Abstract: A system uses a neural network based model to perform scene text recognition. The system achieves high accuracy of prediction of text from scenes based on a neural network architecture that uses double attention mechanism. The neural network based model includes a convolutional neural network component that outputs a set of visual features and an attention extractor neural network component that determines attention scores based on the visual features. The visual features and the attention scores are combined to generate mixed features that are provided as input to a character recognizer component that determines a second attention score and recognizes the characters based on the second attention score. The system trains the neural network based model by adjusting the neural network parameters to minimize a multi-class gradient harmonizing mechanism (GHM) loss. The multi-class GHM loss varies based on a level of difficulty of the sample.

Abstract: A method for querying information includes: acquiring an information query instruction; obtaining a query intention by performing intention identification on the works information query instruction; determining a type of the query intention in a plurality of intention types; obtaining an entity detection result by detecting whether the query intention contains an author entity and a painting entity; acquiring a query result based on the query intention and reference information, wherein the reference information includes the type of the query intention and the entity detection result, and the query result includes at least one information of an image, an audio and a text; and displaying the query result.

Abstract: A voice question and answer method and device, a computer readable storage medium, and an electronic device are described. The method comprises: receiving question voice information, and obtaining question text information according to the question voice information; performing at least one of general semantic analysis processing and dedicated semantic analysis processing on the question text information to generate an analysis result; and obtaining answer information according to the analysis result. The general semantic analysis is used for semantic analysis in the general field, and the dedicated semantic analysis is used for semantic analysis in the art field.

Abstract: A multilayer board includes a laminated insulating body, signal conductors inside the laminated insulating body and extending in a transmission direction, and ground conductors sandwiching each of the signal conductors in a lamination direction via the insulating base material layers. The multilayer board includes a parallel extending portion in which the signal conductors extend parallel and that includes signal conductors arranged separately from each other in a direction orthogonal to the transmission direction in a planar view in the lamination direction, and a signal conductor overlapping with the signal conductor in a planar view in the lamination direction and arranged separately from the signal conductor in the lamination direction. The parallel extending portion includes first and second regions arranged separately in a direction orthogonal to the transmission direction in a planar view in the lamination direction.

Abstract: A method for querying information includes: acquiring an information query instruction; obtaining a query intention by performing intention identification on the works information query instruction; determining a type of the query intention in a plurality of intention types; obtaining an entity detection result by detecting whether the query intention contains an author entity and a painting entity; acquiring a query result based on the query intention and reference information, wherein the reference information includes the type of the query intention and the entity detection result, and the query result includes at least one information of an image, an audio and a text; and displaying the query result.

Abstract: The present invention is directed to positioning a plurality of eye feature points in the target image to determine position coordinates of the plurality of eye feature points normalizing the position coordinates of the plurality of eye feature points to obtain normalized position feature data and determining an eye state in the target image based on the position feature data.

Abstract: A transmission line substrate includes a stacked body that includes insulating base materials, first and second signal lines, and first and second ground conductors. The second signal line is provided on a layer different from the layer of the first signal line and extends in parallel with the first signal line. The first ground conductor is provided on the same layer as the layer of the second signal line and overlapped with the first signal line when viewed in the Z-axis direction. The second ground conductor is provided on the same layer as the layer of the first signal line and overlapped with the second signal line when viewed in the Z-axis direction. A first transmission line includes the first signal line, the first ground conductor, and an insulating base material, and a second transmission line includes the second signal line, the second ground conductor, and the insulating base material.

Abstract: A fingertip detection method, a fingertip detection device and a storage medium are disclosed. The fingertip detection method includes: determining a minimum-depth point in a hand area to be detected based on a depth image; determining a hand vertex in the hand area to be detected based on the depth image; determining a fingertip position based on the minimum-depth point and the hand vertex.

Abstract: A multilayer board includes a layered body including insulating base material layers that are laminated, and first and second signal lines, a first ground conductor including a first opening, a second ground conductor, a third ground conductor, and an interlayer connecting conductor. The first signal line overlaps the first opening when seen in a layering direction. The second signal line is provided on a layer different from a layer including the first signal line and includes a portion extending side by side with the first signal line when seen in the Z-axis direction. The first, second, and third ground conductors are connected by the interlayer connecting conductor. The third ground conductor is disposed on a layer including the first signal line or a layer positioned between the first signal line and the second signal line.

Abstract: An eye state detection method, including: acquiring a target image (101); positioning a plurality of eye feature points in the target image to determine position coordinates of the plurality of eye feature points (102); normalizing the position coordinates of the plurality of eye feature points to obtain normalized position feature data (103); and determining an eye state in the target image based on the position feature data (104). An eye state detection apparatus, a device and a medium are also provided.

Abstract: A transmission line substrate includes a stacked body that includes insulating base materials, first and second signal lines, and first and second ground conductors. The second signal line is provided on a layer different from the layer of the first signal line and extends in parallel with the first signal line. The first ground conductor is provided on the same layer as the layer of the second signal line and overlapped with the first signal line when viewed in the Z-axis direction. The second ground conductor is provided on the same layer as the layer of the first signal line and overlapped with the second signal line when viewed in the Z-axis direction. A first transmission line includes the first signal line, the first ground conductor, and an insulating base material, and a second transmission line includes the second signal line, the second ground conductor, and the insulating base material.

