Abstract: A modular medical dressing includes a layered dressing arrangement having a dressing layer with a first surface and a second surface, a release layer releasably adhered to the first surface, and a backing layer releasably adhered to the second surface. The modular medical dressing further includes a pre-defined tearable portion formed on the layered dressing arrangement. The pre-defined tearable portion is tearable from the layered dressing arrangement to reduce a surface area of the layered dressing arrangement. The pre-defined tearable portion may have a plurality of first tear lines connected to define a first tearable portion. At least a portion of the release layer is configured for use as securement tape for securing a catheter to an anatomical structure.

Abstract: Insertion of supplemental content into a virtual environment is automated using a machine learning model. The machine learning model is trained to calculate a confidence value that a candidate virtual object fits into a virtual environment based on an input that includes a candidate virtual object, a list of persistent virtual objects, and a list of temporary virtual objects. The machine learning model is trained using the persistent and temporary objects displayed in the current virtual environment until it predicts that a selected virtual object fits into the current virtual environment. The trained machine learning model is then used to select a virtual object comprising supplemental content to be inserted as a new virtual object in the virtual environment.

Abstract: Some aspects of the technology described herein perform identity identification on faces in a video. Object tracking is performed on detected faces in frames of a video to generate tracklets. Each tracklet comprises a sequence of consecutive frames in which each frame includes a detected face for a person. The tracklets are clustered using face feature vectors for detected faces of each tracklet to generate a plurality of clusters. Information is stored in an identity datastore, including a first identifier for a first identity in association with an indication of frames from tracklets in a first cluster from the plurality of clusters.

Abstract: Techniques are disclosed for detecting adversarial attacks. A machine learning (ML) system processes the input into and output of a ML model using an adversarial detection module that does not include a direct external interface. The adversarial detection module includes a detection model that generates a score indicative of whether the input is adversarial using, e.g., a neural fingerprinting technique or a comparison of features extracted by a surrogate ML model to an expected feature distribution for the output of the ML model. In turn, the adversarial score is compared to a predefined threshold for raising an adversarial flag. Appropriate remedial measures, such as notifying a user, may be taken when the adversarial score satisfies the threshold and raises the adversarial flag.

Abstract: The current disclosure relates to systems and methods for wakeword or keyword detection in Virtual Personal Assistants (VPAs). In particular, systems and methods are provided for wakeword detection using deep neural networks including a parametric pooling layer, wherein the parametric pooling layer includes trainable parameters, enabling the layer to learn to distinguish between informative feature vectors and non-informative/noisy feature vectors extracted from a variable length acoustic signal. In one example, a parametric pooling layer may aggregate a variable length feature map, comprising a plurality of feature vectors extracted from an acoustic signal, into an embedding vector of pre-determined length, by weighting each of the plurality of feature vectors based on one or more learned parameters in a parametric pooling layer, and aggregating the plurality of weighted feature vectors into the embedding vector.

Abstract: Technology is disclosed herein for enhanced similarity search. In an implementation, a search environment includes one or more computing hardware, software, and/or firmware components in support of enhanced similarity search. The one or more components identify a modality for a similarity search with respect to a query object. The components generate an embedding for the query object based on the modality and based on connections between the query object and neighboring nodes in a graph.

Abstract: Technology is disclosed herein for enhanced similarity search. In an implementation, a search environment includes one or more computing hardware, software, and/or firmware components in support of enhanced similarity search. The one or more components identify a modality for a similarity search with respect to a query object. The components generate an embedding for the query object based on the modality and based on connections between the query object and neighboring nodes in a graph. The embedding for the query object provides the basis for the search for similar objects.

Abstract: Technology is disclosed herein for enhanced similarity search. In an implementation, a search environment includes one or more computing hardware, software, and/or firmware components in support of enhanced similarity search. The one or more components identify a modality for a similarity search with respect to a query object. The components generate an embedding for the query object based on the modality and based on connections between the query object and neighboring nodes in a graph.

Abstract: Methods and systems are provided for managing streaming media content from a content provider in a vehicle infotainment system by predicting an upcoming region of degraded data communication, adjusting a size of a media content buffer in response to the upcoming region of degraded data communication, and playing the buffered media content during an interrupted communication with the content provider. In this way, a probability of media content streaming interruption/latency may be reduced.

Abstract: A device may obtain, from a collection of data sources, personal information and activity information for a group of individuals. The device may generate profile information by associating the personal information and the activity information for each individual in the group of individuals. The device may determine a set of features capable of being used to train a set of machine learning models by using one or more feature identification techniques to analyze the profile information. The set of features may include generic features and contextualized features associated with the group of individuals. The device may train the set of machine learning models using one or more subsets of features of the set of features. The device may use the set of machine learning models to process a request from a client device for a list of prospective targets for a campaign.

Abstract: Techniques are disclosed for detecting adversarial attacks. A machine learning (ML) system processes the input into and output of a ML model using an adversarial detection module that does not include a direct external interface. The adversarial detection module includes a detection model that generates a score indicative of whether the input is adversarial using, e.g., a neural fingerprinting technique or a comparison of features extracted by a surrogate ML model to an expected feature distribution for the output of the ML model. In turn, the adversarial score is compared to a predefined threshold for raising an adversarial flag. Appropriate remedial measures, such as notifying a user, may be taken when the adversarial score satisfies the threshold and raises the adversarial flag.

