Abstract: Multiple predictions about the position of an object during a time period may each indicate the position of the object at a respective time during the time period. Respective validity indications corresponding to the multiple predictions may each indicate an accuracy of the corresponding prediction. Whether a change has occurred in a distribution of the predictions from a first subset of predictions to a second subset of predictions during the time period may be determined. If the change has occurred, a prediction from the first subset of predictions or the second subset of predictions may be selected, based on the validity of the predictions and/or the detection of a motion, as a best indication of the position of the object.

Abstract: Detecting motions associated with a body part of a patient may include using an image sensor installed inside a medical scanner to capture first and second images of the patient inside the medical scanner, wherein the first image may depict the patient in a first state and the second image may depict the patient in a second state. A first area, in the first image, that corresponds to the body part of the patient may be identified and a second area, in the second image, that corresponds to the body part may also be identified so that a first plurality of features may be extracted from the first area of the first image and a second plurality of features may be extracted from the second area of the second image. A motion associated with the body part of the patient may be determined based on the first and second pluralities of features.

Abstract: A person's privacy is protected by the law in many settings and disclosed herein are systems, methods, and instrumentalities associated with anonymizing an image of a person while still preserving the visual saliency and/or utility of the image for one or more downstream tasks. These objectives may be accomplished using various machine-learning (ML) techniques such as ML models trained for extracting identifying and residual features from the input image as well as ML models trained for transforming the identifying features into identity-concealing features and for preserving the utility features of the image. An output image may be generated based on the various ML models, wherein the identity of the person may be substantially disguised in the output image while the background and utility attributes of the original image may be substantially maintained in the output image.

Abstract: Described herein are systems, methods, and instrumentalities associated with estimating the motions of multiple 3D points in a scene and predicting a view of scene based on the estimated motions. The tasks may be accomplished using one or more machine-learning (ML) models. A first ML model may be used to predict motion-embedding features for a temporal state of a scene, based on motion-embedding features for previous states. A second ML model may be used to predict a motion field representing displacement or deformation of the multiple 3D points from a source time to a target time. Then, a third ML model may be used to predict respective image properties of the 3D points based on their updated locations at the target time and/or a viewing direction. An image of the scene at the target time may then be generated based on the predicted image properties of the 3D points.

Abstract: The physical characteristics of one or more anatomical structures of a person may change in accordance with conditions surrounding the determination of such physical characteristics. Machine learning based techniques may be used to determine a template representation of the one or more anatomical structures that may indicate the physical characteristics of the one or more anatomical structures free of the impact imposed by changing conditions. The template representation may then be used to predict the physical characteristics of the one or more anatomical structures under a new set of conditions, without subjecting the person to additional medical scans.

Abstract: The decision process of a first machine learning (ML) model may be explained based on a second ML model implemented on an apparatus. The apparatus may obtain a prediction about an image made based on the first ML model. The apparatus may further determine visual concepts associated with the image that may have been used by the first ML model to make the prediction, and determine respective contributions of the visual concepts to the prediction made by the first ML model. The apparatus may then generate, based on the second ML model, a textual description that explains the respective contributions of the visual concepts to the prediction made by the first ML model. The second ML model may determine respective image features associated with the visual concepts, map the determined image features to corresponding text features, and generate the textual description based at least on the text features.

Abstract: The 3D pose of a person may be estimated by triangulating 2D representations of body keypoints (e.g., joint locations) of the person. The triangulation may leverage various metrics such as confidence scores associated with the 2D representations of a keypoint and/or temporal consistency between multiple 3D representations of the keypoint. The 2D representations may be arranged into groups, a candidate 3D representation may be determined for each group, taking into account of the confidence score of each 2D representation in the group, and the candidate 3D representation that has the smallest error may be used to represent the keypoint. Other 3D representation(s) of the keypoint determined from images taken at different times may be used to refine the 3D representation of the keypoint.

Abstract: The decision process of a first machine learning (ML) model may be explained based on a second ML model implemented on an apparatus. The apparatus may obtain a prediction about an image made based on the first ML model. The apparatus may further determine visual concepts associated with the image that may have been used by the first ML model to make the prediction, and determine respective contributions of the visual concepts to the prediction made by the first ML model. The apparatus may then generate, based on the second ML model, a textual description that explains the respective contributions of the visual concepts to the prediction made by the first ML model. The second ML model may determine respective image features associated with the visual concepts, map the determined image features to corresponding text features, and generate the textual description based at least on the text features.

Abstract: A method and a system for managing healthcare records of a user are provided. The method includes storing an electronic medical record related to the user in form of a non-fungible token (NFT) written to a blockchain, associating a smart contract to the NFT in the blockchain, authorizing a request to access the electronic medical record related to the user based on the defined ownership of the electronic medical record stored in the blockchain, identifying one or more NFTs from the blockchain comprising one or more electronic medical records related to the user based on processing of the identifier information in associated one or more smart contracts therewith, in response to the request, and sending the one or more electronic medical records corresponding to the identified one or more NFTs to a requestor associated with the request.

Abstract: A system for visual inspection of signal lights at a railroad crossing includes a data source comprising a stream of images, the stream of images including images of signal lights at a railroad crossing, an inspection module configured via computer executable instructions to receive the stream of images, detect signal lights and light instances in the stream of images, encode global information relevant to ambient luminosity and return a first feature vector, encode patch information of luminosity of detected signal lights and return a second feature vector, concatenate the first feature vector with the second feature vector and return a concatenated feature vector, and decode the concatenated feature vector and provide status of the signal lights.

