Abstract: Various embodiments provide for the generation of 3D models of objects. For example, depth data and color image data can be captured from viewpoints around an object using a sensor. A camera having a higher resolution can simultaneously capture image data of the object. Features between images captured by the image sensor and the camera can be extracted and compared to determine a mapping between the camera and the image. Once the mapping between the camera and the image sensor is determined, a second mapping between adjacent viewpoints can be determined for each image around the object. In this example, each viewpoint overlaps with an adjacent viewpoint and features extracted from two overlapping viewpoints are matched to determine their relative alignment. Accordingly, a 3D point cloud can be generated and the images captured by the camera can be projected on the surface of the 3D point cloud to generate the 3D model.

Abstract: The present disclosure is directed to collaborative feature learning using social media data. For example, a machine learning system may identify social media data that includes user behavioral data, which indicates user interactions with content item. Using the identified social user behavioral data, the machine learning system may determine latent representations from the content items. In some embodiments, the machine learning system may train a machine-learning model based on the latent representations. Further, the machine learning system may extract features of the content item from the trained machine-learning model.

Abstract: A method controls multiple continuous actuators to achieve a discrete mode of operation in a system. The method may include determining a desired output state of the system, including processing a control input set for the multiple continuous actuators via a dynamical predictive model of the system, and then processing the control input set via the dynamical predictive model to determine possible control solutions for achieving the desired output state of the system at a calibrated future time point. The method may include using a cost function logic block to identify, from among the possible control solutions, a lowest-cost control solution for executing the discrete mode at the future time point, processing the lowest-cost control solution through a real-time optimization logic block to determine an optimized solution for the discrete mode, and then executing the optimized solution at the future time point.

Abstract: A system and method are provided for operating a powertrain control system. The method includes receiving data measured from a plurality of sensors, the measured data relating to distance dependent speed values, and receiving information from one or more vehicle modules, the vehicle module information relating to distance independent speed values. The method further includes building a speed trajectory profile for a horizon window that includes a plurality of speed change regions represented by at least some distance dependent speed values or at least some distance independent speed values, and creating a synthesized speed profile for the horizon window by processing the speed trajectory profile. The synthesized speed profile optimizes efficiency of the powertrain control system at each of the plurality of speed change regions.

Abstract: A multi-band antenna array includes a plurality of first antennas for resonating at a first band, and a plurality of second antennas for resonating at a second band. A frequency of the second band is higher than a frequency of the first band. Locations of the plurality of first antennas project to a plurality of grid-one positions on a surface; locations of the plurality of second antennas project to a plurality of grid-two positions on the surface. Among the grid-one positions, a second grid-one position is nearest to a first grid-one position by a first distance along a first direction. Among the grid-two positions, a first grid-two position and a second grid-two position are closest two to the first grid-one position. The first and second grid-two positions are separated by a second distance along a second direction; and, the first direction and the second direction are nonparallel.

Abstract: In some embodiments, techniques for synthesizing an image style based on a plurality of neural networks are described. A computer system selects a style image based on user input that identifies the style image. The computer system generates an image based on a generator neural network and a loss neural network. The generator neural network outputs the synthesized image based on a noise vector and the style image and is trained based on style features generated from the loss neural network. The loss neural network outputs the style features based on a training image. The training image and the style image have a same resolution. The style features are generated at different resolutions of the training image. The computer system provides the synthesized image to a user device in response to the user input.

Abstract: A method of start/stop engine control based on vehicle location and driving situation includes identifying the location and driving situation of a host vehicle, and classifying the location and the driving situation of the host vehicle based on the identified location and driving situation. The engine start/stop control is based on at least one of the location classification and driving situation classification.

Abstract: An anode and a lithium ion battery employing the same are provided. The anode includes a lithium-containing layer and a single-ion conductive layer. The single-ion conductive layer includes an inorganic particle, a single-ion conductor polymer, and a binder. The single-ion conductor polymer has a first repeat unit of Formula (I), a second repeat unit of Formula (II), a third repeat unit of Formula (III), and a fourth repeat unit of Formula (IV) wherein R1 is O?M+, SO3?M+, N(SO2F)?M+, N(SO2CF3)?M+, N(SO2CF2CF3)?M+, COO?M+, or PO4?M+; M+ is Li+, Na+, K+, Cs+, or a combination thereof; and R2 is CH3, CH2CH3, or CH2CH2OCH2CH3. In particular, the weight ratio of the inorganic particle to the sum of the single-ion conductor polymer and the binder is from 4:1 to 9:1, and the weight ratio of the binder to the single-ion conductor polymer is from 1:1 to 9:1.

Abstract: An antenna assembly includes a first antenna element coupled to RF circuitry via a first feeder, and a second antenna element coupled to the RF circuitry via a second feeder. The first feeder and the second feeder have different shapes. The first antenna element and the second antenna element radiate in different frequency bands and in a direction parallel to a ground plane. The ground plane is disposed on at least one layer in a substrate that includes a plurality of layers parallel to one another. The first antenna element is disposed on first one or more of the layers and the second antenna element is disposed on second one or more of the layers, which are different from the first one or more of the layers. Another antenna assembly includes a first subarray of the first antenna elements and a second subarray of the second antenna elements.

