Abstract: Systems and methods for multi-modal representation learning are described. One or more embodiments provide a visual representation learning system trained using machine learning techniques. For example, some embodiments of the visual representation learning system are trained using cross-modal training tasks including a combination of intra-modal and inter-modal similarity preservation objectives. In some examples, the training tasks are based on contrastive learning techniques.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods that utilize a progressive refinement network to refine alpha mattes generated utilizing a mask-guided matting neural network. In particular, the disclosed systems can use the matting neural network to process a digital image and a coarse guidance mask to generate alpha mattes at discrete neural network layers. In turn, the disclosed systems can use the progressive refinement network to combine alpha mattes and refine areas of uncertainty. For example, the progressive refinement network can combine a core alpha matte corresponding to more certain core regions of a first alpha matte and a boundary alpha matte corresponding to uncertain boundary regions of a second, higher resolution alpha matte. Based on the combination of the core alpha matte and the boundary alpha matte, the disclosed systems can generate a final alpha matte for use in image matting processes.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a plurality of neural networks in a multi-branch pipeline to generate image masks for digital images. Specifically, the disclosed system can classify a digital image as a portrait or a non-portrait image. Based on classifying a portrait image, the disclosed system can utilize separate neural networks to generate a first mask portion for a portion of the digital image including a defined boundary region and a second mask portion for a portion of the digital image including a blended boundary region. The disclosed system can generate the mask portion for the blended boundary region by utilizing a trimap generation neural network to automatically generate a trimap segmentation including the blended boundary region. The disclosed system can then merge the first mask portion and the second mask portion to generate an image mask for the digital image.

Abstract: A method and system determines in real time the bearing capacity of a foundation tamped by a high-speed hydraulic tamper. Four wireless acceleration sensors are arranged uniformly along tamping plate edges, sensor position tamping points are determined; the soil is tamped, the plate peak acceleration slows, tends to, and reaches stabilization in a range, a relationship curve between the tamping number and plate peak acceleration is determined; different loads are applied to the foundation to obtain corresponding settlements, coordinate axes are established, points are drawn according to each test data group and sequentially connected with a smooth curve to obtain a settlement-load curve, and the curve is fitted; a tamping number and foundation bearing capacity relationship is obtained; the two relationship curves are combined to obtain a relationship curve, and the foundation bearing capacity magnitude at a certain moment during the tamping operation is determined by using the acceleration index.

Abstract: A fast-response direct-current current transformer based on multi-sensor fusion is provided and includes: a magnetic modulator, a current correction module, an excitation transformer, an alternating current detection and filtering circuit, a phase-sensitive demodulation and filtering system, a PI controller, and a power amplifier. The current correction module measures a primary current and obtain a feed-forward signal, outputs a false balance state configured to control a magnetic core to quickly exit or avoid entering magnetic saturation after amplifying the feed-forward signal and a PI control signal, and keeps output of the magnetic modulator stable. The magnetic modulator and Hall current sensors are fused in the disclosure, such that the possibility of failure due to a false balance problem caused by saturation of a magnetic core is reduced. After the false balance is generated, the magnetic core may be controlled to quickly exit a magnetic saturation state through a feed-forward output current.

Abstract: A fast-response direct-current current transformer based on multi-sensor fusion is provided and includes: a magnetic modulator, a current correction module, an excitation transformer, an alternating current detection and filtering circuit, a phase-sensitive demodulation and filtering system, a PI controller, and a power amplifier. The current correction module measures a primary current and obtain a feed-forward signal, outputs a false balance state configured to control a magnetic core to quickly exit or avoid entering magnetic saturation after amplifying the feed-forward signal and a PI control signal, and keeps output of the magnetic modulator stable. The magnetic modulator and Hall current sensors are fused in the disclosure, such that the possibility of failure due to a false balance problem caused by saturation of a magnetic core is reduced. After the false balance is generated the magnetic core may be controlled to quickly exit a magnetic saturation state through a feed-forward output current.

