Abstract: Metadata for highlights of a video stream is extracted from card images embedded in the video stream. The highlights may be segments of a video stream, such as a broadcast of a sporting event, that are of particular interest to one or more users. Card images embedded in video frames of the video stream are identified and processed to extract text. The text characters may be recognized by applying a machine-learned model trained with a set of characters extracted from card images embedded in sports television programming contents. The training set of character vectors may be pre-processed to maximize metric distance between the training set members. The text may be interpreted to obtain the metadata. The metadata may be stored in association with the portion of the video stream. The metadata may provide information regarding the highlights, and may be presented concurrently with playback of the highlights.

Abstract: A computing system receives a proposed bet selection for an event. The proposed bet selection includes team information and opponent information. The computing system generates a plurality of queries by analyzing the proposed bet selection. The computing system retrieves historical data related to the proposed bet selection based on the plurality of queries. The computing system analyzes the historical data to generate a plurality of insights related to the proposed bet selection. The computing system provides the historical data and the plurality of insights to a user submitting the proposed bet selection.

Abstract: According to systems and techniques disclosed herein, a plurality of real-time event data including a plurality of real-time event actions of a player may be received. One or more event actions associated with a unique identifier may be updated with the plurality of real-time event actions. A unique index may be generated based on a plurality of weights applied to the one or more event actions associated with the unique identifier. The unique index may be generated in real-time as the plurality of real-time event data is received. An interactive display may be generated including at least a graphical representation of the one or more event actions associated with the unique identifier, a graphical representation of the plurality of weights applied to the one or more event actions, and the unique index. The interactive display may be generated in real-time as the plurality of real-time event data is received.

Abstract: A method may include receiving data for a game, the data comprising at least tracking data or event data. The method may include determining an occurrence of a trigger event within the game based on the data for the game, and providing the data for the game and the trigger event to a machine learning (ML) model. The ML model may be trained to generate a graphic based on the data for the game and the occurrence of the trigger event. The method may include receiving, from the ML model, the graphic based on the data for the game and the occurrence of the trigger event; and generating, using a template, a visual element including the graphic for presentation within a user interface. The visual element may be associated with a marker, the marker representing a recommended position for an interactive element to be presented within the user interface.

Abstract: Customized highlight shows for sporting events, entertainment events, and/or the like, having a narrative component, are generated and presented. The events can be sporting events, entertainment events, and/or the like. For example, in the context of sporting events, a determination is made as to what types of sports, teams, leagues, players, plays and/or the like are of interest to the user. A customized highlight show is then generated and presented, containing those specific portions of the sporting events that are likely to be of interest, arranged in a manner that is likely to be entertaining and interesting to the user and that presents a cohesive narrative.

Abstract: Examples disclosed herein may generate a refined and denoised body pose data from a video feed of a sporting event. Tracking data containing player locations may be used to determine correspondence between a location and a body pose. For example, body pose with middle of key footpoints with shortest distance from the location may be selected as a likely body pose for the location. The body pose data may be refined to estimate the length of missing limbs or limbs with unusual length ratios. The body pose data may further be filtered to filter out unwanted body poses such as body poses of spectators or noisy body poses. The refined and filtered body pose data may be used for other downstream processing such as projecting the body poses to a three dimensional play surface.

Abstract: A computing system identifies broadcast video for a plurality of games in a first league. The broadcast video includes a plurality of video frames. The computing system generates tracking data for each game from the broadcast video of a corresponding game. The computing system enriches the tracking data. The enriching includes merging play-by-play data for the game with the tracking data of the corresponding game. The computing system generates padded tracking data based on the tracking data. The computing system projects player performance in a second league for each player based on the tracking data and the padded tracking data.

Abstract: A computing system receives data for a game. The data includes at least one of tracking data or event data. Based on the data for the game, the computing system determines that an event has occurred within the game. Based on the determining, the computing system generates a graphic responsive to the event. The graphic includes insights related to the event. The computing system recommends an image relevant to the event based on metatags associated with the event. The computing system generates a visual element by merging the image and the graphic.

Abstract: A computing system identifies broadcast video data for a game. The computing system generates tracking data for the game from the broadcast video data using computer vision techniques. The tracking data includes coordinates of players during the game. The computing system generates optical character recognition data for the game from the broadcast video data by applying one or more optical character recognition techniques to each frame of the plurality of frames to extract score and time information from a scoreboard displayed in each frame. The computing system detects a plurality of events that occurred in the game by applying one or more machine learning techniques to the tracking data. The computing system receives play-by-play data for the game. The computing system generates enriched tracking data. The generating includes merging the play-by-play data with one or more of the tracking data, the optical character recognition data, and the plurality of events.

Abstract: A method of generating a multi-modal prediction is disclosed herein. A computing system retrieves event data from a data store. The event data includes information for a plurality of events across a plurality of seasons. Computing system generates a predictive model using a mixture density network, by generating an input vector from the event data learning, by the mixture density network, a plurality of values associated with a next play following each play in the event data. The mixture density network is trained to output the plurality of values near simultaneously. Computing system receives a set of event data directed to an event in a match. The set of event data includes information directed to at least playing surface position and current score. Computing system generates, via the predictive model, a plurality of values associated with a next event following the event based on the set of event data.