Abstract: An apparatus in accordance with embodiments of the present disclosure may obtain an image depicting one or more hands of a person in a medical environment; and detect, using a first machine learning (ML) model, a plurality of 2D landmarks associated with a hand of the person depicted in the image. The apparatus may further determine, using a second ML model, 3D features of the hand of the person based on the plurality of 2D landmarks. The apparatus may determine a gesture indicated by the hand of the person based on the 3D features of the hand predicted using the second ML model. Alternatively, in determining the 3D features of the hand, the system may stack the plurality of 2D landmarks across a sequence of image frames in a video, and use a third ML model to determine the 3D features of the hand based on the stacked 2D landmarks.

Abstract: A prediction regarding respective areas of an image that correspond to bodies of people depicted in the image and regarding an area of the image that corresponds to a body part may be made based on a machine learning (ML) model. A vector that points from the area of the image that corresponds to the body part to another area of the image may also be obtained based on the ML model. An association between the body part and one of the depicted people may be determined based at least on the vector and the respective areas of the image that correspond to the bodies of the people depicted in the image. Determining the association between the body part and the one of the people may include determining that the area of the image to which the vector points corresponds to the body of the one of the people.

Abstract: It is recognized herein that deep-learning approaches to anomaly detection can require a large amount of training data to properly learn the task. It is further recognized herein that capturing images of anomalies can be particularly costly or impractical or, in some cases, impossible. For example, by definition, anomalies can be rare and, therefore, gathering enough samples to train a convolutional neural network can be tedious. Annotating anomalies that are depicted can also be an expensive and time-consuming task. In various examples, realistic synthetic images are generated that include plausible and annotated surface defects (anomalies). Such synthetic images are used to train an efficient anomaly segmentation network in a fully supervised manner.

Abstract: Multiple predictions about the position of an object during a time period may each indicate the position of the object at a respective time during the time period. Respective validity indications corresponding to the multiple predictions may each indicate an accuracy of the corresponding prediction. Whether a change has occurred in a distribution of the predictions from a first subset of predictions to a second subset of predictions during the time period may be determined. If the change has occurred, a prediction from the first subset of predictions or the second subset of predictions may be selected, based on the validity of the predictions and/or the detection of a motion, as a best indication of the position of the object.

Abstract: Described herein are machine learning (ML) based on systems, methods, and instrumentalities associated with image search and/or retrieval. An apparatus as described herein may obtain a query image and a textual description associated with the query image, and generate, using an artificial neural network (ANN), a feature representation that may represent the image and the textual description as an associated pair. Based on the feature representation, the apparatus may identify one or more images from an image repository and provide an indication regarding the one or more identified images, for example, as a ranked list.

Abstract: Disclosed herein are systems, methods and instrumentalities associated with multi-view 3D human model estimation using machine learning (ML) based techniques. These techniques may use synthetically generated data to train an ML model that may be used to progressively regress a 3D human body model based on multi-view 2D images. The training data may be synthetically generated based on statistical distributions of human poses and human body shapes, as well as a statistical distribution of camera viewpoints. The progressive regression may be performed based on consensus features shared by the multi-view images and diversity features derived from at least one of the multi-view images. Consistency between the multi-view images may also be maintained during the regression process.

Abstract: The physical characteristics of one or more anatomical structures of a person may change in accordance with conditions surrounding the determination of such physical characteristics. Machine learning based techniques may be used to determine a template representation of the one or more anatomical structures that may indicate the physical characteristics of the one or more anatomical structures free of the impact imposed by changing conditions. The template representation may then be used to predict the physical characteristics of the one or more anatomical structures under a new set of conditions, without subjecting the person to additional medical scans.

Abstract: Detecting motions associated with a body part of a patient may include using an image sensor installed inside a medical scanner to capture first and second images of the patient inside the medical scanner, wherein the first image may depict the patient in a first state and the second image may depict the patient in a second state. A first area, in the first image, that corresponds to the body part of the patient may be identified and a second area, in the second image, that corresponds to the body part may also be identified so that a first plurality of features may be extracted from the first area of the first image and a second plurality of features may be extracted from the second area of the second image. A motion associated with the body part of the patient may be determined based on the first and second pluralities of features.

Abstract: Disclosed herein are systems, methods and instrumentalities associated with multi-person joint location and pose estimation based on an image that depicts multiple people in a scene, where at least some of the joint locations of a person may be blocked or obstructed by other people or objects in the scene. The estimation may be performed by detecting and grouping joint locations in the image using a bottom-up approach, and refining each group of detected joint locations by recovering obstructed joint location(s) that may be missing from the group. The detection, grouping, and/or refinement may be accomplished based on one or more machine learning (ML) models that may be implemented using artificial neural networks such as convolutional neural networks.

Abstract: A system for visual inspection of signal lights at a railroad crossing includes a data source comprising a stream of images, the stream of images including images of signal lights at a railroad crossing, an inspection module configured via computer executable instructions to receive the stream of images, detect signal lights and light instances in the stream of images, encode global information relevant to ambient luminosity and return a first feature vector, encode patch information of luminosity of detected signal lights and return a second feature vector, concatenate the first feature vector with the second feature vector and return a concatenated feature vector, and decode the concatenated feature vector and provide status of the signal lights.