Abstract: The method for vehicle appearance feature recognition includes: multiple region segmentation results of a target vehicle are obtained from an image to be recognized; global feature data and multiple pieces of region feature data are extracted from the image to be recognized based on the multiple region segmentation results; and the global feature data and the multiple pieces of region feature data are fused to obtain appearance feature data of the target vehicle.

Abstract: An image question answering method includes: extracting a question feature representing a semantic meaning of a question, a global feature of an image, and a detection frame feature of a detection frame encircling an object in the image; obtaining a first weight of each of at least one area of the image and a second weight of each of at least one detection frame of the image according to question feature, global feature, and detection frame feature; performing weighting processing on global feature by using first weight to obtain an area attention feature of image; performing weighting processing on detection frame feature by using second weight to obtain a detection frame attention feature of image; and predicting an answer to question according to question feature, area attention feature, and detection frame attention feature.

Abstract: Target matching method and apparatus, electronic device, and storage medium, including: extracting feature vector of each frame in query image sequence and feature vector of each frame in candidate image sequence; determining self-expression feature vector of query image sequence, collaborative expression feature vector of the query image sequence, self-expression feature vector of candidate image sequence, and collaborative expression feature vector of candidate image sequence based on feature vector of each frame in query image sequence and feature vector of each frame in candidate image sequence; determining similarity feature vector between query image sequence and candidate image sequence based on self-expression feature vector of query image sequence, collaborative expression feature vector of query image sequence, self-expression feature vector of candidate image sequence, and collaborative expression feature vector of candidate image sequence; and determining matching result between query image sequen

Abstract: A method for identifying a target, a non-transitory computer-readable storage medium, and an electronic device include: acquiring a first image and a second image, the first image and the second image each including a target to be determined; generating a prediction path based on the first image and the second image, both ends of the prediction path respectively corresponding to the first image and the second image; and performing validity determination on the prediction path and determining, according to a determination result, whether the targets to be determined in the first image and the second image are the same target to be determined.

Abstract: Image detection methods and apparatuses, electronic devices and storage media include: down-sampling a second image to obtain a first image; determining at least one key sub-region in the second image for category detection; respectively extracting a feature of the first image and a feature of the at least one key sub-region; and generating a category detection result of the second image at least based on the extracted features.

Abstract: The present invention discloses a dynamic straightening method for a left/right tilt. The method includes: drawing an unevenness curve according to a distance from a shapemeter to a surface of a plate, where there are a plurality of unevenness curves; using a barycentric formula to obtain a first barycentric coordinate of each unevenness curve; calculating a tilt value of a straightening roll corresponding to each unevenness curve according to the first barycentric coordinate of each unevenness curve; determining an unevenness curve of a current straightening roll; adjusting the straightening roll according to the tilt value of the straightening roll corresponding to the unevenness curve, to straighten the plate; and going back to the step of determining an unevenness curve of a current straightening roll until the plate is totally straightened. The present invention improves plate straightening accuracy by dynamically adjusting parameters of the straightening roll.

Abstract: Example detecting methods and apparatus are described.

Abstract: The present disclosure relates to a neural network training method and apparatus, and an image processing method and apparatus. The training method includes: performing classification processing on a target image in a training set by means of a neural network to obtain a prediction classification result of the target image; and training the neural network according to the prediction classification result, and an initial category tag and a corrected category tag of the target image. Embodiments of the present disclosure may supervise the training process of the neural network by means of the initial category tag and the corrected category tag, and simplify the training process and a network structure.

Abstract: A 3D object detection method includes: obtaining two-dimensional (2D) coordinates of at least one predetermined key point of a target object in an image to be processed; constructing a pseudo 3D detection body of the target object in a 2D space according to the 2D coordinates of the at least one predetermined key point; obtaining depth information of a plurality of vertices of the pseudo 3D detection body; and determining a 3D detection body of the target object in a 3D space according to the depth information of the plurality of vertices of the pseudo 3D detection body.

Abstract: A method and device for cross-modal information retrieval, and a storage medium are provided. The method includes: acquiring first modal information and second modal information; performing feature fusion on a modal feature of the first modal information and a modal feature of the second modal information, and determining a first fused feature corresponding to the first modal information and a second fused feature corresponding to the second modal information; and determining the degree of similarity between the first modal information and the second modal information on the basis of the first fused feature and the second fused feature.

Abstract: The present disclosure provides an elevator control method, apparatus, electronic device, storage medium and system, which relate to artificial intelligence technology. The method includes: obtaining a user instruction, where the user instruction is determined by a speech device based on a user's speech content; recognizing the user instruction and converting the user instruction into an elevator control instruction; and controlling an elevator via the elevator control instruction. The elevator control method provided by the present disclosure enables the user to control the elevator through the speech device without touching the elevator, and thereby reducing potential safety risk caused by multiple people touching the elevator.

