Abstract

Systems and methods are provided for generating labeled image data for improved training of an image classifier, such as a multi-layered machine learning model configured to identify target image objects in image data. When the initially trained classifier is unable to identify a particular object in input image data, such as an object that did not appear in initial training data, feature information determined by the classifier for the given image data may be provided to a clustering model. The clustering model may group image data having similar features into different clusters or groups, which may in turn be labeled at the group level by an annotator. The image data assigned to the different clusters, along with the associated labels, may subsequently be used as training data for training a classifier to identify the labeled objects in images.

IPC Classes  ?

• G06K 9/62 - Methods or arrangements for recognition using electronic means

Abstract

Systems and methods are described for server-side manipulation of underlying video content in order to dynamically place overlay content within a video stream in a manner whereby a viewing user sees the advertisement content over or integrated within a portion of the base video content. Segments of the original video file may be modified by a server to display overlay content over a portion of the original content, and a revised manifest file may be generated by the server and sent to a client device. The revised manifest file may cause a video player on the client device to present in sequence (a) a first original portion of the video, (b) a second portion of the video modified to include overlaid advertisement content or other overlay content within the second portion, followed by (c) a third original portion of the video.

IPC Classes  ?

• H04N 21/234 - Processing of video elementary streams, e.g. splicing of video streams or manipulating MPEG-4 scene graphs
• H04L 29/06 - Communication control; Communication processing characterised by a protocol
• H04N 21/2343 - Processing of video elementary streams, e.g. splicing of video streams or manipulating MPEG-4 scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements
• H04N 21/643 - Communication protocols
• H04N 21/81 - Monomedia components thereof
• H04N 21/845 - Structuring of content, e.g. decomposing content into time segments

Abstract

Systems and methods are provided for integrating supplemental overlay content within streaming video content that is to be broadcast to viewer devices. The overlay content to include in the streaming video content may be dynamically determined during video streaming and incorporated within individual frames of the video data, such as by a computing device of a user who is broadcasting his play of a video game or other activity, prior to the user's computing device sending those video frames (with embedded overlay content therein) to a streaming platform to be broadcast to potentially many viewers' devices.

IPC Classes  ?

• H04N 21/234 - Processing of video elementary streams, e.g. splicing of video streams or manipulating MPEG-4 scene graphs
• H04N 21/258 - Client or end-user data management, e.g. managing client capabilities, user preferences or demographics or processing of multiple end-users preferences to derive collaborative data
• H04N 21/2665 - Gathering content from different sources, e.g. Internet and satellite
• H04N 21/81 - Monomedia components thereof
• H04N 21/478 - Supplemental services, e.g. displaying phone caller identification or shopping application

Abstract

Systems and methods are provided for identifying one or more portions of images or video frames that are appropriate for augmented overlay of advertisement or other visual content, and augmenting the image or video data to include such additional visual content. Identifying the portions appropriate for overlay or augmentation may include employing one or more machine learning models configured to identify objects or regions of an image or video frame that meet criteria for visual augmentation. The pose of the augmented content presented within the image or video frame may correspond to the pose of one or more real-world objects in the real world scene captured within the original image or video.

IPC Classes  ?

• G06T 19/00 - Manipulating 3D models or images for computer graphics

Abstract

Systems and methods are provided for generating and using classification models to automatically classify pages or other source content as including text about one or more real-world events. Generating the classification models may include analyzing text content of a large number of different pages from both a reference source and from more dynamic sources, such as from publisher sources via a network. Features for training classifiers may be determined based in part on the top n-grams identified among pages that have been determined to be associated with a given event.

IPC Classes  ?

• G06Q 30/02 - Marketing; Price estimation or determination; Fundraising

Abstract

Systems and methods are described for dynamically presenting overlay content on portions of an image or video within a page or other user interface, while allowing at least partial user interactivity with the underlying image or video. Overlay content may be displayed within a container object that is placed over the underlying page image or video. The visible overlay content may be smaller than and/or differently shaped than the container object (such as by not being rectangular and/or by the overlay content including transparent portions), such that some of the underlying image or video remains visible beneath the overlay content and the container. When a user selection is made within the container object, the responsive action to be performed by the client computing device may be either an action identified in the original page code or an action associated with the overlay content, depending on location of the selection.

IPC Classes  ?

• G06Q 30/02 - Marketing; Price estimation or determination; Fundraising

Abstract

Systems and methods are described for identifying sports-related objects in media content, such as image or video data, using machine learning models. Features of the media content may be provided as input to classification models trained to detect depiction of various sports-related objects and scenes in order to generate various metrics associated with an underlying sporting event depicted in the media content.

IPC Classes  ?

• G06K 9/00 - Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
• G06K 9/62 - Methods or arrangements for recognition using electronic means