Abstract: An embodiment generates an initial set of training data from monitoring data. The initial set of training data is generated by combining outputs from a plurality of pretrained classifiers. The embodiment trains a new classification model using the initial set of training data to identify anomalies in monitoring data. The embodiment performs a multiple-level clustering of the data samples resulting in a plurality of clusters of sub-clusters of data samples, and generates a review list of data samples by selecting a representative data sample from each of the clusters. The embodiment receives an updated data sample from the expert review that includes a revised target classification for at least one of the data samples of the expert review list. The embodiment then trains another replacement classification model using a revised set of training data that includes the updated data sample and associated revised target classification.

Abstract: The present invention discloses an enhanced, self-healable or recoverable and recyclable 3D printed article and a preparation method and use thereof. By introducing a functional monomer into a 3D printing system, a self-healable or recoverable 3D printed article is prepared or the interface strength of the 3D printed article is enhanced; or by using at least one monofunctional thermoplastic photosensitive resin monomer as one of 3D printing raw materials, a recyclable 3D printed article is prepared.

Abstract: The general problem of pattern change discovery between high-dimensional data sets is addressed by considering the notion of the principal angles between the subspaces is introduced to measure the subspace difference between two high-dimensional data sets. Current methods either mainly focus on magnitude change detection of low-dimensional data sets or are under supervised frameworks. Principal angles bear a property to isolate subspace change from the magnitude change. To address the challenge of directly computing the principal angles, matrix factorization is used to serve as a statistical framework and develop the principle of the dominant subspace mapping to transfer the principal angle based detection to a matrix factorization problem. Matrix factorization can be naturally embedded into the likelihood ratio test based on the linear models. The method may be unsupervised and addresses the statistical significance of the pattern changes between high-dimensional data sets.

Abstract: A computer vision processor of a camera generates hyperzooms for persons or vehicles from image frames captured by the camera. The hyperzooms include a first hyperzoom associated with the persons or vehicles. The computer vision processor tracks traffic patterns of the persons or vehicles while obviating network usage by the camera by predicting positions of the persons or vehicles using a Kalman Filter from the first hyperzoom. The persons or vehicles are detected in the second hyperzoom. The positions of the persons or vehicles are updated based on detecting the persons or vehicles in the second hyperzoom. The first hyperzoom is removed from the camera. Tracks of the persons or vehicles are generated based on the updated positions. The second hyperzoom is removed from the camera. Track metadata is generated from the tracks for storing in a key-value database located on a non-transitory computer-readable storage medium of the camera.

Abstract: A method for generating cropped images depicting objects captured in video data includes receiving, at a processor of a video camera system, a video stream including a series of video frames depicting an object. A classification for the object is generated, and an occurrence of the object being detected is identified in an additional video frame(s) from the series of video frames. A motion associated with the object is calculated based on the classification and the additional video frame(s). At least one image that depicts the object and includes a cropped portion of a video frame from the series of video frames is generated, along with an associated set of at least one quality score, in response to calculating the motion. The method also includes causing transmission of the at least one image to at least one remote compute device based on the set of at least one quality score.

Abstract: Embodiments of the disclosure are directed to methods of removing metal oxide from a substrate surface by exposing the substrate surface to a hydrogen (H2) plasma and pulses of RF. In some embodiments, the substrate surface has at least one feature thereon, the at least one feature defining a trench having a top surface, a bottom surface, and two opposed sidewalls. The hydrogen (H2) plasma and pulses of RF remove substantially all of the metal oxide, e.g., tungsten oxide (WOx), molybdenum oxide (MoOx), or ruthenium oxide (RuOx), from the substrate surface, without damaging the dielectric and/or critical dimension (CD)/profile of the structure. A metal fill can then be selectively deposited in the trench.

Abstract: Clustering a plurality of client devices running an application as a function of a data structure such that the plurality of client devices are each assigned a cluster. Client devices having similar performance metrics are assigned the same cluster. An operation of the application is modified as a function of the performance metrics of the client device. The modification of application operation is performed by turning certain features of the application on and off using a rule based on device cluster.

Abstract: The present disclosure provides a computer-implemented method. The method includes: acquiring 3D volumetric data for representing a real-world scene; acquiring a current set of active 3D volumetric data from the 3D volumetric data in response to an activating action on the 3D volumetric data; updating a plurality of sets of active 3D volumetric data based on the current set of active 3D volumetric data, the plurality of sets of active 3D volumetric data being acquired from the 3D volumetric data; constructing a surface based on the plurality of updated sets of active 3D volumetric data; and simulating a deformation of a part of the real-world scene based on the surface, the part of the real-world scene corresponding to the plurality of updated sets of active 3D volumetric data. In addition, the present disclosure also provides an electronic device, and a storage medium.

Abstract: Methods of manufacturing and processing semiconductor devices (i.e., electronic devices) are described. Embodiments of the disclosure advantageously provide methods to reduce the resistance of the work function layer of an electronic device, as well as using a low resistivity metal for filling the gate.

Abstract: A method for identifying human poses in an image, a computer system, and a non-transitory computer-readable medium are provided. The method includes obtaining the image, encoding the image into a feature map, converting the feature map into a plurality of TPDF maps corresponding to a plurality of predefined part types, and generating a global pose map based on the feature map and the plurality of TPDF maps corresponding to the predefined part types. Each TPDF map corresponds to a respective predefined part type and represents a plurality of vectors connecting each position on the image to a closest body part among the one or more body parts of the respective predefined part type. A global pose map is generated based on the feature map and the plurality of TPDF maps, identifying one or more human bodies having a plurality of body parts in a scene of the image.