Abstract: In one aspect, a color plenoptic imaging system captures a plenoptic image of an object. The plenoptic image is made up of a plurality of superpixels, and each superpixel includes a center subpixel. The collection of center subpixels from the plurality of superpixels forms a set of captured center view data for the object. The sensor array includes at least two arrays of different color sensors that capture subpixels of different colors. The microlens array and the sensor array are positioned such that, within the set of captured center view data, for each of the different colors, adjacent center subpixels of that color are separated by not more than three intervening center subpixels of a different color.

Abstract: In one aspect, a color plenoptic imaging system captures a plenoptic image of an object. The plenoptic image is made up of a plurality of superpixels, and each superpixel includes a center subpixel. The collection of center subpixels from the plurality of superpixels forms a set of captured center view data for the object. The sensor array includes at least two arrays of different color sensors that capture subpixels of different colors. The microlens array and the sensor array are positioned such that, within the set of captured center view data, for each of the different colors, adjacent center subpixels of that color are separated by not more than three intervening center subpixels of a different color.

Abstract: A device may obtain, from a collection of data sources, personal information and activity information for a group of individuals. The device may generate profile information by associating the personal information and the activity information for each individual in the group of individuals. The device may determine a set of features capable of being used to train a set of machine learning models by using one or more feature identification techniques to analyze the profile information. The set of features may include generic features and contextualized features associated with the group of individuals. The device may train the set of machine learning models using one or more subsets of features of the set of features. The device may use the set of machine learning models to process a request from a client device for a list of prospective targets for a campaign.

Abstract: In one aspect, a plenoptic imaging system includes imaging optics, a microlens array and a sensor array. A method for color correction of views captured by the plenoptic imaging system includes the following. A plenoptic image of an object captured by the plenoptic imaging system is accessed. The plenoptic image includes many superpixels. Each superpixel includes many subpixels corresponding to different views of the object. The subpixels are of at least two different colors. An initial color view of the object is generated from the plenoptic image. The initial color view includes color pixels. Pixel-wise color correction factors are applied to the color pixels in the initial color view, thereby generating a corrected color view. The pixel-wise color correction factors are determined based on an initial color view generated for a calibration object of known color, as captured by the plenoptic imaging system.

Abstract: In one aspect, a color plenoptic imaging system captures a plenoptic image of an object. The plenoptic image is made up of a plurality of superpixels, and each superpixel includes a center subpixel. The collection of center subpixels from the plurality of superpixels forms a set of captured center view data for the object. The sensor array includes at least two arrays of different color sensors that capture subpixels of different colors. The microlens array and the sensor array are positioned such that, within the set of captured center view data, for each of the different colors, adjacent center subpixels of that color are separated by not more than three intervening center subpixels of a different color.

Abstract: In one aspect, a plenoptic imaging system includes imaging optics, a microlens array and a sensor array. A method for color correction of views captured by the plenoptic imaging system includes the following. A plenoptic image of an object captured by the plenoptic imaging system is accessed. The plenoptic image includes many superpixels. Each superpixel includes many subpixels corresponding to different views of the object. The subpixels are of at least two different colors. An initial color view of the object is generated from the plenoptic image. The initial color view includes color pixels. Pixel-wise color correction factors are applied to the color pixels in the initial color view, thereby generating a corrected color view. The pixel-wise color correction factors are determined based on an initial color view generated for a calibration object of known color, as captured by the plenoptic imaging system.

Abstract: A color preview image is generated, preferably in real-time, for a plenoptic imaging system. The raw plenoptic image has a structure containing superpixels and also contains different color channels. For a principal color channel, a center view is generated by determining the pixel value for a center view of the superpixel, i.e. at the centroid of the superpixel. For each of the other color channels, the ratio of that color channel to the principal color channel is calculated for each superpixel. A center view for each non-principal color channel is determined by multiplying the color ratios times the pixel values for the principal color center view. These center views for the principal and non-principal color channels are combined into a color preview image. The calculations preferably can be performed in real-time at video rates.

Abstract: A color preview image is generated, preferably in real-time, for a plenoptic imaging system. The raw plenoptic image has a structure containing superpixels and also contains different color channels. For a principal color channel, a center view is generated by determining the pixel value for a center view of the superpixel, i.e. at the centroid of the superpixel. For each of the other color channels, the ratio of that color channel to the principal color channel is calculated for each superpixel. A center view for each non-principal color channel is determined by multiplying the color ratios times the pixel values for the principal color center view. These center views for the principal and non-principal color channels are combined into a color preview image. The calculations preferably can be performed in real-time at video rates.

Abstract: A method is described of image processing in which three input images are filtered to generate a temporal median filtered image, each of the three input images representing a same scene and captured under different lighting conditions relative to each other. A shadow present in one or more of the three input images is identified and removed from the temporal median filtered image to generate an output image.