Various embodiments relate generally to computer vision and automation to autonomously identify and deliver for application a treatment to an object among other objects, data science and data analysis, including machine learning, deep learning, and other disciplines of computer-based artificial intelligence to facilitate identification and treatment of objects, and robotics and mobility technologies to navigate a delivery system, more specifically, to an agricultural delivery system configured to identify and apply, for example, an agricultural treatment to an identified agricultural object. In some examples, a method may include, receiving data representing a policy specifying a type of action for an agricultural object, selecting an emitter with which to perform a type of action for the agricultural object as one of one or more classified subsets, and configuring the agricultural projectile delivery system to activate an emitter to propel an agricultural projectile to intercept the agricultural object.

A method for perception and fitting for a stair tracker includes receiving sensor data for a robot adjacent to a staircase. For each stair of the staircase, the method includes detecting, at a first time step, an edge of a respective stair of the staircase based on the sensor data. The method also includes determining whether the detected edge is a most likely step edge candidate by comparing the detected edge from the first time step to an alternative detected edge at a second time step, the second time step occurring after the first time step. When the detected edge is the most likely step edge candidate, the method includes defining, by the data processing hardware, a height of the respective stair based on sensor data height about the detected edge. The method also includes generating a staircase model including stairs with respective edges at the respective defined heights.

A method for perception and fitting for a stair tracker includes receiving sensor data for a robot adjacent to a staircase. For each stair of the staircase, the method includes detecting, at a first time step, an edge of a respective stair of the staircase based on the sensor data. The method also includes determining whether the detected edge is a most likely step edge candidate by comparing the detected edge from the first time step to an alternative detected edge at a second time step, the second time step occurring after the first time step. When the detected edge is the most likely step edge candidate, the method includes defining, by the data processing hardware, a height of the respective stair based on sensor data height about the detected edge. The method also includes generating a staircase model including stairs with respective edges at the respective defined heights.

Methods and systems are described. A method includes accessing training data samples that includes a plurality of transaction laundering associated features and generating random samples, training a first plurality of different models to identify transaction laundering merchants based on random samples generated from each of the training data samples, training a second plurality of different models to identify the transaction laundering merchants based on the training data, generating a transaction laundering classification for a merchant from each of the first plurality of models and each of the second plurality of models, generating a first model group classification based on a first majority vote on transaction laundering classifications from the first plurality of models, and generating a second model group classification based on a second majority vote on transaction laundering classifications from the second plurality of models. A likelihood that the merchant is a transaction launderer is determined.

Embodiments of the present disclosure provide a method, device and computer program product for backing up data. The method comprises obtaining a data attribute of specific data to be backed up from a client to a server, a resource utilization rate at the client, and a network condition between the client and the server. The method further comprises setting, based on the data attribute, the resource utilization rate and the network condition, a plurality of parameters for performing stream backup, wherein the plurality of parameters at least comprises a concurrent number of stream transmission and a concurrent number of data parsing. The method further comprises parsing, according to the set plurality of parameters, the specific data and backing up the specific data from the client to the server.

A virtual content creation method according to an embodiment of the present invention includes, by a server, receiving a model content including at least one of a text, an SMS, a voice-recorded MP3 file, a picture, and a video of a model; by the server, extracting a model feature including at least one of a text feature, a voice feature, an image feature, and a video feature from the model content; and when a user wants to communicate with the model, by the server, being operated based on deep learning or artificial intelligence to allow the user to input a user content to the server, determine a user state by detecting an emotional state of the user from the user content, and transform the model content into the virtual content using the model feature or the user state.

A virtual content creation method according to an embodiment of the present invention includes, by a server, receiving a model content including at least one of a text, an SMS, a voice-recorded MP3 file, a picture, and a video of a model; by the server, extracting a model feature including at least one of a text feature, a voice feature, an image feature, and a video feature from the model content; and when a user wants to communicate with the model, by the server, being operated based on deep learning or artificial intelligence to allow the user to input a user content to the server, determine a user state by detecting an emotional state of the user from the user content, and transform the model content into the virtual content using the model feature or the user state.

This disclosure provides for methods and system for meta few-shot class incremental learning. According to an aspect a method is provided. The method includes obtaining at least one weight attention map of a first network and updating weights of a second network using the at least one weight attention map, where the second network is a modulatory network. The method further includes generating at least one feature attention map of the second network based on the at least one weight attention map of the first network and a set of input images of at least one class. The method further includes generating at least one feature map of the first network based on the set of input images of the at least one class, and updating the at least one feature map of the first network based on the feature attention map of the second network.

This disclosure provides for methods and system for meta few-shot class incremental learning. According to an aspect a method is provided. The method includes obtaining at least one weight attention map of a first network and updating weights of a second network using the at least one weight attention map, where the second network is a modulatory network. The method further includes generating at least one feature attention map of the second network based on the at least one weight attention map of the first network and a set of input images of at least one class. The method further includes generating at least one feature map of the first network based on the set of input images of the at least one class, and updating the at least one feature map of the first network based on the feature attention map of the second network.

A computer-implemented method includes: receiving, by a computing device, sensor data associated with a geographic location; processing, by the computing device, the sensor data to identify an infrastructure asset within the geographic location; determining, by the computing device, a condition of the infrastructure asset based on processing the sensor data; and storing or outputting, by the computing device, information regarding the condition of the infrastructure asset.