Abstract: Methods and apparatus for processing a substrate are provided. In some embodiments, a method includes depositing an amorphous interlayer atop a first layer on a substrate, wherein the first layer is a metal-containing layer, and depositing a metal layer atop the amorphous interlayer.

Abstract: A folding device for a disposable hygiene article includes: a first conveying portion along a first path; a second conveying portion along a second path extending in a direction intersecting with the first path; a folding mechanism to fold the disposable hygiene article between the first and second conveying portions; a driving mechanism connected to the folding component, to drive the folding component by performing reciprocating linear motion along the direction of the second path between a folding and retracted positions; and a guiding mechanism in an extension direction of the first path or by using the first path as a reference, a front end portion of the article to an opposite side of the second conveying portion. The driving mechanism includes at least one pulley directly connected to a servo motor and a synchronous belt wrapped around the outer circumference of the pulleys in a looping path.

Abstract: A method of gap fill may include depositing a sacrificial Si layer in an opening of a feature and on a field of a substrate. In addition, the method may include depositing a metal layer in the opening and on the field, where at least a portion of the sacrificial Si layer is replaced with the metal layer. The method may also include depositing a metal gapfill material in the opening and on the field directly over the metal layer, where the metal gapfill material completely fills the opening.

Abstract: Embodiments disclosed herein include electronic packages with chocked flow cooling. In an embodiment, an electronic package may comprise a package substrate, a die electrically and mechanically coupled to the package substrate, and a lid over the die. In an embodiment, the lid has a first opening and a second opening that is opposite from the first opening. In an embodiment, the electronic package may further comprise a coolant plate covering the first opening. In an embodiment, the coolant plate comprises a first surface facing away from the die and a second surface facing the die, and a plurality of vents from the first surface to the second surface. In an embodiment, the first openings of the plurality of vents have a first dimension and second openings of the plurality of vents have a second dimension that is smaller than the first dimension.

Abstract: According to one aspect, spatial action localization in the future (SALF) may include feeding a frame from a time step of a video clip through an encoder to generate a latent feature, feeding the latent feature and one or more latent features from one or more previous time steps of the video clip through a future feature predictor to generate a cumulative information for the time step, feeding the cumulative information through a decoder to generate a predicted action area and a predicted action classification associated with the predicted action area, and implementing an action based on the predicted action area and the predicted action classification. The encoder may include a 2D convolutional neural network (CNN) and/or a 3D-CNN. The future feature predictor may be based on an ordinary differential equation (ODE) function.

Abstract: A robotic system and method of rapid deployment is provided. The robotic system may include a control system, and a transfer unit cell in communication with the control system for facilitating transfer of objects from a source to a destination. The transfer unit cell may translate between a deployed configuration configured to receive and interact with objects, a retracted configuration where the transfer unit cell is retracted into itself, and a transport configuration for moving the transfer unit cell via a transport unit. The transfer unit cell may include a cell base plate, a robotic arm mount for supporting a robot, a conveyor system for receiving or providing at least one target object, a sensor mount for receiving a sensor system, and a unit enclosure mounted to the cell base plate of the transfer unit cell to facilitate transport of the transfer unit cell and translation between positions.

Abstract: Systems and methods for trajectory imputation and prediction are provided. In one embodiment, a method includes generating a spatial missing pattern in an imputation stream by applying a binary mask to an observational dataset over a number of past timesteps. The method includes extracting spatial features from the spatial missing pattern for the number of past time steps. The method includes encoding the spatial features of the observational dataset into imputation latent variables in a latent space based on the spatial missing pattern. The method includes generating a temporal missing pattern by modeling temporal dependency as temporal decay from the past time to the first time based on the latent space. The method includes determining imputation trajectories based on the imputation latent variables and the temporal missing pattern. The method includes predicting future trajectories for the number of agents for a number of future timesteps based temporal missing pattern.

Abstract: A computer system obtains an image of a scene captured by a camera and identifies a two-dimensional (2D) pose of the person in the image. The 2D pose includes a plurality of 2D joint positions in the image. The 2D pose is converted to a three-dimensional (3D) pose of the person including a plurality of 3D joint positions. The computer system determines a rotation angle of each joint relative to a T-pose of the person based on the plurality of 3D joint positions. The rotation angle of each joint is applied to a skeleton template of the avatar. The computer system renders the skeleton template of the avatar having the rotation angle for each joint.

Abstract: A method and related system operations include obtaining a video stream with an image sensor of a camera device, detecting a plurality of target objects by executing a neural network model based on the video stream with a vision processor unit of the camera device. The method also includes generating a plurality of bounding boxes, determining a plurality of character sequences by, for each respective bounding box of the plurality of bounding boxes, performing a set of optical character recognition (OCR) operations to determine a respective character sequence of the plurality of character sequences. The method also includes updating a plurality of tracklets to indicate the plurality of bounding boxes and storing the plurality of tracklets in association with the plurality of character sequences in a memory of the camera device.

Abstract: Embodiments of the disclosure relate to methods of depositing tungsten. Some embodiments of the disclosure provide methods for depositing tungsten which are performed at relatively low temperatures. Some embodiments of the disclosure provide methods in which the ratio between reactant gasses is controlled. Some embodiments of the disclosure provide selective deposition of tungsten. Some embodiments of the disclosure provide methods for depositing tungsten films at a low temperature with relatively low roughness, stress and impurity levels.