Abstract: Systems and methods herein describe novel motion representations for animating articulated objects consisting of distinct parts. The described systems and method access source image data, identify driving image data to modify image feature data in the source image sequence data, generate, using an image transformation neural network, modified source image data comprising a plurality of modified source images depicting modified versions of the image feature data, the image transformation neural network being trained to identify, for each image in the source image data, a driving image from the driving image data, the identified driving image being implemented by the image transformation neural network to modify a corresponding source image in the source image data using motion estimation differences between the identified driving image and the corresponding source image, and stores the modified source image data.

Abstract: A module structure and a display device are disclosed. The module structure includes a backlight sheet, a display screen, and a glass cover which are stacked, and further includes a light guide plate, LED lights, and a flexible circuit board disposed between the display screen and the glass cover, the LED lights are located on a side of the light guide plate facing away from a display area, and the LED lights are electrically connected to the flexible circuit board.

Abstract: System and methods for compressing image-to-image models. Generative Adversarial Networks (GANs) have achieved success in generating high-fidelity images. An image compression system and method adds a novel variant to class-dependent parameters (CLADE), referred to as CLADE-Avg, which recovers the image quality without introducing extra computational cost. An extra layer of average smoothing is performed between the parameter and normalization layers. Compared to CLADE, this image compression system and method smooths abrupt boundaries, and introduces more possible values for the scaling and shift. In addition, the kernel size for the average smoothing can be selected as a hyperparameter, such as a 3×3 kernel size. This method does not introduce extra multiplications but only addition, and thus does not introduce much computational overhead, as the division can be absorbed into the parameters after training.

Abstract: The 3D structure and appearance of objects extracted from 2D images are represented in a volumetric grid containing quantized feature vectors of values representing different aspects of the appearance and shape of an object, such as local features, structures, or colors that define the object. An encoder-decoder framework applies spatial transformations directly to a latent volumetric representation of the encoded image content. The volumetric representation is quantized to substantially reduce the space required to represent the image content. The volumetric representation is also spatially disentangled, such that each voxel acts as a primitive building block and supports various manipulations, including novel view synthesis and non-rigid creative manipulations.

Abstract: Methods and systems are disclosed for performing operations for generating a 3D model of a scene. The operations include: receiving a set of two-dimensional (2D) images representing a first view of a real-world environment; applying a machine learning model comprising a neural light field network to the set of 2D images to predict pixel values of a target image representing a second view of the real-world environment, the machine learning model being trained to map a ray origin and direction directly to a given pixel value; and generating a three-dimensional (3D) model of the real-world environment based on the set of 2D images and the predicted target image.

Abstract: A control system for conducting an election may include a voter client configured to be used by a voter to cast a vote for a candidate, a registrar server, and a moderator server. The moderator server may be configured to obscure the identity of the voter. The registrar server may be configured to randomly assign a ballot to the obscured voter. The registrar server may be configured to encrypt the ballot. The moderator server may be configured to transmit the encrypted ballot to the voter client. The voter client may be configured to decrypt the encrypted ballot to recover the ballot. The voter client, in response to the voter selecting a desired candidate, may be configured to generate a ballot associated with a vote. The voter client may be configured to encrypt the ballot using a public key of the registrar server and a public key of the moderator server.

Abstract: The present disclosure provides a light strip, including a circuit board. A plurality of LEDs is arranged on the circuit board and spaced apart from each other in an extension direction of the circuit board, a positive connection end and a plurality of negative connection ends are arranged on the circuit board, and a plurality of LEDs is coupled between each negative connection end and the positive connection end. A plurality of LEDs between the first negative connection end and the positive connection end includes a head-end LED and a tail-end LED. The plurality of LEDs between the first negative connection end and the positive connection end includes a first LED and a second LED arranged at opposite sides of a first position in the extension direction of the circuit board. The present disclosure further provides a backlight module and a display module.

Abstract: A multimodal video generation framework (MMVID) that benefits from text and images provided jointly or separately as input. Quantized representations of videos are utilized with a bidirectional transformer with multiple modalities as inputs to predict a discrete video representation. A new video token trained with self-learning and an improved mask-prediction algorithm for sampling video tokens is used to improve video quality and consistency. Text augmentation is utilized to improve the robustness of the textual representation and diversity of generated videos. The framework incorporates various visual modalities, such as segmentation masks, drawings, and partially occluded images. In addition, the MMVID extracts visual information as suggested by a textual prompt.

Abstract: Techniques for training a neural network having a plurality of computational layers with associated weights and activations for computational layers in fixed-point formats include determining an optimal fractional length for weights and activations for the computational layers; training a learned clipping-level with fixed-point quantization using a PACT process for the computational layers; and quantizing on effective weights that fuses a weight of a convolution layer with a weight and running variance from a batch normalization layer. A fractional length for weights of the computational layers is determined from current values of weights using the determined optimal fractional length for the weights of the computational layers. A fixed-point activation between adjacent computational layers is related using PACT quantization of the clipping-level and an activation fractional length from a node in a following computational layer.

Abstract: A portable medical device includes a portable medical bag, a plurality of connectors and a processor. These connectors respectively connect the portable medical bag and every medical device contained inside the portable medical bag. The portable medical bag obtains the device management information of each the medical device through these connectors. The device management information includes the remaining power of medical device. The processor calculates the charge strategy information of the corresponding medical device according to the medical device information, address information and device management information. In addition, a management method for portable medical device is also provided.

Abstract: A system and method for automatically generating a care record are provided, which are suitable for a baby bed cover. The system includes an image capturing device and a processor. The image capturing device captures a real-time image of a baby in the baby bed. The processor is configured to receive the real-time image and detects whether an abnormal event occurs in the real-time image. The processor detects an opening time and a closing time of the bed cover to obtain a start and end time of a care operation. The processor recognizes an abnormal event type according to the abnormal event, selects a care record template according to the abnormal event type, and generates a care record according to an occurrence time of the abnormal event, the abnormal event type, the start and end time of the care operation, and the care record template.

