Abstract: Systems, methods, and computer-executable instructions for synthesizing facts from multiple sources. A user search string associated with a topic is received. Queries associated with the user search string are generated. Website content is queried, using the plurality of queries associated with the user search string, to generate results. The results are ranked based on a first feature. The results are filtered based on the first feature to generate intermediate results. The intermediate results are ranked based on a second feature. The second feature is most costly to calculate than the first feature. The filtered intermedia results are filtered based on the second feature to generate final results. Distinct facts from the final results are determined. The distinct facts include content from different URLs. The distinct facts associated with the topic are returned.

Abstract: Examples are disclosed herein that relate to automatically calibrating cameras based on human detection. One example provides a computing system comprising instructions executable to receive image data comprising depth image data and two-dimensional image data of a space from a camera, detect a person in the space via the image data, determine a skeletal representation for the person via the image data, determine over a period of time a plurality of locations at which a reference point of the skeletal representation is on a ground area in the image data, determine a ground plane of the three-dimensional representation based upon the plurality of locations at which the reference point of the skeletal representation is on the ground area in the image data, and track a location of an object within the space relative to the ground plane.

Abstract: The disclosure discloses a motor driving system converter fault diagnosis method based on adaptive sparse filtering, and belongs to the field of driving system fault diagnosis. The disclosure applies an unsupervised learning algorithm to an application scene of converter fault diagnosis. Effective features are automatically extracted from original data, and the problem of manual feature design based on expert knowledge is solved. Meanwhile, in consideration of current fundamental period change caused by different rotation speed working conditions, rotation speed feedback is introduced, secondary sampling is carried out on current sampled at a constant frequency, it is ensured that the length of a signal input into the deep sparse filtering network is one fundamental wave period, redundant information is better removed from original data, the calculation burden is relieved, and the accuracy and rapidity of the diagnosis algorithm are improved to a certain extent.

Abstract: Techniques for improved camera calibration are disclosed. An image is analyzed to identify a first set of key points for an object. A virtual object is generated. The virtual object has a second set of key points. A reprojected version of the second set is fitted to the first set in 2D space until a fitting threshold is satisfied. To do so, a 3D alignment of the second set is generated in an attempt to fit (e.g., in 2D space) the second set to the first set. Another operation includes reprojecting the second set into 2D space. In response to comparing the reprojected second set to the first set, another operation includes determining whether a fitting error between those sets satisfies the fitting threshold. A specific 3D alignment of the second set is selected. The camera is calibrated based on resulting reprojection parameters.

Abstract: An object re-identifier. For each of a plurality of frames of a video, a quality of the frame is assessed and a confidence that a previously-recognized object is present in the frame is determined. The determined confidence for the frame is weighted based on the assessed quality of the frame such that frames with higher relative quality are weighted more heavily than frames with lower relative quality. An overall confidence that the previously-recognized object is present in the video is assessed based on the weighted determined confidences.

Abstract: A computing system is provided. The computing system includes a processor configured to execute a convolutional neural network that has been trained, the convolutional neural network including a backbone network that is a concatenated pyramid network, a plurality of first head neural networks, and a plurality of second head neural networks. At the backbone network, the processor is configured to receive an input image as input and output feature maps extracted from the input image. The processor is configured to: process the feature maps using each of the first head neural networks to output corresponding keypoint heatmaps; process the feature maps using each of the second head neural networks to output corresponding part affinity field heatmaps; link the keypoints into one or more instances of virtual skeletons using the part affinity fields; and output the instances of the virtual skeletons.

Abstract: Provide are a reticle transfer device and an exposure system. The reticle transfer device includes a bearing member, a light source, a light detector and a controller. The bearing member is configured to bear the reticle, and the light source is configured to emit irradiation light to the reticle and form reflected light. The light detector is configured to obtain the reflected light and generate a light detection signal. The controller is configured to determine whether particulate matter exists on a surface of the reticle based on the light detection signal. The reticle transfer device can determine whether particulate matter exists on the surface of the reticle in real time based on the light detection signal.

