Abstract: Systems, methods, and computer program products are provided for breach detection using convolutional neural networks (CNNs). An example system includes a processor configured to generate a plurality of permuted images, each image comprising a field of points associated with suspected fraudulent transactions, an x-axis position of each point associated with a time, and a y-axis position of each point corresponding to a randomized index of a payment device. The processor is also configured to assign a breach likelihood score to each image using a CNN model. The processor is further configured to compare the breach likelihood score of each image to a threshold score. The processor is further configured to detect the breach event based on one or more breach likelihood scores satisfying the threshold score. The processor is further configured to, in response to detecting the breach event, decline transactions with the entity associated with the breach event.

Abstract: Systems, methods, and computer program products for multi-domain ensemble learning based on multivariate time sequence data are provided. A method may include receiving multivariate sequence data. At least a portion of the multivariate sequence data may be inputted into a plurality of anomaly detection models to generate a plurality of scores. The multivariate sequence data may be combined with the plurality of scores to generate combined intermediate data. The combined intermediate data may be inputted into a combined ensemble model to generate an output score. In response to determining that the output score satisfies a threshold, at least one of an alert may be communicated to a user device, the multivariate sequence data may be inputted into the feature-domain ensemble model to generate a feature importance vector, or at least one of a model-domain, a time-domain, a feature-domain, or the combined ensemble model may be updated.

Abstract: Methods and systems are provided for synthesizing realistic time series data that may be used to better identify outliers within the synthesized realistic time series data. Noise can be introduced to a time domain representation of time series data and can introduce noise to a frequency domain representation of the time series data. Further, labeled anomalous points can be inserted into the time series data. The time series data may then be used for training a machine learning model to identify anomalies within new time series data.

Abstract: Various implementations disclosed herein include devices, systems, and methods that provide a visual marker including a plurality of markings arranged in a corresponding plurality of shapes. In some implementations, each marking is formed of a set of sub-markings separated by gaps and arranged according to a respective shape, and the gaps of the plurality of markings are configured to encode data and indicate orientation of the visual marker. In some implementations, the plurality of markings are arranged in a plurality of concentric rings of increasing size. In some implementations, the orientation is encoded in a first set of gaps and data in a second set of gaps of the gaps in the plurality of markings.

Abstract: Various implementations disclosed herein assess the blurriness of portions of images depicting shapes such as codes or text that have known structural elements. This may involve determining whether a portion of an image of a code or text is sufficiently clear (not blurry) to be accurately interpreted. Blur may be assessed based on spatial frequency of statistical analysis. Blur may be assessed using a machine learning model that is trained using target blur metrics determined based on spatial frequency (e.g., analysis of high frequency portions of discrete cosine transforms of image portions) or statistical analysis (e.g., based on corner/edge detection in image portions).

Abstract: Systems, methods, and computer program products for multi-domain ensemble learning based on multivariate time sequence data are provided. A method may include receiving multivariate sequence data. At least a portion of the multivariate sequence data may be inputted into a plurality of anomaly detection models to generate a plurality of scores. The multivariate sequence data may be combined with the plurality of scores to generate combined intermediate data. The combined intermediate data may be inputted into a combined ensemble model to generate an output score. In response to determining that the output score satisfies a threshold, at least one of an alert may be communicated to a user device, the multivariate sequence data may be inputted into the feature-domain ensemble model to generate a feature importance vector, or at least one of a model-domain, a time-domain, a feature-domain, or the combined ensemble model may be updated.

Abstract: Methods and devices for processing image data for scene completion, including receiving an original image from an original viewpoint corresponding to a first direction, wherein the original image includes an object; obtaining a first image from a new viewpoint corresponding to a second direction different from the first direction by rotating the original image based on 3-dimensional (3D) information generated from 2-dimensional (2D) information which is obtained from the original image; determining an area within the first image for generating a second surface of the object based on depth information about a depth between the object and the background of the original image, wherein the determined area is expected to include an object area; and obtaining a second image by inputting the first image and the determined area to an artificial intelligence (AI) inpainting model, wherein the AI inpainting model generates the second surface of the object which occupies a portion of the determined area in the second im

Abstract: Various implementations disclosed herein include devices, systems, and methods that provide a visual marker including a plurality of markings arranged in a corresponding plurality of shapes. In some implementations, each marking is formed of a set of sub-markings separated by gaps and arranged according to a respective shape, and the gaps of the plurality of markings are configured to encode data and indicate orientation of the visual marker. In some implementations, the plurality of markings are arranged in a plurality of concentric rings of increasing size. In some implementations, the orientation is encoded in a first set of gaps and data in a second set of gaps of the gaps in the plurality of markings.

Abstract: One or more computing devices, systems, and/or methods are provided. In an example, an internet resource identification item associated with one or more internet resources may be identified. User activity information associated with a plurality of events may be analyzed to determine a plurality of sets of text associated with the internet resource identification item, wherein each set of text of the plurality of sets of text is associated with an event, of the plurality of events, associated with an internet resource of the one or more internet resources. A plurality of term representations may be determined based upon the plurality of sets of text. A user intention-based representation associated with the internet resource identification item may be generated based upon the plurality of term representations. A content item may be selected for presentation via a client device based upon the user intention-based representation.

Abstract: The present teaching relates to method and system for prediction of demographic/interest based on data from different sources (DFDS) relating to users. The DFDS is processed to link data from different sources associated with each of the users. The linked DFDS associated with each user is used to obtain a joint feature vector for simultaneously predicting, based on a joint prediction model, multiple pieces of demographic/interest information of the user. Based on the predicted demographics/interests for different users, content is distributed to target users identified based on their respective predicted demographics/interests.