Abstract: A multilayer board includes a laminated insulating body, signal conductors inside the laminated insulating body and extending in a transmission direction, and ground conductors sandwiching each of the signal conductors in a lamination direction via the insulating base material layers. The multilayer board includes a parallel extending portion in which the signal conductors extend parallel and that includes signal conductors arranged separately from each other in a direction orthogonal to the transmission direction in a planar view in the lamination direction, and a signal conductor overlapping with the signal conductor in a planar view in the lamination direction and arranged separately from the signal conductor in the lamination direction. The parallel extending portion includes first and second regions arranged separately in a direction orthogonal to the transmission direction in a planar view in the lamination direction.

Abstract: A transmission line substrate includes a stacked body that includes insulating base materials, first and second signal lines, and first and second ground conductors. The second signal line is provided on a layer different from the layer of the first signal line and extends in parallel with the first signal line. The first ground conductor is provided on the same layer as the layer of the second signal line and overlapped with the first signal line when viewed in the Z-axis direction. The second ground conductor is provided on the same layer as the layer of the first signal line and overlapped with the second signal line when viewed in the Z-axis direction. A first transmission line includes the first signal line, the first ground conductor, and an insulating base material, and a second transmission line includes the second signal line, the second ground conductor, and the insulating base material.

Abstract: A voice question and answer method and device, a computer readable storage medium, and an electronic device are described. The method comprises: receiving question voice information, and obtaining question text information according to the question voice information; performing at least one of general semantic analysis processing and dedicated semantic analysis processing on the question text information to generate an analysis result; and obtaining answer information according to the analysis result. The general semantic analysis is used for semantic analysis in the general field, and the dedicated semantic analysis is used for semantic analysis in the art field.

Abstract: A multilayer board includes a laminated insulating body, signal conductors inside the laminated insulating body and extending in a transmission direction, and ground conductors sandwiching each of the signal conductors in a lamination direction via the insulating base material layers. The multilayer board includes a parallel extending portion in which the signal conductors extend parallel and that includes signal conductors arranged separately from each other in a direction orthogonal to the transmission direction in a planar view in the lamination direction, and a signal conductor overlapping with the signal conductor in a planar view in the lamination direction and arranged separately from the signal conductor in the lamination direction. The parallel extending portion includes first and second regions arranged separately in a direction orthogonal to the transmission direction in a planar view in the lamination direction.

Abstract: A multilayer board includes a layered body including insulating base material layers that are laminated, and first and second signal lines, a first ground conductor including a first opening, a second ground conductor, a third ground conductor, and an interlayer connecting conductor. The first signal line overlaps the first opening when seen in a layering direction. The second signal line is provided on a layer different from a layer including the first signal line and includes a portion extending side by side with the first signal line when seen in the Z-axis direction. The first, second, and third ground conductors are connected by the interlayer connecting conductor. The third ground conductor is disposed on a layer including the first signal line or a layer positioned between the first signal line and the second signal line.

Abstract: A multilayer board includes a layered body including insulating base material layers that are laminated, and first and second signal lines, a first ground conductor including a first opening, a second ground conductor, a third ground conductor, and an interlayer connecting conductor. The first signal line overlaps the first opening when seen in a layering direction. The second signal line is provided on a layer different from a layer including the first signal line and includes a portion extending side by side with the first signal line when seen in the Z-axis direction. The first, second, and third ground conductors are connected by the interlayer connecting conductor. The third ground conductor is disposed on a layer including the first signal line or a layer positioned between the first signal line and the second signal line.

Abstract: The present application provides a gesture recognition method, a device, an apparatus and a storage medium. The gesture recognition method includes: acquiring coordinates of a center point of a gesture in an ith frame of image; determining whether the center point of the gesture in the ith frame of image is within a preset region; if yes, determining that coordinates of an actual center point of the gesture in the ith frame of image are coordinates of an actual center point of the gesture in the (i?1)th frame of image; wherein i is an integer greater than or equal to 2, and the preset region is a region taking the actual center point of the gesture in the (i?1)th frame of image as a center; and performing a dynamic-gesture recognition according to coordinates of an actual center point of the gesture in each frame of image.

Abstract: A fingertip detection method, a fingertip detection device and a storage medium are disclosed. The fingertip detection method includes: determining a minimum-depth point in a hand area to be detected based on a depth image; determining a hand vertex in the hand area to be detected based on the depth image; determining a fingertip position based on the minimum-depth point and the hand vertex.

Abstract: A resin multilayer substrate includes a substrate main body including first, second, and third wiring portions connected to one another by a connecting portion. First, second and third external connection terminals are respectively included in the first, second and third wiring portions. The first external connection terminal includes a conductor exposed at a surface of the substrate main body. The second and third external connection terminals include connectors mounted on conductors on the surface of the substrate main body. An auxiliary mounting conductor is disposed between the first external connection terminal and the second and third external connection terminals on the surface of the substrate main body.