Disclosed herein are an apparatus and method for classifying clothing attributes based on deep learning. The apparatus includes memory for storing at least one program and a processor for executing the program, wherein the program includes a first classification unit for outputting a first classification result for one or more attributes of clothing worn by a person included in an input image, a mask generation unit for outputting a mask tensor in which multiple mask layers respectively corresponding to principal part regions obtained by segmenting a body of the person included in the input image are stacked, a second classification unit for outputting a second classification result for the one or more attributes of the clothing by applying the mask tensor, and a final classification unit for determining and outputting a final classification result for the input image based on the first classification result and the second classification result.

Systems and methods for self-supervised representation learning as a means to generate context-specific pretrained models include selecting data from a set of available data sets; selecting a pretext task from domain specific pretext tasks; selecting a target problem specific network architecture based on a user selection from available choices or any customized model as per user preference; and generating a pretrained model for the selected network architecture using the selected data obtained from the set of available data sets and a pretext task as obtained from domain specific pretext tasks.

Described are a system, method, and computer program product for segmenting a plurality of accounts. The method includes processing transaction data for a plurality of transactions conducted by a plurality of accounts using a plurality of account identifiers, the transaction data for each transaction including data identifying the transaction as an electronic transaction or a physical transaction, segmenting the plurality of accounts into at least two groups including an active customer group and an inactive customer group based on the transaction data for each transaction conducted by each of the plurality of accounts, determining a third subset of customers from the second subset of customers based on at least one predicative model and a transaction profile of each customer of the second subset of customers, and automatically enrolling the third subset of customers into an automated campaign.

Systems, methods, and computer readable media for messaging system with augmented reality (AR) makeup are presented. Methods include processing a first image to extract a makeup portion of the first image, the makeup portion representing the makeup from the first image and training a neural network to process images of people to add AR makeup representing the makeup from the first image. The methods may further include receiving, via a messaging application implemented by one or more processors of a user device, input that indicates a selection to add the AR makeup to a second image of a second person. The methods may further include processing the second image with the neural network to add the AR makeup to the second image and causing the second image with the AR makeup to be displayed on a display device of the user device.

Systems and methods for managing Application Programming Interfaces (APIs) are disclosed. Systems may involve automatically generating a honeypot. For example, the system may include one or more memory units storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving, from a client device, a call to an API node and classifying the call as unauthorized. The operation may include sending the call to a node-imitating model associated with the API node and receiving, from the node-imitating model, synthetic node output data. The operations may include sending a notification based on the synthetic node output data to the client device.

A method for generating a predictive model for quantization parameters of a neural network is described. The method comprises accessing a first vector of data values corresponding to input values to a first layer implemented in a neural network, generating a feature vector of one or more features extracted from the data values of the first vector, accessing a second vector of data values corresponding to the input values of a second layer implemented in the neural network, subsequent to the first layer, generating a target vector of data values comprising one or more quantization parameters for the second layer, from the data values of the second vector, evaluating, on the basis of the feature vector and the target vector, a predictive model for predicting the one or more quantization parameters of the second layer and modifying the predictive model on the basis of the evaluation.

Videos captured in low light conditions can be processed in order to identify an activity being performed in the video. The processing may use both the video and audio streams for identifying the activity in the low light video. The video portion is processed to generate a darkness-aware feature which may be used to modulate the features generated from the audio and video features. The audio features may be used to generate a video attention feature and the video features may be used to generate an audio attention feature. The audio and video attention features may also be used in modulating the audio video features. The modulated audio and video features may be used to predict an activity occurring in the video.

A network quantization method is a network quantization method of quantizing a neural network, and includes a database construction step of constructing a statistical information database on tensors that are handled by neural network, a parameter generation step of generating quantized parameter sets by quantizing values included in each tensor in accordance with the statistical information database and the neural network, and a network construction step of constructing a quantized network by quantizing the neural network with use of the quantized parameter sets. The parameter generation step includes a quantization-type determination step of determining a quantization type for each of a plurality of layers that make up the neural network.

A method is provided for generating a visualization for explaining a behavior of a machine learning (ML) model. In the method, an image is input to the ML model for an inference operation. The input image has an increased resolution compared to an image resolution the ML model was intended to receive as an input. A resolution of a plurality of resolution-independent convolutional layers of the neural network are adjusted because of the increased resolution of the input image. A resolution-independent convolutional layer of the neural network is selected. The selected resolution-independent convolutional layer is used to generate a plurality of activation maps. The plurality of activation maps is used in a visualization method to show what features of the image were important for the ML model to derive an inference conclusion. The method may be implemented in a computer program having instructions executable by a processor.

Provided are an audio reconstruction method and device for providing improved sound quality by reconstructing a decoding parameter or an audio signal obtained from a bitstream, by using machine learning. The audio reconstruction method includes obtaining a plurality of decoding parameters of a current frame by decoding a bitstream, determining characteristics of a second parameter included in the plurality of decoding parameters and associated with a first parameter, based on the first parameter included in the plurality of decoding parameters, obtaining a reconstructed second parameter by applying a machine learning model to at least one of the plurality of decoding parameters, the second parameter, and the characteristics of the second parameter, and decoding an audio signal, based on the reconstructed second parameter.