Abstract: A computing system identifies player tracking data and event data corresponding to a match. The match includes a first team and a second team. The player tracking data includes coordinate positions of each player during the event. The event data defines events that occur during the match. The computing system divides the player tracking data into a plurality of segments based on the event information. For each segment of the plurality of segments, the computing system learns a first formation associated with a respective team in possession. For each segment of the plurality of segments, the computing system learns a second formation associated with a respective team not in possession. The computing system maps each first formation to a first class of known formation clusters. The computing system maps each second formation to a second class of known formation clusters.

Abstract: A method for delivering interactive video to a user is disclosed herein. A computing system identifies video contents corresponding to a sporting event. The video contents include a plurality of video frames. The computing system annotates each video frame of the plurality of video frames to uniquely identify the video frame and contents contained therein. The computing system receives, from a plurality of prediction models, a plurality of data inputs related to agents and actions captured in each video frame of the plurality of video frames. The computing system generates a plurality of data frames based on the plurality of data inputs. The computing system associates each data frame with a respective video frame using the annotations. The computing system causes a user device to present the interactive video to the user by instructing the user device to merge the plurality of data frames with the plurality of video frames.

Abstract: A computing system receives a proposed bet selection for an event. The proposed bet selection includes team information and opponent information. The computing system generates a plurality of queries by analyzing the proposed bet selection. The computing system retrieves historical data related to the proposed bet selection based on the plurality of queries. The computing system analyzes the historical data to generate a plurality of insights related to the proposed bet selection. The computing system provides the historical data and the plurality of insights to a user submitting the proposed bet selection.

Abstract: Examples disclosed herein may generate a refined and denoised body pose data from a video feed of a sporting event. Tracking data containing player locations may be used to determine correspondence between a location and a body pose. For example, body pose with middle of key footpoints with shortest distance from the location may be selected as a likely body pose for the location. The body pose data may be refined to estimate the length of missing limbs or limbs with unusual length ratios. The body pose data may further be filtered to filter out unwanted body poses such as body poses of spectators or noisy body poses. The refined and filtered body pose data may be used for other downstream processing such as projecting the body poses to a three dimensional play surface.

Abstract: A system and method of calibrating moving cameras capturing a sporting event is disclosed herein. A computing system retrieves a broadcast video feed for a sporting event. The broadcast video feed includes a plurality of video frames. The computing system labels, via a neural network, components of a playing surface captured in each video frame. The computing system matches a subset of labeled video frames to a set of templates with various camera perspectives. The computing system fits a playing surface model to the set of labeled video frames that were matched to the set of templates. The computing system identifies camera motion in each video frame using an optical flow model. The computing system generates a homography matrix for each video frame based on the fitted playing surface model and camera motion. The computing system calibrates each camera based on the homography matrix generated for each video frame.

Abstract: A method of generating a player prediction is disclosed herein. A computing system retrieves data from a data store. The computing system generates a predictive model using an artificial neural network. The artificial neural network generates one or more personalized embeddings that include player-specific information based on historical performance. The computing system selects, from the data, one or more features related to each shot attempt captured in the data. The artificial neural network learns an outcome of each shot attempt based at least on the one or more personalized embeddings and the one or more features related to each shot attempt.

Abstract: A computing system receives data for a game. The data includes at least one of tracking data or event data. Based on the data for the game, the computing system determines that an event has occurred within the game. Based on the determining, the computing system generates a graphic responsive to the event. The graphic includes insights related to the event. The computing system recommends an image relevant to the event based on metatags associated with the event. The computing system generates a visual element by merging the image and the graphic.

Abstract: A method of generating a dynamic rating for an entity and rearranging an icon associated with the entity on a graphical user interface (GUI) of a computer system. The method includes: receiving a first set of data associated with one or more parameters for the entity; calculating a plurality of ability scores based on the first set of data; generating a first player rating based on each ability score of the plurality of ability scores; dynamically adjusting the plurality of ability scores based on receiving a second set of data associated with the one or more parameters for the entity; updating the first player rating based on the adjusted plurality of ability scores; automatically rearranging the icon to a position above or below a current position of the icon on the GUI based on the updated first player rating.

Abstract: A system and method of re-identifying players in a broadcast video feed are provided herein. A computing system retrieves a broadcast video feed for a sporting event. The broadcast video feed includes a plurality of video frames. The computing system generates a plurality of tracks based on the plurality of video frames. Each track includes a plurality of image patches associated with at least one player. Each image patch of the plurality of image patches is a subset of the corresponding frame of the plurality of video frames. For each track, the computing system generates a gallery of image patches. A jersey number of each player is visible in each image patch of the gallery. The computing system matches, via a convolutional autoencoder, tracks across galleries. The computing system measures, via a neural network, a similarity score for each matched track and associates two tracks based on the measured similarity.

Abstract: One or more highlights of a video stream may be identified. The highlights may be segments of a video stream, such as a broadcast of a sporting event, that are of particular interest to one or more users. According to one method, at least a portion of the video stream may be stored. The portion of the video stream may be compared with templates of a template database to identify the one or more highlights. Each highlight may be a subset of the video stream that is deemed likely to match the one or more templates. The highlights, an identifier that identifies each of the highlights within the video stream, and/or metadata pertaining particularly to the one or more highlights may be stored to facilitate playback of the highlights for the users.