There is described a computer-implemented method and system for classifying images, the computer-implemented method comprising: receiving an image to be classified, generating a vector representation of the image to be classified using an image embedding method, comparing the vector representation of the image to predefined vector representations of the predefined image categories, and identifying a relevant category amongst the predefined image categories based on the comparison, the relevant category being associated with the image to be classified and outputting the relevant category.

Systems and methods of the present disclosure enable movement recognition and tracking by receiving movement measurements associated with movements of a user. The movement measurements are converted into feature values. An action recognition machine learning model having trained action recognition parameters generates, based on the feature values, an action label representing an action performed during an action-related interval. An activity recognition machine learning model having trained activity recognition parameters generates, based on the action label, an activity label representing an activity performed during an activity-related interval, where the activity includes the action. A task recognition machine learning model having trained task recognition parameters generates, based on the action label and the activity label, a task label representing a task performed during a task-related interval, where the task includes the activity and action. An activity log is updated based on the action label, the activity label, and the task label.

Systems and methods of the present disclosure enable movement recognition and tracking by receiving movement measurements associated with movements of a user. The movement measurements are converted into feature values. An action recognition machine learning model having trained action recognition parameters generates, based on the feature values, an action label representing an action performed during an action-related interval. An activity recognition machine learning model having trained activity recognition parameters generates, based on the action label, an activity label representing an activity performed during an activity-related interval, where the activity includes the action. A task recognition machine learning model having trained task recognition parameters generates, based on the action label and the activity label, a task label representing a task performed during a task-related interval, where the task includes the activity and action. An activity log is updated based on the action label, the activity label, and the task label.

A system, a method and a non-transitory computer readable storage medium for base calling are described. The base calling method includes processing through a neural network first image data comprising images of clusters and their surrounding background captured by a sequencing system for one or more sequencing cycles of a sequencing run. The base calling method further includes producing a base call for one or more of the clusters of the one or more sequencing cycles of the sequencing run.

A method of secure classification of input data by a convolutional neural network (CNN), including (a) determination, by application of the CNN to the input data, of a first classification vector associating with each of a plurality of potential classes a representative integer score of the probability of the input data belonging to the potential class, the first vector corresponding to one possible vector, each possible vector of the first set associating with each of the plurality of potential classes an integer score; (b) construction, from the first vector, of a second classification vector of the input data, such that the second vector also belongs to the first space of possible vectors and has a distance with the first vector according to a given distance function equal to a non-zero reference distance; and return of the second vector as result of the secure classification.

Aspects of the present disclosure enable humanly-specified relationships to contribute to a mapping that enables compression of the output structure of a machine-learned model. An exponential model such as a maximum entropy model can leverage a machine-learned embedding and the mapping to produce a classification output. In such fashion, the feature discovery capabilities of machine-learned models (e.g., deep networks) can be synergistically combined with relationships developed based on human understanding of the structural nature of the problem to be solved, thereby enabling compression of model output structures without significant loss of accuracy. These compressed models provide improved applicability to “on device” or other resource-constrained scenarios.

Some embodiments of the present disclosure provide a pneumothorax detection method performed by a computing device. The method may comprise obtaining predicted pneumothorax information, predicted tube information, and a predicted spinal baseline with respect to an input image from a trained pneumothorax prediction model; determining at least one pneumothorax representative position for the predicted pneumothorax information and at least one tube representative position for the predicted tube information, in a prediction image in which the predicted pneumothorax information and the predicted tube information are displayed; dividing the prediction image into a first region and a second region by the predicted spinal baseline; and determining a region in which the at least one pneumothorax representative position and the at least one tube representative position exist among the first region and the second region.

An intelligent robot cleaner setting a travel path based on a video learning includes a travel driver, a suction unit, an image acquisition unit, and a controller. The travel driver moves to an area to be cleaned along the travel path. The suction unit sucks foreign substances on the travel path. The image acquisition unit acquires an image on the travel path. The controller analyzes the image, decides whether an object is present on the travel path, classifies a type of the object, and sets a bypass travel path that avoids the object if the object is an avoidance object.

A method for multi-target detection and an apparatus for multi-target detection are capable of detecting at least two targets in real time or near real time. The real-time detection or near real time detection can be achieved by at least one of a Recipe Group Approach, an End Member Grouping Approach, and a Pixelated Grouping Based Approach.

The disclosure provides a text classification model training method, a text classification method, an apparatus, an electronic device, and a computer-readable storage medium, and relates to artificial intelligence technology. The text classification model training method includes: performing machine translation on a plurality of first text samples in a first language to obtain a plurality of second text samples in a second language different from the first language; training a first text classification model for the second language based on a plurality of third text samples in the second language and corresponding class labels; performing confidence-based filtering on the plurality of second text samples by the trained first text classification model; and training a second text classification model for the second language based on the filtered second text samples.