Abstract: In one embodiment, a device tracks objects in video data captured by one or more cameras in a location. The device represents spatial characteristics of the objects over time as timeseries. The device associates different portions of the timeseries with behavioral regimes of the objects. The device makes a determination that one of the objects is a reflection of another of the objects, based on a correlation between changes of their respective behavioral regimes.

Abstract: An apparatus, computer readable storage medium and method of generating a diverse set of images from few-shot images, includes a parameter input receiving values for control parameters to control an extent to which each reference image impacts a newly generated image. The apparatus involves an image generation deep learning network for generating an image for each of the values for the control parameters. The deep learning network has an encoder, a transformer-based fusion block, and a decoder. The transformer-based fusion block includes a mapping network that computes meta-weights from features extracted from the reference images and the control parameters, and a cross-attention block to generate modulation weights based on the meta-weights. An output displays high-quality and diverse images generated based on the values for the control parameter.

Abstract: In one embodiment, a device represents spatial characteristics of an object depicted in video data over time as one or more timeseries. The device associates different portions of the one or more timeseries with behavioral regimes of the object. The device generates ground truth labels for frames of the video data based on changes in the behavioral regimes of the object associated with those frames. The device trains a self-supervised model to detect an event depicted in the video data using the ground truth labels and their associated frames.

Abstract: A modular and on-demand battery thermal management system (BTMS) for an electric machine or a stationary energy storage solution with a battery is disclosed. The BTMS may include one or more independently operable BTMS modules, where each BTMS module may be configured to cool a corresponding component of the electric machine, such as a particular battery pack. Each BTMS module, in turn, may include a plurality of BTMS units that cool coolant that is to be delivered to the components that are to be cooled within the electric machine. The individual BTMS units may be independently operable by a BTMS controller based at least in part on the cooling needs of the components to be cooled. The BTMS controller is also configured to control pumps and valves to appropriately direct coolant to the BTMS units that are operating in a modular fashion.

Abstract: Various systems and methods are described for implementing trust authority or trust attestation verification operations, including for Trust-as-a-Service or Attestation-as-a-Service implementations, in accordance with the techniques discussed herein. In various examples, operations and configurations are described to enable service-to-service attestation using a trust authority, to operate an attestation service, and to coordinate trust operations between relying and requesting parties.

Abstract: The present disclosure relates to techniques for interacting with an electronic device. More specifically, the present disclosure relates to initiating action(s) using an interface configured to control operation of IoT devices. A network device may be detected. Information for the network may be received. Capabilities of the network may be determined. An interface module may facilitate display of a network device interface. A control object may facilitate control of the network device.

Abstract: An electronic device includes a first substrate having a first bonding region, a first circuit, a second circuit, a third circuit, and a plurality of first conductive contacts. The first and second circuit are located at a first edge and a second edge of the first bonding region, the third circuit is located between the first and the second circuits. A second substrate having a second bonding region corresponding to the first bonding region in position and a fourth circuit, a fifth circuit, a sixth circuit, and a plurality of second conductive contacts. When the first substrate is bonded with the second substrate, the first circuit, the second circuit, the third circuit, the fourth circuit, the fifth circuit, and the sixth circuit form a loop, and the first and second conductive contacts are electrically connected to a plurality of signal circuits.

Abstract: A method of repairing a fractured bone may include implanting a prosthetic stem into an intramedullary canal of the fractured bone. First and second bone segments of the fractured bone may be robotically machined to include first and second implant-facing surfaces that are substantially negatives of first and second surface portions of the first end of the prosthetic stem. The first and second tuberosities may be machined so that the first and second bone segments have first and second interlocking surfaces shaped to interlock with each other. During implantation, the first and second implant-facing surfaces are in contact with the first and second surface portions of the first end of the prosthetic stem, and the first interlocking surface interlocks with the second interlocking surface.

Abstract: Systems/techniques that facilitate AI-based region-of-interest masks for improved data reconstructions are provided. In various embodiments, a system can access a set of two-dimensional medical scan projections. In various aspects, the system can generate a set of two-dimensional region-of-interest masks respectively corresponding to the set of two-dimensional medical scan projections. In various instances, the system can generate a region-of-interest visualization based on the set of two-dimensional region-of-interest masks and the set of two-dimensional medical scan projections. In various cases, the system can generate the set of two-dimensional region-of-interest masks by executing a machine learning segmentation model on the set of two-dimensional medical scan projections.

Abstract: The present invention provides bicyclic heterocyclyl kinase enzyme inhibitor compounds of formula (I), which are therapeutically useful as kinase inhibitors, particularly IRAK4 inhibitors. wherein A, Y, Z, X1, X2, X3, R1, R3, ‘m’, ‘n’ and ‘p’ have the meanings given in the specification and pharmaceutically acceptable salts or stereoisomers thereof that are useful in the treatment and prevention of diseases or disorders, in particular their use in diseases or disorders mediated by kinase enzyme, particularly IRAK4 enzyme. The present invention also provides pharmaceutical compositions comprising at least one of the compounds of compound of formula (I) together with a pharmaceutically acceptable carrier, diluent or excipient therefor.