Abstract: Techniques for improved camera calibration are disclosed. An image is analyzed to identify a first set of key points for an object. A virtual object is generated. The virtual object has a second set of key points. A reprojected version of the second set is fitted to the first set in 2D space until a fitting threshold is satisfied. To do so, a 3D alignment of the second set is generated in an attempt to fit (e.g., in 2D space) the second set to the first set. Another operation includes reprojecting the second set into 2D space. In response to comparing the reprojected second set to the first set, another operation includes determining whether a fitting error between those sets satisfies the fitting threshold. A specific 3D alignment of the second set is selected. The camera is calibrated based on resulting reprojection parameters.

Abstract: To improve the accuracy and efficiency of object detection through computer digital image analysis, the detection of some objects can inform the sub-portion of the digital image to which subsequent computer digital image analysis is directed to detect other objects. In such a manner object detection can be made more efficient by limiting the image area of a digital image that is analyzed. Such efficiencies can represent both computational efficiencies and communicational efficiencies arising due to the smaller quantity of digital image data that is analyzed. Additionally, the detection of some objects can render the detection of other objects more accurate by adjusting confidence thresholds based on the detection of those related objects. Relationships between objects can be utilized to inform both the image area on which subsequent object detection is performed and the confidence level of such subsequent object detection.

Abstract: A computing system is provided. The computing system includes a processor configured to execute a convolutional neural network that has been trained, the convolutional neural network including a backbone network that is a concatenated pyramid network, a plurality of first head neural networks, and a plurality of second head neural networks. At the backbone network, the processor is configured to receive an input image as input and output feature maps extracted from the input image. The processor is configured to: process the feature maps using each of the first head neural networks to output corresponding keypoint heatmaps; process the feature maps using each of the second head neural networks to output corresponding part affinity field heatmaps; link the keypoints into one or more instances of virtual skeletons using the part affinity fields; and output the instances of the virtual skeletons.

Abstract: A synthesis method for low-racemization impurity liraglutide comprises the following steps: performing synthesis to obtain a propeptide, coupling 2 to 5 peptides comprising Thr-Phe on the propeptide by using a solid-phase synthesis method; further, performing solid-phase synthesis to obtain a liraglutide resin; the liraglutide resin is cracked after modification, or the liraglutide resin is directly cracked, purified and frozen dry, so as to obtain the liraglutide.

Abstract: Techniques for improved camera calibration are disclosed. An image is analyzed to identify a first set of key points for an object. A virtual object is generated. The virtual object has a second set of key points. A reprojected version of the second set is fitted to the first set in 2D space until a fitting threshold is satisfied. To do so, a 3D alignment of the second set is generated in an attempt to fit (e.g., in 2D space) the second set to the first set. Another operation includes reprojecting the second set into 2D space. In response to comparing the reprojected second set to the first set, another operation includes determining whether a fitting error between those sets satisfies the fitting threshold. A specific 3D alignment of the second set is selected. The camera is calibrated based on resulting reprojection parameters.

Abstract: A method for environment-specific training of a machine learning model, comprises receiving, for a local environment, a data stream including a plurality of sequential data snippets. Programmed labels are generated for each data snippet using a student version of a machine learning model. A portion of data snippets and associated programmed labels are selected and uploaded to a server-side computing device for evaluation by a teacher version of the machine learning model. An environment-specific training update is received from the server-side computing device. This training update is based on a comparison of the selected programmed labels and pseudolabels generated for the selected portion of data snippets by the teacher version. The environment-specific training update is applied to the student version to generate an updated student version. The updated student version of the machine learning model is then used to generate programmed labels for newly received data snippets.