Abstract: Described are a system, method, and computer program product for breach detection using convolutional neural networks. The method includes receiving transaction data associated with a plurality of transactions completed in a first time period. The method also includes identifying a set of suspected fraudulent transactions of the plurality of transactions based on inputting at least one parameter of the transaction data into a fraud evaluation model. The method further includes generating an image comprising a field of points, wherein each point is associated with at least one transaction of the set of suspected fraudulent transactions, and wherein an x-axis position in the image of each point in the field of points is associated with a time subperiod of the first time period in which the at least one transaction occurred. The method further includes detecting a breach event by processing the image with a convolutional neural network (CNN) model.

Abstract: Systems, methods, and apparatuses for controlling a robot including a manipulator, including: determining three-dimensional (3D) geometry information about a target object based on an image of the target object; determining 3D geometry information about a scene in which the target object is to be placed based on at least one image of the scene; obtaining affordance information by providing the 3D geometry information about the target object and the 3D geometry information about the scene to at least one neural network model; commanding the robot to grasp the target object using the manipulator according to a grasp orientation corresponding to the affordance information; and commanding the robot to position the manipulator according to a placement direction corresponding to the affordance information in order to place the target object at a location in the scene.

Abstract: Described herein are techniques and systems directed to using context data provided by supplemental devices to reduce false declines during transaction authorization. In some embodiments, upon a transaction being declined based on a level of risk associated with the transaction, a service provider may obtain context data from a number of supplemental devices associated with a user, resource provider, location, or other suitable factor. This context data may then be assessed by the service provider to determine a degree to which the context data supports that the user conducting the transaction is the owner of the account used to conduct the transaction. The level of risk may then be adjusted based on that degree and the adjusted level of risk is used to determine whether to approve or decline the transaction.

Abstract: Systems, methods, and computer program products for multi-domain ensemble learning based on multivariate time sequence data are provided. A method may include receiving multivariate sequence data. At least a portion of the multivariate sequence data may be inputted into a plurality of anomaly detection models to generate a plurality of scores. The multivariate sequence data may be combined with the plurality of scores to generate combined intermediate data. The combined intermediate data may be inputted into a combined ensemble model to generate an output score. In response to determining that the output score satisfies a threshold, at least one of an alert may be communicated to a user device, the multivariate sequence data may be inputted into the feature-domain ensemble model to generate a feature importance vector, or at least one of a model-domain, a time-domain, a feature-domain, or the combined ensemble model may be updated.

Abstract: One or more computing devices, systems, and/or methods for generating time-preserving embeddings are provided. User trails of user activities performed by users are generated. Frequencies at which the activities were performed are identified. Indices are assigned to a set of activities identified from the activities as having frequencies above a threshold. Activity descriptions of the set of activities are mapped to the indices to generate a vocabulary. A model is trained using the user trails, timestamps of the activities, and the vocabulary to learn a set of time-preserving embeddings.

Abstract: One or more computing devices, systems, and/or methods are provided. In an example, an internet resource identification item associated with one or more internet resources may be identified. User activity information associated with a plurality of events may be analyzed to determine a plurality of sets of text associated with the internet resource identification item, wherein each set of text of the plurality of sets of text is associated with an event, of the plurality of events, associated with an internet resource of the one or more internet resources. A plurality of term representations may be determined based upon the plurality of sets of text. A user intention-based representation associated with the internet resource identification item may be generated based upon the plurality of term representations. A content item may be selected for presentation via a client device based upon the user intention-based representation.

Abstract: Methods and systems for predicting titles for contents segments of media items at a platform using machine-learning are provided herein. A media item is provided to users of a platform, the media item having a plurality of content segments comprising a first content segment and a second content segment preceding the first content segment in the media item. The first content segment and a title of the second content segment are provided as input to a machine-learning model trained to predict a title for the first content segment that is consistent with the title of the second content segment. One or more outputs of the machine-learning model are obtained which indicate the title for the first content segment. An indication of each content segment and a respective title of each content segment are provided for presentation to at least one user of the one or more users.

Abstract: This teaching relates to predictive targeting. Training data are obtained with pairs of data. Each pair includes an ad opportunity context corresponding to an ad served to a plurality of audiences and a label vector having a plurality of labels, each of which indicates a reaction, with respect to the ad served, of a corresponding one of the audiences in the ad opportunity context. Based on the training data, model parameters of a joint predictive model are learned via machine learning based on an initialized model with initial model parameters by minimizing a loss in an iterative process. The learned joint predictive model is to be used to map an input context of an ad opportunity to an output label vector having a plurality of probabilities, each of which predicts a likelihood of a reaction of a corresponding one of the audiences to the input context of the ad opportunity.

Abstract: Various implementations disclosed herein include devices, systems, and methods that provide a visual marker including a plurality of markings arranged in a corresponding plurality of shapes. In some implementations, each marking is formed of a set of sub-markings separated by gaps and arranged according to a respective shape, and the gaps of the plurality of markings are configured to encode data and indicate orientation of the visual marker. In some implementations, the plurality of markings are arranged in a plurality of concentric rings of increasing size. In some implementations, the orientation is encoded in a first set of gaps and data in a second set of gaps of the gaps in the plurality of markings.

Abstract: One or more computing devices, systems, and/or methods are provided. In an example, an internet resource identification item associated with one or more internet resources may be identified. User activity information associated with a plurality of events may be analyzed to determine a plurality of sets of text associated with the internet resource identification item, wherein each set of text of the plurality of sets of text is associated with an event, of the plurality of events, associated with an internet resource of the one or more internet resources. A plurality of term representations may be determined based upon the plurality of sets of text. A user intention-based representation associated with the internet resource identification item may be generated based upon the plurality of term representations. A content item may be selected for presentation via a client device based upon the user intention-based representation.