An artificial intelligence (AI) system may be configured to efficiently annotate most if not all unlabeled image data. Some embodiments may: provide, to an object-detection, machine-learning (ML) model, a plurality of unlabeled data such that the object-detection model predicts a plurality of regions; correct at least one vertex of bounds of at least one of the regions such that the bounds fit tighter around an object; convert the regions to first subregions by cropping the first subregions from the unlabeled data; and provide the first subregions to an embedding, ML model configured to output feature vectors for each of the first subregions.

This disclosure relates to an apparatus for object detection. The apparatus comprises a video camera, an object detector, and a controller. The video camera may be configured to generate a video stream of frames. The object detector may be configured to accept the video stream as input data and to perform object detection. The controller may be coupled to the video camera and the object detector. The controller may be configured to manage object detection in order to satisfy a performance metric and/or operate within an operational constraint.

A method for detecting anomalies in a system. The method includes collecting training data from the system, converting the training data into training images using an image generator, and designating each of the training images as corresponding to events for the system, where the events are at least one of an expected normal event and a non-normal event. The method further includes generating an image recognition model based on the training images and the designations thereof. The method further includes collecting new data from the system, converting the new data into input images, and analyzing the input images using the image recognition model to determine which of the events for the system are represented in the input images, where the anomalies are detected when the input images are determined to at least one of represent a non-normal event and fail to represent an expected normal event.

Techniques for machine learning optimization are provided. A video comprising a plurality of segments is received, and a first segment of the plurality of segments is processed with a machine learning (ML) model to generate a plurality of tags, where each of the plurality of tags indicates presence of an element in the first segment. A respective accuracy value is determined for each respective tag of the plurality of tags, where the respective accuracy value is based at least in part on a maturity score for the ML model. The first segment is classified as accurate, based on determining that an aggregate accuracy of tags corresponding to the first segment exceeds a predefined threshold. Upon classifying the first segment as accurate, the first segment is bypassed during a review process.

The present disclosure generally relates to evaluating communication workflows comprised of tasks using machine-learning techniques. More particularly, the present disclosure relates to systems and methods for generating a prediction of a task outcome of a communication workflow, generating a recommendation of one or more tasks to add to a partial communication workflow to complete the communication workflow, and generating a vector representation of a communication workflow.

In an approach for object detection with missing annotations under visual inspection, a processor receives an image. A processor classifies the image being a not-good image using a pre-trained classifier. A not-good image means one or more defect objects being in the image. A processor, in response to classifying the image being the not-good image, detects the one or more defect objects in the not-good image. A processor masks the one or more defect objects in the not-good image. A processor inputs the masked image to train a detector.

Systems and methods for predicting user interaction with vehicles. A computing device receives an image and a video segment of a road scene, the first at least one of an image and a video segment being taken from a perspective of a participant in the road scene and then generates stimulus data based on the image and the video segment. Stimulus data is transmitted to a user interface and response data is received, which includes at least one of an action and a likelihood of the action corresponding to another participant in the road scene. The computing device aggregates a subset of the plurality of response data to form statistical data and a model is created based on the statistical data. The model is applied to another image or video segment and a prediction of user behavior in the another image or video segment is generated.

A computer-implemented method includes preprocessing a variable dimension medical image, identifying one or more areas of interest in the medical image; and analyzing the one or more areas of interest using a deep learning model. A computing system includes one or more processors; and one or more memories storing instructions that, when executed by the one or more processors, cause the computing system to preprocess a variable dimension medical image, identify one or more areas of interest in the medical image; and analyze the one or more areas of interest using a deep learning model. A non-transitory computer readable medium contains program instructions that when executed, cause a computer to preprocess a variable dimension medical image, identify one or more areas of interest in the medical image, and analyze the one or more areas of interest using a deep learning model.

Embodiments of the present application provide a method and apparatus for updating an online self-learning event detection model. The method includes: presenting, when at least one target alerting event generated by the current event detection model is detected, to a user the at least one target alerting event, so that the user provides an event result for each target alerting event based on the at least one presented target alerting event; obtaining the event result for each target alerting event provided by the user based on the at least one presented target alerting event; determining whether a target alerting event for which an event result has been provided by the user satisfies a predetermined update condition, and if so, training and obtaining a target event detection model based on at least one target alerting event for which an event result has been provided by the user and corresponding event result, and predetermined training samples; and replacing the current event detection model with the target event detection model. By means of the method and apparatus according to the present application, the current event detection model may be continually updated, and thus improving the accuracy of the online learning.

Methods and systems for a monitoring system for data collection in an industrial environment including a data collector communicatively coupled to a plurality of input channels connected to data collection points operatively coupled to at least one of an oil production component or gas production component; a data storage structured to store a plurality of diagnostic frequency band ranges for the at least one of an oil production component or gas production component; a data acquisition circuit structured to interpret a plurality of detection values from the plurality of input channels; and a data analysis circuit structured to analyze the plurality of detection values to determine measured frequency band data and compare the measured frequency band data to the plurality of diagnostic frequency band ranges, and to diagnose an operational parameter of the least one of an oil production component or gas production component in response to the comparison.