A system and method are provided for performing operations comprising: receiving one or more images from an image capture device of a medical treatment location; applying a trained machine learning model to the one or more images to detect presence of a patient in the medical treatment location, the trained machine learning model being trained to establish a relationship between one or more features of images of the medical treatment location and patient presence; generating context assessment for the medical treatment location based on the detected presence of the patient; and transmitting, over a network, the context assessment for presentation on a user interface of a client device.

Systems and methods for generating assessments based on construction site images are provided. For example, image data captured from a construction site using at least one image sensor may be obtained. Further, at least one electronic record associated with the construction site may be obtained. The image data and the at least one electronic record may be analyzed to generate at least one assessment related to the construction site. For example, the image data may be analyzed to identify at least one discrepancy between the at least one electronic record and the construction site, and the identified at least one discrepancy may be used in the generation of the at least one assessment.

A map file includes two-dimensional or three-dimensional geometric data items collectively representing layout of a building. The map file is parsed and the geometric data items are analyzed to identify building elements including rooms, floors, and objects of the building, and to identify containment relationships between the elements. A space model having a space graph is constructed. The space graph includes nodes that correspond to the respective building elements and links forming relationships between nodes that correspond to the identified containment relationships. Each node may include node metadata, rules or code that operate on the metadata, and a node type that corresponds to a type of physical space. Some nodes may include user representations or device representations that represent physical sensors associated therewith. The representations may receive data from the respectively represented sensors, and the sensor data becomes available via the space model.

Provided are systems and methods for personalized videos featuring multiple persons. An example method includes receiving a user selection of a video having at least one frame with metadata that include a first location and a second location and receiving an image of a source face and a further image of a further source face, modifying the image of the source face to generate an image of a modified source face and modifying the further image of the further source face to generate an image of a modified further source face, inserting, in the at least one frame of the video, the image of the modified source face at the first location and the image of the modified further source face at the second location to generate a personalized video, and sending the personalized video via a communication chat.

Provided are an image processing apparatus and an image processing method that enable a strobe image using a 3D model to be generated. A strobe model in which 3D models of an object at a plurality of times generated from a plurality of viewpoint images captured from a plurality of viewpoints are disposed in a three-dimensional space is generated. When the strobe model is generated, a target object that is a target in which the 3D model is disposed in the strobe model is set according to a degree of object relevance indicating relevance with a key object serving as a reference for disposition of the 3D model in the strobe model.

A computer-implemented method for designing a 3D modeled object via user-interaction. The method includes obtaining the 3D modeled object and a machine-learnt decoder. The machine-learnt decoder is a differentiable function taking values in a latent space and outputting values in a 3D modeled object space. The method further includes defining a deformation constraint for a part of the 3D modeled object. The method further comprises determining an optimal vector. The optimal vector minimizes an energy. The energy explores latent vectors. The energy comprises a term which penalizes, for each explored latent vector, non-respect of the deformation constraint by the result of applying the decoder to the explored latent vector. The method further includes applying the decoder to the optimal latent vector. This constitutes an improved method for designing a 3D modeled object via user-interaction.

A method includes displaying a first graphical representation on a screen. The first graphical representation includes a box-and-whisker plot of a dataset. The method also includes receiving a first interaction indication indicating a graphical user interaction by a user at a first interaction location on the first graphical representation. In response to the received first interactive indication, the method includes displaying a second graphical representation on the screen based on the first interaction indication, the second graphical representation including a density plot of the dataset having a respective scale equal to a corresponding scale of the box-and-whisker plot. The method also includes receiving a second interaction indication indicating the graphical user interaction by the user at a second interaction location on the second graphical representation, and in response, displaying an updated second graphical representation of the dataset on the screen based on the second interaction indication.

Methods for improving compliance with regulations pertaining to vehicle driving records are disclosed. One or more digital images from a camera mounted in a vehicle are received. Based on a determination that the vehicle has hours of service that have not been assigned to a driver, a subset of the one or more digital images corresponding to the hours of service are identified based on the timestamps. The subset of the one or more digital images are processed to identify a correspondence between a face of a person included in the one or more digital images and a face of a known person. Based on the correspondence transgressing a threshold level of correspondence, a user interface is generated for presentation on a device. The user interface includes an interactive user interface element for accepting a recommendation to assign the known person as the driver for the unassigned hours of service.

The present invention relates to a device and a control method therefor and, more specifically, the device comprises: a memory for storing at least one command; a depth camera for capturing at least one hand of a user; a display module; and a controller for controlling the memory, the depth camera, and the display module. The controller controls the depth camera so as to capture the at least one hand of a user and controls the display module so as to output a visual feedback that changes on the basis of the captured hand of a user.

Disclosed are a system, method, and computer program product for generating pruned tractograms of neural fiber bundles. The method includes receiving scan data produced by diffusion imaging of at least a portion of a brain from a magnetic-resonance imaging (MRI) device. The method also includes generating an initial tractogram by mapping neuronal fiber pathways of a target fiber bundle of the scan data. The method further includes generating a density map using a set of tracts from the initial tractogram, identifying each tract that passes through a segment of the density map more than once, and setting a contribution of said tract to a unique tract count of the segment equal to a threshold pruning value. The method further includes generating a pruned tractogram by identifying a segment having a unique tract count less than or equal to the threshold pruning value and excluding the segment from the pruned tractogram.