Abstract: Systems, computer program products, and methods are described herein for predicting, detecting, and preventing unauthorized access events associated with electronic systems. The systems, computer program products, and methods may be configured to receive, from a first automated teller machine, an alert message including information associated with a first unauthorized access event occurring at the first automated teller machine and determine, based on the information in the alert message, a location of the first automated teller machine. The systems, computer program products, and methods may be configured to identify a second automated teller machine proximate the location of the first automated teller machine and provide, to the second automated teller machine, one or more commands to be executed by the second automated teller machine to prevent a second unauthorized access event from occurring at the second automated teller machine.

Abstract: The disclosed computer-implemented method may include receiving, as input, an audio/video data object; isolating a video stream of a visible potential speaker over a plurality of frames of the audio/video data object; isolating an audio stream over the plurality of frames; providing the isolated video stream and the isolated audio stream to a machine learning model trained with contrastive learning, the contrastive learning using (i) a corpus of video segments of visible speakers with corresponding original audio for positive samples; and (ii) a corpus of video segments of visible speakers with corresponding dubbed audio for negative samples; and evaluating a match between the isolated audio stream and the isolated video stream based at least in part on an output of the machine learning model. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: Embodiments of a surface heat exchanger for a vehicle are described. In one embodiment, a surface heat exchanger includes a plurality of fins on a first outer surface The surface heat exchanger is mounted within an interior of a duct of a vehicle. An inlet of the duct is located on a side of the vehicle forward of a rear axle of the vehicle and an outlet of the duct is located rearward of the inlet. The plurality of fins of the surface heat exchanger are exposed to the interior of the duct. The plurality of fins are configured to transfer heat to airflows interacting with the plurality of fins as the airflows pass through the duct.

Abstract: A system and method enabling the seamless transition between viewing a recorded portion of a program and rejoining a live stream of that program. The system and method enable the rapid provision of live-streamed content upon the exhaustion of the playback of recorded content. This achieved by utilizing a universal resource locator associated with the source of the content.

Abstract: The present disclosure relates to the field of switch gears, and envisages an actuator for a switch gear of an electric panel having a door. The actuator comprises an aligner assembly and an actuator plate assembly. The aligner assembly comprises an aligner pivotably mounted on the switch gear housing, and engaging with a toggle of a circuit breaker, of the switch gear, to angularly displace the toggle. The aligner has a pair of slanting flanges configured to define a valley separated by a gap. The actuator plate assembly comprises a mounting plate mounted on the enclosure door. A shaft element, having a handle element and an engaging element, passes through the mounting plate. The engaging element is configured to nest in the gap of the aligner to angularly displace the aligner.

Abstract: The disclosure provides a method and system of improvement in the real-time operation of a terminal station in an industrial facility using a machine learning-based self-adaptive system comprising obtaining real-time operations data and historical data stored in a local database or at a cloud-storage. The data relates to input parameters of the terminal station. The method includes inputting the input parameter to a machine learning configurable module of the machine learning-based self-adaptive system and analyzing the input parameter using dynamic machine learning models and algorithms to identify patterns to each of the input parameters. The method further includes evaluating the identified pattern against the real-time operations data obtained from the terminal station and predicting at least one output parameter based on the input parameter and the identified pattern against the real-time operations. Based on the prediction, adjusting the output parameter of the real-time operations data.

Abstract: Techniques for presence-detection devices to vary presence-detection sensitivity to detect different types of movements by objects, such as major movements and minor movements, using ultrasonic signals. The devices detect movement of a person in an environment by emitting ultrasonic signals into the environment, and characterizing the change in the frequency, or the Doppler shift, of the reflections of the ultrasonic signals off the person caused by the movement of the person relative to the presence-detection devices. The presence-detection devices may control the presence-detection sensitivity in order to detect major movements, such as a user walking in a room, as well as objects minor movements, such as a user typing at a computer. By adjusting the presence-detection sensitivity, the devices are able to improve the overall accuracy of detecting the presence of users in an environment.

Abstract: Embodiments described herein relate to integrated abrasive (IA) polishing pads, and methods of manufacturing IA polishing pads using, at least in part, surface functionalized abrasive particles in an additive manufacturing process, such as a 3D inkjet printing process. In one embodiment, a method of forming a polishing article includes dispensing a first plurality of droplets of a first precursor, curing the first plurality of droplets to form a first layer comprising a portion of a sub-polishing element, dispensing a second plurality of droplets of the first precursor and a second precursor onto the first layer, and curing the second plurality of droplets to form a second layer comprising portions of the sub-polishing element and portions of a plurality of polishing elements. Here, the second precursor includes functionalized abrasive particles having a polymerizable group chemically bonded to surfaces thereof.

Abstract: A multi-modal sensor system includes: an underlying sensor system; a polarization camera system configured to capture polarization raw frames corresponding to a plurality of different polarization states; and a processing system including a processor and memory, the processing system being configured to control the underlying sensor system and the polarization camera system, the memory storing instructions that, when executed by the processor, cause the processor to: control the underlying sensor system to perform sensing on a scene and the polarization camera system to capture a plurality of polarization raw frames of the scene; extract first tensors in polarization representation spaces based on the plurality of polarization raw frames; and compute a characterization output based on an output of the underlying sensor system and the first tensors in polarization representation spaces.

Abstract: Embodiments of the present invention provide an intuitive platform for non-contact instructions regarding resource allocation. In this way, a user may utilize one or more specific gestures which are captured, analyzed, and responded to by the system of the invention in order to initiate or complete one or more resource activities such as a resource transfer, resource transfer split, or other resource action.