Abstract: Transferring motion between consecutive frames to a digital image is leveraged in a digital medium environment. A digital image and at least a portion of the digital video are exposed to a motion transfer model. The portion of the digital video includes at least a first digital video frame and a second digital video frame that is consecutive to the first digital video frame. Flow data between the first digital video frame and the second digital image frame is extracted, and the flow data is then processed to generate motion features representing motion between the first digital video frame and the second digital video frame. The digital image is processed to generate image features of the digital image. Motion of the digital video is then transferred to the digital image by combining the motion features with the image features to generate a next digital image frame for the digital image.

Abstract: An electrically driven pump is provided, which includes an impeller. The impeller includes an upper plate, blades and a lower plate. The blades are formed on a lower surface of the upper plate, the blades include first blades and second blades, and a length of each of the first blades is greater than a length of each of the second blades. The first blades are uniformly distributed along a circumference of the upper plate. The first blades and the second blades are distributed alternately in the circumferential direction. The first blades each include a first head portion and a first tail portion, the second blade includes a second head portion and a second tail portion, and the first tail portion and the second tail portion are aligned with outer edge of the upper plate. The impeller arranged in such manner facilitates the improvement of hydraulic efficiency and lift.

Abstract: A tunable antenna module for a mobile device includes an antenna, a frequency-division circuit and one or more impedance-tuning circuits. The frequency-division circuit is coupled to a radiator of the antenna for forming one or more signal paths for one or more of component frequencies of a radio-frequency signal of the antenna. One or more the impedance-tuning circuits are coupled to the frequency-division circuit for tuning an impedance of the antenna at one or more of the component frequencies of the radio-frequency signal.

Abstract: The present disclosure includes methods and systems for searching for digital visual media based on semantic and spatial information. In particular, one or more embodiments of the disclosed systems and methods identify digital visual media displaying targeted visual content in a targeted region based on a query term and a query area provide via a digital canvas. Specifically, the disclosed systems and methods can receive user input of a query term and a query area and provide the query term and query area to a query neural network to generate a query feature set. Moreover, the disclosed systems and methods can compare the query feature set to digital visual media feature sets. Further, based on the comparison, the disclosed systems and methods can identify digital visual media portraying targeted visual content corresponding to the query term within a targeted region corresponding to the query area.

Abstract: The present disclosure relates to a fashion recommendation system that employs a task-guided learning framework to jointly train a visually-aware personalized preference ranking network. In addition, the fashion recommendation system employs implicit feedback and generated user-based triplets to learn variances in the user's fashion preferences for items with which the user has not yet interacted. In particular, the fashion recommendation system uses triplets generated from implicit user data to jointly train a Siamese convolutional neural network and a personalized ranking model, which together produce a user preference predictor that determines personalized fashion recommendations for a user.

Abstract: The present disclosure relates to a personalized fashion generation system that synthesizes user-customized images using deep learning techniques based on visually-aware user preferences. In particular, the personalized fashion generation system employs an image generative adversarial neural network and a personalized preference network to synthesize new fashion items that are individually customized for a user. Additionally, the personalized fashion generation system can modify existing fashion items to tailor the fashion items to a user's tastes and preferences.

Abstract: The present disclosure includes methods and systems for searching for digital visual media based on semantic and spatial information. In particular, one or more embodiments of the disclosed systems and methods identify digital visual media displaying targeted visual content in a targeted region based on a query term and a query area provide via a digital canvas. Specifically, the disclosed systems and methods can receive user input of a query term and a query area and provide the query term and query area to a query neural network to generate a query feature set. Moreover, the disclosed systems and methods can compare the query feature set to digital visual media feature sets. Further, based on the comparison, the disclosed systems and methods can identify digital visual media portraying targeted visual content corresponding to the query term within a targeted region corresponding to the query area.

Abstract: An anode and a lithium ion battery employing the same are provided. The anode includes a lithium-containing layer and a single-ion conductive layer. The single-ion conductive layer includes an inorganic particle, a single-ion conductor polymer, and a binder. The single-ion conductor polymer has a first repeat unit of Formula (I), a second repeat unit of Formula (II), a third repeat unit of Formula (III), and a fourth repeat unit of Formula (IV) wherein R1 is O?M+, SO3?M?, N(SO2F)?M+, N(SO2CF3)?M+, N(SO2CF2CF3)?M+, COO?M+, or PO4?M+; M+ is Li+, Na+, K+, Cs+, or a combination thereof; and R2 is CH3, CH2CH3, or CH2CH2OCH2CH3. In particular, the weight ratio of the inorganic particle to the sum of the single-ion conductor polymer and the binder is from 4:1 to 9:1, and the weight ratio of the binder to the single-ion conductor polymer is from 1:1 to 9:1.

Abstract: Techniques are disclosed for generating audio based on visual information. In some examples, an audio generation system is trained using supervised learning using a training set generated from videos. The trained audio generation system is able to infer audio for provided silent video based on the visual contents of the silent video, and generate raw waveform samples that represent the inferred audio.

Abstract: A method of start/stop engine control based on vehicle location and driving situation includes identifying the location and driving situation of a host vehicle, and classifying the location and the driving situation of the host vehicle based on the identified location and driving situation. The engine start/stop control is based on at least one of the location classification and driving situation classification.

Abstract: An antenna with swappable and selective radiation direction includes a first arm, a second arm electrically connected to the first arm, a third arm is electrically connected to the first arm, a first impedance tuning circuit coupled to the second arm for connecting the second arm to a ground or a first matching component according to a control signal, and a second impedance tuning circuit coupled to the third arm for connecting the third arm to the ground or a second matching component according to the control signal. By tuning impedance of the antenna, the antenna operates in a first mode corresponding to a first radiation direction or a second mode corresponding to a second radiation direction.