop attribution processor may be connected to the campaign database and the campaign database may contain an indication of one or more locations of interest to an advertiser. The correlation between user exposure and a user's location may be a correlation between user exposure and the location or locations of interest.

Abstract: Recommendations are made to an e-shopper based on commercials that the e-shopper may have recently viewed on TV or heard on radio. In one preferred embodiment, a cloud-based server collects and stores TV viewership data through mobile devices, using automated content recognition (ACR).

Abstract: Systems and methods are provided for selectively replacing commercials that are in a video data stream with alternative commercials. Automatic content recognition (ACR) is performed on the video data stream to detect the identity of each of the commercials played in a commercial block during a commercial break. Commercials in the video data stream which are detected as being displayed on a video display device are stored in a first database, and commercials in the video data stream which are detected as not being displayed on the video display device are stored in a second database. A rules engine defines how commercials in the video data stream should be replaced with other commercials. Commercials in the video data stream that were previously detected as being displayed on the video display device are selectively replaced with commercials that were previously detected as not being displayed on the video display device.

Abstract: A method for managing a bidding process by keeping track of the sources for ad auction opportunity on the basis of an app generating the opportunity or web activity generating the opportunity. The bidding platform may limit bids on opportunities for a campaign when the successful placement of ads or opportunities from any source exceeds the source threshold set for that source.

Abstract: A computer program product is provided for predicting ad spend for a specific media program aired or streamed on a specific network at a specific date and time using a database of media program data that includes known ad spend for a subset of media programs, and viewership data for each of the media programs, including total viewership and viewership ratings. Each of the media programs is identified by its respective network, and date and time of airing or streaming. A random forest model is trained to predict ad spend using variables that are identified as being correlated with ad spend. The trained random forest model is then used to predict ad spend for a specific media program that is aired or streamed on a specific network at a specific date and time, and which has an unknown ad spend.

Abstract: A method is provided to identify whether video content, which includes a plurality of image frames, is likely to include an advertisement. The video content is split into a plurality of segments, each segment having a pre-specified duration. Subtitle text information is extracted from each segment and is passed through a natural language processing (NLP) language model to extract an embedding representing the subtitle text information for each of the segments, wherein the NLP language model is previously trained to differentiate between subtitle text information from video content items that were each previously identified as being an advertisement in comparison to subtitle text information from video content items that were each previously identified as not being an advertisement. The embedding representing the subtitle text information for each of the segments is passed through a classifier to obtain a probability regarding whether each segment is an advertisement or not.

Abstract: A system and method are provided for detecting the presence of potential commercials in a video data stream. Each of the commercials has an expected time length that is an integer multiple of a first predetermined time length, and has an overall time length that is equal to or less than a second predetermined time length. Transitions in the audio or video of the video data stream are detected and the time of the transitions are recorded. Time differences between one or more successive transitions are detected. Any time differences that are an integer multiple of the first predetermined time length, and that have an overall time length that is equal to or less than the second predetermined time length are identified. The contents of the video data stream associated with the identified time differences are flagged as potential commercials and sent to a content processing platform for further analysis.

Abstract: A content recommendation system that recommends content based on previous user content information and information regarding the user and user device. The system is capable of accurately recommending content using collaborative filtering by comparing the user's profile to other user profiles. User profiles rely on implicit ratings to determine user preferences. Implicit ratings may be determined by collecting the content that a user consumed, in addition to user and user device information. The system recommends content that similar users have consumed. The system is also able to identify and recommend trending content by analyzing changes in metrics over time. The system may also rely on automatic content recognition to identify content that the user is consuming without requiring active user input.

Abstract: Unknown potential commercials are detected in a video data stream that contains segments of program type content, and blocks of commercial content. Each block includes a plurality of successive individual commercials. A library of known commercials is maintained in a first database. A video data stream is received in a video processing engine which includes a search engine that is in communication with the first database. The search engine identifies all known commercials in the video data stream and their respective start and end times. The video processing engine identifies all time segments that are sandwiched between the known commercials. The video processing engine filters out as a potential commercial any identified time segments that are significantly longer than the time length of a commercial. The video processing engine designates content of each of the time segments that were not filtered out as being one or more unknown potential commercials.

Abstract: Systems and methods are provided to generate a personalized video channel for a viewer. Selected parameters of the viewer's viewing behavior with respect to one or more media devices that are associated with the viewer are automatically monitored and detected during one or more sampling periods. Media content sources that are available to the viewer on the one or more media devices are automatically detected. A personalized video channel is then generated for the viewer using at least the monitoring parameters and the detected media content sources. During a viewing session on one of the media devices, the generated personalized video channel is displayed.