Abstract: The invention provides the internal fixation system of spine posterior screw-plate, including the vertebral plate. The vertebral plate is curved, its internal cambered surface directly faces the spine, and external cambered surface of vertebral plate is equipped with a reinforcing rib. The vertebral plate is set with the perforative injecting hole. One side of vertebral plate is fixed with a fixed connecting plate, and the end of the fixed connecting plate away from the vertebral plate is set with the first regulating hole. The bottom of the fixed connecting plate on two sides of the first regulating hole is set with n-shaped caulking groove.

Abstract: The invention provides the internal fixation system of multi-function adjustable spine posterior screw-rod. It not only includes the vertebral plate, but also includes the adjustable connecting rod, screw and lock nut. Among them, vertebral plate is curved, its internal cambered surface directly faces the spine, and external cambered surface of vertebral plate is equipped with a reinforcing rib. The vertebral plate is set with the perforative injecting hole, and the external cambered surface of vertebral plate is set with the located block. The surface of the located block is set with the concave threaded hole, and the located block on two sides of the threaded hole is set with the U-shaped bracket. The top of screw expands to form a locking block, which surface is set with the concave locking hole. The locking block on both sides of locking hole is set with the U-shaped locking groove.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a plurality of neural networks in a multi-branch pipeline to generate image masks for digital images. Specifically, the disclosed system can classify a digital image as a portrait or a non-portrait image. Based on classifying a portrait image, the disclosed system can utilize separate neural networks to generate a first mask portion for a portion of the digital image including a defined boundary region and a second mask portion for a portion of the digital image including a blended boundary region. The disclosed system can generate the mask portion for the blended boundary region by utilizing a trimap generation neural network to automatically generate a trimap segmentation including the blended boundary region. The disclosed system can then merge the first mask portion and the second mask portion to generate an image mask for the digital image.

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a plurality of neural networks in a multi-branch pipeline to generate image masks for digital images. Specifically, the disclosed system can classify a digital image as a portrait or a non-portrait image. Based on classifying a portrait image, the disclosed system can utilize separate neural networks to generate a first mask portion for a portion of the digital image including a defined boundary region and a second mask portion for a portion of the digital image including a blended boundary region. The disclosed system can generate the mask portion for the blended boundary region by utilizing a trimap generation neural network to automatically generate a trimap segmentation including the blended boundary region. The disclosed system can then merge the first mask portion and the second mask portion to generate an image mask for the digital image.

Abstract: A style of a digital image is transferred to another digital image of arbitrary resolution. A high-resolution (HR) content image is segmented into several low-resolution (LR) patches. The resolution of a style image is matched to have the same resolution as the LR content image patches. Style transfer is then performed on a patch-by-patch basis using, for example, a pair of feature transforms—whitening and coloring. The patch-by-patch style transfer process is then repeated at several increasing resolutions, or scale levels, of both the content and style images. The results of the style transfer at each scale level are incorporated into successive scale levels up to and including the original HR scale. As a result, style transfer can be performed with images having arbitrary resolutions to produce visually pleasing results with good spatial consistency.

Abstract: A panoptic labeling system includes a modified panoptic labeling neural network (“modified PLNN”) that is trained to generate labels for pixels in an input image. The panoptic labeling system generates modified training images by combining training images with mask instances from annotated images. The modified PLNN determines a set of labels representing categories of objects depicted in the modified training images. The modified PLNN also determines a subset of the labels representing categories of objects depicted in the input image. For each mask pixel in a modified training image, the modified PLNN calculates a probability indicating whether the mask pixel has the same label as an object pixel. The modified PLNN generates a mask label for each mask pixel, based on the probability. The panoptic labeling system provides the mask label to, for example, a digital graphics editing system that uses the labels to complete an infill operation.

Abstract: Various embodiments of systems and methods for cross media joint friend and item recommendations are disclosed herein.