Abstract: An antenna includes a first portion and a second portion. The first portion is of a first shape and the second portion is of a second shape. The second portion is connected to the first portion by a junction. The antenna operates in a first frequency band and a second frequency band.

Abstract: The embodiments of the present disclosure disclose an evaluation apparatus and a method for seal integrity of a wellbore in a full life cycle. The apparatus may include an oil pipe temperature and pressure simulation assembly, an oil casing annular temperature and pressure simulation assembly, a formation confining pressure simulation assembly, a casing-cement sheath-formation combination preparation assembly, a blowby characteristic detection assembly, and a monitoring system. The present disclosure may crustal stress quickly complete scanning of cement slurry system and maintenance and preparation of casing-cement sheath-formation combination, intelligent monitor blowby pressure of cement sheath in real time, test the critical blowby pressure curve of cement sheath of oil and gas wells under various production conditions throughout the life cycle for evaluating the seal integrity of wellbore, and provide technical support for the formulation of wellbore safeguard measures.

Abstract: In some embodiments, a system performs a service using a plurality of compute nodes. A second compute node installs a dependency injection container to manage a dependency graph of dependencies for classes in an application. The dependency injection container is determined from a first compute node in the plurality of compute nodes that manages performing the service with the plurality of compute nodes. The second compute node receives information identifying a node in the dependency graph from the first compute node. The information is received to create a first object that has been created on the first compute node. The second compute node uses the information to determine a first class for the node in the dependency graph and a dependency on a second class and creates the first object of the first class with the dependency on a second object of the second class on the second compute node.

Abstract: A messaging system performs neural network hair rendering for images provided by users of the messaging system. A method of neural network hair rendering includes processing a three-dimensional (3D) model of fake hair and a first real hair image depicting a first person to generate a fake hair structure, and encoding, using a fake hair encoder neural subnetwork, the fake hair structure to generate a coded fake hair structure. The method further includes processing, using a cross-domain structure embedding neural subnetwork, the coded fake hair structure to generate a fake and real hair structure, and encoding, using an appearance encoder neural subnetwork, a second real hair image depicting a second person having a second head to generate an appearance map. The method further includes processing, using a real appearance renderer neural subnetwork, the appearance map and the fake and real hair structure to generate a synthesized real image.

Abstract: A method for driving display panel includes: for one of adjacent two frames of displayed images, when scanning odd-numbered row of sub-pixels, inputting data signals to the data lines coupled to the data selector in first order by a data selector; when scanning even-numbered row of sub-pixels, inputting data signals to the data lines coupled to the data selector in second order by the data selector; first and second orders each represents an order of inputting data signals to the data lines; first order is opposite to second order; for the other of the adjacent two frames of displayed images, when scanning odd-numbered row of sub-pixels, inputting data signals to the data lines coupled to the data selector in second order by the data selector; when scanning even-numbered row of sub-pixels, inputting data signals to the data lines coupled to the data selector in first order by the data selector.

Abstract: The present disclosure provides a backlight module and a display device. The backlight module includes: a back plate including a bottom wall and a side wall coupled thereto, with the bottom wall and the side wall defining an accommodating space; a light guide plate disposed in the accommodating space and including: a light outgoing surface disposed away from the bottom wall, a bottom surface disposed toward the bottom wall, and a light incident surface coupled between the light outgoing face and the bottom face; a light source disposed in the accommodating space and configured to emit light toward the light incident surface; and a composite film located on a side of the light guide plate away from the bottom wall and including a diffuser sheet and a plurality of prism sheets combined together and sequentially arranged in a direction away from the light guide plate.

Abstract: A messaging system performs neural network hair rendering for images provided by users of the messaging system. A method of neural network hair rendering includes processing a three-dimensional (3D) model of fake hair and a first real hair image depicting a first person to generate a fake hair structure, and encoding, using a fake hair encoder neural subnetwork, the fake hair structure to generate a coded fake hair structure. The method further includes processing, using a cross-domain structure embedding neural subnetwork, the coded fake hair structure to generate a fake and real hair structure, and encoding, using an appearance encoder neural subnetwork, a second real hair image depicting a second person having a second head to generate an appearance map. The method further includes processing, using a real appearance renderer neural subnetwork, the appearance map and the fake and real hair structure to generate a synthesized real image.

Abstract: The present disclosure provides a light strip, including a circuit board. A plurality of LEDs is arranged on the circuit board and spaced apart from each other in an extension direction of the circuit board, a positive connection end and a plurality of negative connection ends are arranged on the circuit board, and a plurality of LEDs is coupled between each negative connection end and the positive connection end. A plurality of LEDs between the first negative connection end and the positive connection end includes a head-end LED and a tail-end LED. The plurality of LEDs between the first negative connection end and the positive connection end includes a first LED and a second LED arranged at opposite sides of a first position in the extension direction of the circuit board. The present disclosure further provides a backlight module and a display module.

Abstract: Device and method for implementing a vehicle sharing reward program. The present invention provides for a cost-sharing plan where two or more constituencies share the rental cost associated with a user who rents a shared vehicle in a vehicle sharing program. This results in a reimbursement of the rental cost to the user. When enrolling in the vehicle sharing reward program, the user is given a health prescription to adhere to on any trip taken while using a shared vehicle. On a selected travel route, the user visits a vehicle sharing station, where the sharing station includes a kiosk that the user uses to check-in and upload relevant information such as distance traveled and locations visited. By complying with the health prescription issued to the user, the user can have its total rental cost reimbursed.