Abstract: Described are systems and methods to determine hair patterns presented in content items. The determined hair patterns may be associated with the content items to facilitate indexing, filtering, etc. of the content items based on the determined hair patterns. In exemplary implementations, a corpus of content items may be associated with an embedding vector that includes a binary representation of the content item. The embedding vectors associated with each content item can be provided as inputs to a trained machine learning model, which can process the embedding vectors to determine one or more hair patterns presented in each content item while eliminating the need for performing image pre-processing prior to determination of the hair pattern(s) presented in the content item.

Abstract: Described are systems and methods to determine hair patterns presented in content items. The determined hair patterns may be associated with the content items to facilitate indexing, filtering, etc. of the content items based on the determined hair patterns. In exemplary implementations, a corpus of content items may be associated with an embedding vector that includes a binary representation of the content item. The embedding vectors associated with each content item can be provided as inputs to a trained machine learning model, which can process the embedding vectors to determine one or more hair patterns presented in each content item while eliminating the need for performing image pre-processing prior to determination of the hair pattern(s) presented in the content item.

Abstract: Described are systems and methods to determine hair patterns presented in content items. The determined hair patterns may be associated with the content items to facilitate indexing, filtering, etc. of the content items based on the determined hair patterns. In exemplary implementations, a corpus of content items may be associated with an embedding vector that includes a binary representation of the content item. The embedding vectors associated with each content item can be provided as inputs to a trained machine learning model, which can process the embedding vectors to determine one or more hair patterns presented in each content item while eliminating the need for performing image pre-processing prior to determination of the hair pattern(s) presented in the content item.

Abstract: The disclosed embodiments provide a system for processing data. During operation, the system receives, over a set of event streams, a set of logging events for actions performed between members and jobs over multiple channels. Next, the system aggregates a subset of the logging events spanning a logging window by a reference identifier (ID) generated based on a user session of a member, a first member ID for the member, and a first job ID for a job. The system then creates, based on a unified data logic, a record containing a subset of the actions represented by the logging events and contexts for the subset of the actions. Finally, the system outputs the record for use in subsequent analysis associated with the member and the job.

Abstract: Described are systems and methods for extracting parameters associated with a look/beauty aesthetic presented in a content item such as an image or a video. The extracted parameters can be used to identify beauty products that can be used to create a similar look/beauty aesthetic and to render the beauty product on a streaming live-feed video of the user so that the user can assess how the product looks on the user. Aspects of the disclosure also relate to classifying content items presenting a look/beauty aesthetic based on a dominant skin tone present in the content item.

Abstract: In an example, features in a boosting decision tree model are initialized to zero, the boosting decision tree model located in a GLMM and connected to a deep neural network collaborative filtering model via a prediction layer. While the features in the boosting decision tree model remain zero, the deep neural network collaborative filtering model is trained. One or more trees in the boosting decision tree model are boosted using logits produced by the training of the deep neural network collaborative filtering model as a margin. The prediction layer is trained using features from the deep neural network collaborative filtering model and features from the boosting decision tree model. It is then determined whether a set of convergence criteria is met. If not, then the deep neural network collaborative filtering model is retrained using the features and the process is repeated until the set of convergence criteria is met.

Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains a set of rules for filtering job recommendations, wherein the rules are selected to maximize a reduction in negative outcomes associated with the job recommendations. Next, the system generates a label for a set of candidate-job pairs that match one or more of the rules and inputs the label with a set of candidate-job features for the set of candidate-job pairs as training data for a filtering model. The system then applies the filtering model to additional candidate-job features associated with a candidate and a set of jobs to produce a set of scores, wherein each score represents a likelihood that the candidate perceives a corresponding job as an undesirable recommendation. Finally, the system outputs a subset of the jobs as recommendations to the candidate based on the set of scores.

Abstract: The disclosed embodiments provide a system for processing data. During operation, the system receives, over a set of event streams, a set of logging events for actions performed between members and jobs over multiple channels. Next, the system aggregates a subset of the logging events spanning a logging window by a reference identifier (ID) generated based on a user session of a member, a first member ID for the member, and a first job ID for a job. The system then creates, based on a unified data logic, a record containing a subset of the actions represented by the logging events and contexts for the subset of the actions. Finally, the system outputs the record for use in subsequent analysis associated with the member and the job.

Abstract: The present principles generally relate to multimedia processing and viewing, and particularly, to apparatuses and methods for obtaining enhanced user feedback ratings of a multimedia program. In an exemplary embodiment, viewers are provided with different opportunities to provide user feedback including feedback ratings for the multimedia program during various points in the playout of the program. The various points can be based on the content of the program or during different selected time intervals during the playout of the program.

Abstract: This disclosure relates to systems and methods for recommending relevant positions. A method includes receiving a request from a member for available employment positions posted at a social networking service, determining a cohort for the member, retrieving a query that is associated with the cohort for the member, executing the query at a database of employment positions, receiving results of the query, and causing the results of the query to be displayed, using an electronic user interface, to the member.