Abstract: The disclosure describes one or more implementations of a neural network architecture pruning system that automatically and progressively prunes neural networks. For instance, the neural network architecture pruning system can automatically reduce the size of an untrained or previously-trained neural network without reducing the accuracy of the neural network. For example, the neural network architecture pruning system jointly trains portions of a neural network while progressively pruning redundant subsets of the neural network at each training iteration. In many instances, the neural network architecture pruning system increases the accuracy of the neural network by progressively removing excess or redundant portions (e.g., channels or layers) of the neural network. Further, by removing portions of a neural network, the neural network architecture pruning system can increase the efficiency of the neural network.

Abstract: The present disclosure relates to shaping the architecture of a neural network. For example, the disclosed systems can provide a neural network shaping mechanism for at least one sampling layer of a neural network. The neural network shaping mechanism can include a learnable scaling factor between a sampling rate of the at least one sampling layer and an additional sampling function. The disclosed systems can learn the scaling factor based on a dataset while jointly learning the network weights of the neural network. Based on the learned scaling factor, the disclosed systems can shape the architecture of the neural network by modifying the sampling rate of the at least one sampling layer.

Abstract: In some embodiments, an application receives a request to execute a convolutional neural network model. The application determines the computational complexity requirement for the neural network based on the computing resource available on the device. The application further determines the architecture of the convolutional neural network model by determining the locations of down-sampling layers within the convolutional neural network model based on the computational complexity requirement. The application reconfigures the architecture of the convolutional neural network model by moving the down-sampling layers to the determined locations and executes the convolutional neural network model to generate output results.

Abstract: Systems and methods for transcoding media content are disclosed. In some embodiments, the method includes obtaining a transcoded media content that is transcoded from an uploaded media content. The method includes determining a plurality of degradation metric values corresponding to the transcoded media content based on the uploaded media content and the transcoded media content, each degradation metric value corresponding to a different degradation metric type. The method includes mapping each degradation metric value to a respective calibrated score to obtain a plurality of calibrated scores. The method includes determining an aggregated quality score of the transcoded media content based on the plurality of calibrated scores and an exponential weighting function. The exponential weighting function exponentiates each of the calibrated scores by a respective weighting exponent and aggregates the exponentiated calibrated scores.

Abstract: A machine learning model compression system and related techniques are described herein. The machine learning model compression system can intelligently remove certain parameters of a machine learning model, without introducing a loss in performance of the machine learning model. Various parameters of a machine learning model can be removed during compression of the machine learning model, such as one or more channels of a single-branch or multi-branch neural network, one or more branches of a multi-branch neural network, certain weights of a channel of a single-branch or multi-branch neural network, and/or other parameters. In some cases, compression is performed only on certain selected layers or branches of the machine learning model. Candidate filters from the selected layers or branches can be removed from the machine learning model in a way that preserves local features of the machine learning model.

Abstract: The invention provides the internal fixation system of multi-function adjustable spine posterior screw-rod. It not only includes the vertebral plate, but also includes the adjustable connecting rod, screw and lock nut. Among them, vertebral plate is curved, its internal cambered surface directly faces the spine, and external cambered surface of vertebral plate is equipped with a reinforcing rib. The vertebral plate is set with the perforative injecting hole, and the external cambered surface of vertebral plate is set with the located block. The surface of the located block is set with the concave threaded hole, and the located block on two sides of the threaded hole is set with the U-shaped bracket. The top of screw expands to form a locking block, which surface is set with the concave locking hole. The locking block on both sides of locking hole is set with the U-shaped locking groove.

Abstract: The invention provides the internal fixation system of spine posterior screw-plate, including the vertebral plate. The vertebral plate is curved, its internal cambered surface directly faces the spine, and external cambered surface of vertebral plate is equipped with a reinforcing rib. The vertebral plate is set with the perforative injecting hole. One side of vertebral plate is fixed with a fixed connecting plate, and the end of the fixed connecting plate away from the vertebral plate is set with the first regulating hole. The bottom of the fixed connecting plate on two sides of the first regulating hole is set with n-shaped caulking groove.