Abstract: Improved techniques for determining an object's 3D orientation. An image is analyzed to identify a 2D object and a first set of key points. The first set defines a first polygon. A 3D virtual object is generated. This 3D virtual object has a second set of key points defining a second polygon representing an orientation of the 3D virtual object. The second polygon is rotated a selected number of times. For each rotation, each rotated polygon is reprojected into 2D space, and a matching score is determined between each reprojected polygon and the first polygon. A specific reprojected polygon is selected whose corresponding matching score is lowest. The orientation of the 3D virtual object is set to an orientation corresponding to the specific reprojected polygon. Based on the orientation of the 3D virtual object, an area of focus of the 2D object is determined.

Abstract: A computing system is provided. The computing system includes a processor configured to execute a convolutional neural network that has been trained, the convolutional neural network including a backbone network that is a concatenated pyramid network, a plurality of first head neural networks, and a plurality of second head neural networks. At the backbone network, the processor is configured to receive an input image as input and output feature maps extracted from the input image. The processor is configured to: process the feature maps using each of the first head neural networks to output corresponding keypoint heatmaps; process the feature maps using each of the second head neural networks to output corresponding part affinity field heatmaps; link the keypoints into one or more instances of virtual skeletons using the part affinity fields; and output the instances of the virtual skeletons.

Abstract: A neural architecture search (NAS) with a weak predictor comprises: receiving network architecture scoring information; iteratively sampling a search space, wherein the sampling comprises: generating a set of candidate architectures within the search space; learning a first predictor; evaluating performance of the candidate architectures; and based on at least the performance of the set of candidate architectures and the network architecture scoring information, refining the search space to a smaller search space; based on at least the network architecture scoring information, thresholding the performance of candidate architectures to determine scored output candidate architectures; and reporting the scored output candidate architectures. In some examples, the candidate architectures each comprise a machine learning (ML) model, for example a neural network (NN).

Abstract: A computer device for automatic feature detection comprises a processor, a communication device, and a memory configured to hold instructions executable by the processor to instantiate a dynamic convolution neural network, receive input data via the communication network, and execute the dynamic convolution neural network to automatically detect features in the input data. The dynamic convolution neural network compresses the input data from an input space having a dimensionality equal to a predetermined number of channels into an intermediate space having a dimensionality less than the number of channels. The dynamic convolution neural network dynamically fuses the channels into an intermediate representation within the intermediate space and expands the intermediate representation from the intermediate space to an expanded representation in an output space having a higher dimensionality than the dimensionality of the intermediate space.

Abstract: An object re-identifier. For each of a plurality of frames of a video, a quality of the frame is assessed and a confidence that a previously-recognized object is present in the frame is determined. The determined confidence for the frame is weighted based on the assessed quality of the frame such that frames with higher relative quality are weighted more heavily than frames with lower relative quality. An overall confidence that the previously-recognized object is present in the video is assessed based on the weighted determined confidences.

Abstract: The disclosure provides an N-phase N+1 bridge arm inverter, including: N+1 bridge arms, wherein each of the bridge arms includes an upper bridge arm power switching device and a lower bridge arm power switching device, upper node of the upper bridge arm power switching device in each of the bridge arms is connected to a DC bus voltage, lower node of the lower bridge arm power switching device is connected to a power ground, and lower node of the upper bridge arm power switching device is connected to upper node of the lower bridge arm power switching device as an output node of the bridge arm. N is a total phase number of a motor, N is an odd number, and N is greater than 3.

Abstract: Improved techniques for determining an object's 3D orientation. An image is analyzed to identify a 2D object and a first set of key points. The first set defines a first polygon. A 3D virtual object is generated. This 3D virtual object has a second set of key points defining a second polygon representing an orientation of the 3D virtual object. The second polygon is rotated a selected number of times. For each rotation, each rotated polygon is reprojected into 2D space, and a matching score is determined between each reprojected polygon and the first polygon. A specific reprojected polygon is selected whose corresponding matching score is lowest. The orientation of the 3D virtual object is set to an orientation corresponding to the specific reprojected polygon. Based on the orientation of the 3D virtual object, an area of focus of the 2D object is determined.