Abstract: In an example, features in a boosting decision tree model are initialized to zero, the boosting decision tree model located in a GLMM and connected to a deep neural network collaborative filtering model via a prediction layer. While the features in the boosting decision tree model remain zero, the deep neural network collaborative filtering model is trained. One or more trees in the boosting decision tree model are boosted using logits produced by the training of the deep neural network collaborative filtering model as a margin. The prediction layer is trained using features from the deep neural network collaborative filtering model and features from the boosting decision tree model. It is then determined whether a set of convergence criteria is met. If not, then the deep neural network collaborative filtering model is retrained using the features and the process is repeated until the set of convergence criteria is met.

Abstract: A privacy auditor determines discrepancies between user privacy settings in a social network and installed applications. The privacy auditor can employ a privacy determinator that tests an installed application on various privacy levels to determine actual privacy settings of the installed application. The privacy auditor then uses a privacy comparator to derive differences between the actual privacy settings of the installed application and the user privacy settings from the social network.

Abstract: A receiver on a mobile device accepts at least one unrequested signal from a transmitter located in proximity of a first screen showing a first multimedia content. The received signal contains information associated with a second multimedia content shown on a second screen. The information can trigger an application residing on the mobile device based on the characteristics of the received signal. The information is accepted by the application which then generates second screen information associated with a displaying of a second multimedia content on a second screen, the generation of the second screen information based upon the information, reception of the transmitted signal and a location of the second screen.

Abstract: Described herein is a method and system for providing privacy guarantees with an improved privacy-accuracy trade-off. Dynamic data can be accessed from a database. A sum model is selected from window sum, exponential decay sum, and polynomial decay sum. An algorithm is initiated that produces polylogarithmic bounded error in the range of a sum function associated with the selected sum model and independent of time steps. The data can be assembled in a dyadic tree structure. A non-linearity component can be added to nodes of the dyadic tree structure. For example, this can be a noise components or a weight applied to the update. This can be done, for example, to different nodes differently. Differential private estimators can be constructed for fixed steps of time. The differential private estimators can be applied to a query means or filtering system to enhance privacy protection from potential adversaries.

Abstract: The present embodiments focus on the privacy-utility tradeoff encountered by a user who wishes to release some public data (denoted by X) to an analyst, that is correlated with his private data (denoted by S), in the hope of getting some utility. When noise is added as a privacy preserving mechanism, that is, Y=X+N, where Y is the actual released data to the analyst and N is noise, we show that adding Gaussian noise is optimal under 1_2-norm distortion for continuous data X. We denote the mechanism of adding Gaussian noise that minimizes the worst-case information leakage by Gaussian mechanism. The parameters for Gaussian mechanism are determined based on the eigenvectors and eigenvalues of the covariance of X. We also develop a probabilistic privacy preserving mapping mechanism for discrete data X, wherein the random discrete noise follows a maximum-entropy distribution.

Abstract: The present embodiments focus on the privacy-utility tradeoff encountered by a user who wishes to release some public data to an analyst, which is correlated with his private data, in the hope of getting some utility. When multiple data are released to one or more analyst, we design privacy preserving mappings in a decentralized fashion. In particular, each privacy preserving mapping is designed to protect against the inference of private data from each of the released data separately. Decentralization simplifies the design, by breaking one large joint optimization problem with many variables into several smaller optimizations with fewer variables.

Abstract: The present principles focus on the privacy-utility tradeoff encountered by a user who wishes to release some public data (denoted by X) to an analyst, that is correlated with his private data (denoted by S), in the hope of getting some utility. The public data is distorted before its release according to a probabilistic privacy preserving mapping mechanism, which limits information leakage under utility constraints. In particular, this probabilistic privacy mechanism is modeled as a conditional distribution, P_(Y|X), where Y is the actual released data to the analyst. The present principles design utility-aware privacy preserving mapping mechanisms against inference attacks, when only partial, or no, statistical knowledge of the prior distribution, P_(S,X), is available. Specifically, using maximal correlation techniques, the present principles provide a separability result on the information leakage that leads to the design of the privacy preserving mapping.

Abstract: A method comprising receiving an image, the image including associated contextual information; converting the received image into searchable image data, the searchable image data being descriptive of the received image; filtering information from a search database based on the contextual information associated with the received image to create a filtered information set; collecting a plurality of images from the filtered information set to create a seed data set; comparing the received image to the plurality of images from the seed data set using the searchable image data; and determining whether one of the plurality of images is related to the received image.

Abstract: A method and system of recommending content and targeting advertisements for one or more users is provided. The system includes an aggregator that is connected to the one or more users and collects rich user data therefrom. The method includes collecting rich user data from one or more users; building one or more user profiles corresponding to the one or more users; storing the one or more user profiles in a memory database; requesting one or more content profiles from one or more providers; receiving the one or more content profiles; determining whether one of the user profiles is a target user profile for one of the content profiles based on the rich user data associated with the target user profile; and delivering content programs associated with the content profiles to the target user.

Abstract: A methodology to protect private data when a user wishes to publicly release some data about himself, which is can be correlated with his private data. Specifically, the method and apparatus teach comparing public data with survey data having public data and associated private data. A joint probability distribution is performed to predict a private data wherein said prediction has a certain probability. At least one of said public data is altered or deleted in response to said probability exceeding a predetermined threshold.