Abstract: A method is presented. The method includes receiving a first sequence of frames depicting a dynamic element. The method also includes decomposing each spatial position from multiple spatial positions in the first sequence of frames to a frequency domain. The method further includes determining a distribution of spectral power density over a range of frequencies of the multiple spatial positions. The method still further includes generating a first set of feature maps based on the determined distribution of spectral power density over the range of frequencies. The method still further includes estimating a first physical property of the dynamic element.

Abstract: A transducer system has 1) a MEMS transducer configured to produce an analog output signal in response to an incident acoustic signal, and 2) a modulator apparatus. The modulator apparatus includes an analog modulator configured to receive the analog output signal and produce a first digital signal as a function of the analog output signal. In addition, the modulator apparatus also has a digital converter configured to receive the first digital signal and produce a second digital signal as a function of the first digital signal. The analog modulator has an analog order while, in a corresponding manner, the digital converter has a digital order. Preferably, the digital order is higher than the analog order.

Abstract: In a sequence of major computational steps or in an iterative computation, a stencil amplifier can increase the number of data elements accessed from one or more data structures in a single major step or iteration, thereby decreasing the total number of computations and/or communication operations in the overall sequence or the iterative computation. Stencil amplification, which can be optimized according to a specified parameter such as compile time, rune time, code size, etc., can improve the performance of a computing system executing the sequence or the iterative computation in terms of run time, memory load, energy consumption, etc. The stencil amplifier typically determines boundaries, to avoid erroneously accessing data elements not present in the one or more data structures.

Abstract: A system for compiling programs for execution thereof using a hierarchical processing system having two or more levels of memory hierarchy can perform memory-level-specific optimizations, without exceeding a specified maximum compilation time. To this end, the compiler system employs a polyhedral model and limits the dimensions of a polyhedral program representation that is processed by the compiler at each level using a focalization operator that temporarily reduces one or more dimensions of the polyhedral representation. Semantic correctness is provided via a defocalization operator that can restore all polyhedral dimensions that had been temporarily removed.

Abstract: A method is described. The method includes mapping features extracted from an unannotated red-green-blue (RGB) image of the object to a depth domain. The method further includes determining a three-dimensional (3D) pose of the object by providing the features mapped from the unannotated RGB image of the object to the depth domain to a trained pose estimator network.

Abstract: A transducer system has a transducer configured to receive an incident signal and produce an output signal as a function of the incident signal. As known in the art, the output signal has a ?3 dB point. The transducer system also has circuitry operatively coupled with the transducer. The circuitry includes an amplifier with an output configured to produce an amplified signal as a function of the output signal. In addition, the circuitry further has a positive feedback loop and a negative feedback loop that both are electrically coupled between the transducer and the amplifier. The positive feedback loop is configured to move the ?3 dB point in a first frequency direction. Conversely, the negative feedback loop is configured to move the ?3 dB point in a second frequency direction. Preferably, the first and second frequency directions are different.

Abstract: A method for annotating points on a 2D image of a hand, includes: capturing several images of the hand from different views; for each viewpoint, the hand is imaged using cameras including: one first 2D camera and one 3D camera; using a 3D engine for: creating a 3D hand representation from the 3D camera; considering a 3D model of an articulated hand with predefined annotation points; considering several 3D viewpoints of the hand; for each viewpoint considered: modifying the articulated hand to be superimposed with the 3D representation; considering a 2D image captured from the first 2D camera; superimposing the modified articulated hand on the hand captured on the 2D image; applying the annotation points of the modified articulated hand on the hand captured on the 2D image; and storing the 2D image with annotation on the hand.

Abstract: A method for processing an image is presented. The method locates a subject and an object of a subject-object interaction in the image. The method determines relative weights of the subject, the object, and a context region for classification. The method further classifies the subject-object interaction based on a classification of a weighted representation of the subject, a weighted representation of the object, and a weighted representation of the context region.

Abstract: We present the architecture of a high-performance constraint solver R-Solve that extends the gains made in SAT performance over the past fifteen years on static decision problems to problems that require on-the-fly adaptation, solution space exploration and optimization. R-Solve facilitates collaborative parallel solving and provides an efficient system for unrestricted incremental solving via Smart Repair. R-Solve can address problems in dynamic planning and constrained optimization involving complex logical and arithmetic constraints.

Abstract: We present the architecture of a high-performance constraint solver R-Solve that extends the gains made in SAT performance over the past fifteen years on static decision problems to problems that require on-the-fly adaptation, solution space exploration and optimization. R-Solve facilitates collaborative parallel solving and provides an efficient system for unrestricted incremental solving via Smart Repair. R-Solve can address problems in dynamic planning and constrained optimization involving complex logical and arithmetic constraints.

Abstract: A method for classifying subject activities in videos includes learning latent (previously generated) concepts that are analogous to nodes of a graph to be generated for an activity in a video. The method also includes receiving video segments of the video. A similarity between the video segments and the previously generated concepts is measured to obtain segment representations as a weighted set of latent concepts. The method further includes determining a relationship between the segment representations and their transitioning pattern over time to determine a reduced set of nodes and/or edges for the graph. The graph of the activity in the video represented by the video segments is generated based on the reduced set of nodes and/or edges. The nodes of the graph are represented by the latent concepts. Subject activities in the video are classified based on the graph.