Abstract: Disclosed in embodiments of the present disclosure are an object three-dimensional detection method and apparatus, an intelligent driving control method and apparatus, a medium, and a device. The object three-dimensional detection method comprises: obtaining two-dimensional coordinates of a key point of a target object in an image to be processed; constructing a pseudo three-dimensional detection body of the target object according to the two-dimensional coordinates of the key point; obtaining depth information of the key point; and determining a three-dimensional detection body of the target object according to the depth information of the key point and the pseudo three-dimensional detection body.

Abstract: A method for cross-modal information retrieval is as follows. First modal information and second modal information are acquired. A first semantic feature of the first modal information and a first attention feature of the first modal information are determined according to a modal feature of the first modal information. A second semantic feature of the second modal information and a second attention feature of the second modal information are determined according to a modal feature of the second modal information. A similarity between the first modal information and the second modal information are determined based on the first attention feature, the second attention feature, the first semantic feature, and the second semantic feature.

Abstract: The present disclosure discloses a lateral transistor having a source region, a drain region, a gate near the source region side and a field dielectric positioned in or atop a portion of a well region between the drain region and the gate. The lateral transistor further includes a non-conductive field plate positioning layer positioned atop a portion of the field dielectric and separated laterally from the gate with a first lateral distance, a lateral conductive field plate positioned atop the non-conductive field plate positioning layer and separated laterally from the gate with a second lateral distance and a vertical trenched field plate contact extending vertically from a top surface of an interlayer dielectric layer through the interlayer dielectric layer to reach and contact with the lateral conductive field plate.

Abstract: Disclosed in embodiments of the present disclosure are an object three-dimensional detection method and apparatus, an intelligent driving control method and apparatus, a medium, and a device. The object three-dimensional detection method comprises: obtaining two-dimensional coordinates of a key point of a target object in an image to be processed; constructing a pseudo three-dimensional detection body of the target object according to the two-dimensional coordinates of the key point; obtaining depth information of the key point; and determining a three-dimensional detection body of the target object according to the depth information of the key point and the pseudo three-dimensional detection body.

Abstract: A vehicle lamp detection method includes: obtaining an image block including an image of a vehicle; and performing vehicle lamp detection on the image block by means of a deep neural network, to obtain a vehicle lamp detection result.

Abstract: Disclosed are a method and apparatus for object detection, an electronic device and a computer storage medium. The method includes: acquiring three-dimensional (3D) point cloud data; determining point cloud semantic features corresponding to the 3D point cloud data according to the 3D point cloud data; determining part location information of foreground points based on the point cloud semantic features; extracting at least one initial 3D bounding box based on the point cloud data; and determining a 3D bounding box for an object according to the point cloud semantic features corresponding to the point cloud data, the part location information of the foreground points and the at least one initial 3D bounding box.

Abstract: Embodiments of the present application disclose a binocular matching method, including: obtaining an image to be processed, where the image is a two-dimensional (2D) image including a left image and a right image; constructing a three-dimensional (3D) matching cost feature of the image by using extracted features of the left image and extracted features of the right image, where the 3D matching cost feature includes a group-wise cross-correlation feature, or includes a feature obtained by concatenating the group-wise cross-correlation feature and a connection feature; and determining the depth of the image by using the 3D matching cost feature. The embodiments of the present application also provide a binocular matching apparatus, a computer device, and a storage medium.

Abstract: A method for processing point cloud data includes: point cloud data in a target scene and weight vectors of a first discrete convolution kernel are obtained; interpolation processing is performed on the point cloud data based on the point cloud data and the weight vectors of the first discrete convolution kernel to obtain first weight data, the first weight data representing weights of allocation of the point cloud data to positions corresponding to the weight vectors of the first discrete convolution kernel; first discrete convolution processing is performed on the point cloud data based on the first weight data and the weight vectors of the first discrete convolution kernel to obtain a first discrete convolution result; and a spatial structure feature of at least part of point cloud data in the point cloud data is obtained based on the first discrete convolution result.

Abstract: The present disclosure relates to a network optimization method and apparatus, an image processing method and apparatus, and a storage medium. The network optimization method includes: obtaining an image sample group; obtaining a first feature and a second feature of an image in the image sample group, and obtaining a first classification result by using the first feature of the image; performing feature exchange processing on an image pair in the image sample group to obtain a new image pair; obtaining a first loss value of the first classification result, a second loss value of the new image pair, and a third loss value of first features and second features of the new image pair in a preset manner; and adjusting parameters of a neural network at least according to the first loss value, the second loss value, and the third loss value until a preset requirement is met.