Abstract: Techniques are provided for one or more three-dimensional models representing one or more objects. For example, an input image including one or more objects can be obtained. From the input image, a location field can be generated for each object of the one or more objects. A location field descriptor can be determined for each object of the one or more objects, and a location field descriptor for an object of the one or more objects can be compared to a plurality of location field descriptors for a plurality of three-dimensional models. A three-dimensional model can be selected from the plurality of three-dimensional models for each object of the one or more objects. A three-dimensional model can be selected for the object based on comparing a location field descriptor for the object to the plurality of location field descriptors for the plurality of three-dimensional models.

Abstract: A method for labeling a spherical target includes receiving an input including a representation of an object. The method also includes estimating unconstrained coordinates corresponding to the object. The method further includes estimating coordinates on a sphere by applying a spherical exponential activation function to the unconstrained coordinates. The method also associates the input with a set of values corresponding to a spherical target based on the estimated coordinates on the sphere.

Abstract: A method is presented. The method includes receiving a first sequence of frames. The method also includes decomposing each spatial position from multiple spatial positions in the first sequence of frames to a frequency domain. The method further includes determining a distribution of spectral power density over a range of frequencies of the multiple spatial positions. The method still further includes generating a first set of feature maps based on the determined distribution of spectral power density over the range of frequencies.

Abstract: The present disclosure relates to methods and devices for operation of a GPU. The device can determine a first subset of primitives associated with a set of objects within an image. The first subset of primitives can be based on a first viewpoint with respect to the set of objects. The device can also determine, for a second viewpoint with respect to the set of objects, a second subset of primitives excluding the first subset of primitives. In some aspects, the second subset of primitives can have a difference in depth with respect to the first subset of primitives that is less than a threshold depth. Additionally, the device can mark the first subset of primitives and the second subset of primitives as visible. Further, the device can generate graphical content based on the marked first subset of primitives and the marked second subset of primitives.

Abstract: An apparatus may be configured to obtain, for a Siamese neural network having a recurrent neural network (RNN), an initial representation associated with a target object at a first time step and a set of candidate regions at a current time step. The apparatus may determine an updated representation associated with the target object based on the initial representation at the first time step and observed information associated with the target object at a set of previous time steps, and the observed information associated with the target object may be represented by a hidden state of the RNN. The apparatus may output the updated representation associated with the target object for matching with the set of candidate regions at the current time step by the Siamese neural network. The apparatus may determine the updated representation further based on a hidden state at a previous time step.

Abstract: Transistor noise tolerant, non-volatile (NV) resistance element-based static random access memory (SRAM) physically unclonable function (PUF) circuits and related systems and methods. In exemplary aspects, a transistor and its complementary transistor, such as a pull-up transistor and complement pull-down transistor or pull-down transistor and complement pull-up transistor, of the PUF circuit are replaced with passive NV resistance elements coupled to the respective output node and complement output node to enhance imbalance between cross-coupled transistors of the PUF circuit for improved PUF output reproducibility. The added passive NV resistance elements replacing pull-up or pull-down transistors in the PUF circuit reduces or eliminates transistor noise that would otherwise occur if the replaced transistors were present in the PUF circuit as a result of changes in temperature, voltage variations, and aging effect.

Abstract: Techniques are provided for selecting a three-dimensional model. An input image including an object can be obtained, and a pose of the object in the input image can be determined. One or more candidate three-dimensional models representing one or more objects in the determined pose can be obtained. From the one or more candidate three-dimensional models, a candidate three-dimensional model can be determined to represent the object in the input image.

Abstract: In an example aspect, an apparatus includes a balanced power amplifier, which performs amplification in the presence of a variable antenna impedance. The balanced power amplifier includes a quadrature output power combiner coupled to a first power amplifying path and a second power amplifying path, detection circuitry, and control circuitry. The detection circuitry includes at least one power detector coupled to an isolated port of the quadrature output power combiner and a resistor coupled between the isolated port and a ground. The at least one power detector is configured to measure power at the isolated port, which is based on a resistance of the resistor. The control circuitry is configured to adjust operating conditions of a first power amplifier of the first power amplifying path and the second power amplifier of the second power amplifying path based on the power that is measured at the isolated port.

Abstract: A method, an apparatus, and a computer-readable medium for wireless communication are provided. In one aspect, an example method may include determining to control a bit rate of a content encoder. The method may include generating a first number of shaded texture atlases for use in rendering a second number of frames by a second device based on the determination to control the bit rate of the content encoder. Each respective shaded texture atlas may include a respective plurality of shaded primitives. The method may include encoding, by the content encoder of the first device, a first shaded texture atlas of the first number of shaded texture atlases. The method may include transmitting, by the first device, the encoded first shaded texture atlas to the second device.