Abstract: The embodiments provide an image data generation method, which includes that: multiple virtual three-dimensional prop models respectively corresponding to multiple kinds of table game props are acquired, the table game prop being a game tool used in a table game scene; in a virtual three-dimensional table game scene, at least one virtual three-dimensional prop model including at least one kind of table game prop is randomly determined from the multiple virtual three-dimensional prop models; the at least one virtual three-dimensional prop model is overlaid to the virtual three-dimensional table game scene to form a virtual target game scene; and planar projection processing is performed on the virtual target game scene to obtain two-dimensional image data including the at least one kind of table game prop. The embodiments also disclose an image data generation apparatus, an electronic device, and a computer-readable storage medium.

Abstract: Image identification methods and apparatuses, image generation methods and apparatuses, and neural network training methods and apparatuses are provided. In one aspect, an image identification method includes: obtaining a first image including a physical stack formed by stacking one or more first physical objects, and obtaining, by inputting the first image to a first neural network, category information of each of the one or more first physical objects output by the first neural network. The first neural network is pre-trained with a second image generated based on a virtual stack that is generated by stacking a three-dimensional model of one or more second physical objects.

Abstract: The present disclosure relates to an image retrieval method and apparatus. The method includes: obtaining an image group including a query image and at least one candidate image; calculating an intermediate similarity between any two images in the image group; performing multi-scale feature fusion based on the intermediate similarity between the any two images to obtain a final similarity between the query image and each candidate image; and determining a target image corresponding to the query image from each candidate image based on the final similarity. The present disclosure can improve precision and robustness of image retrieval.

Abstract: The present disclosure relates to a network training method and device, an image processing method and device, the method comprising: performing pixel shuffling on a first image in a training set to obtain a second image, wherein the first image is an image subjected to pixel shuffling; performing, by a feature extraction network of a neural network, feature extraction on the first image to obtain a first image feature, and performing, by a feature extraction network, feature extraction on the second image to obtain a second image feature; performing, by a recognition network of the neural network, recognition on the first image feature to obtain a recognition result of the first image; and training the neural network according to the recognition result, the first image feature and the second image feature. Embodiments of the present disclosure enable improvement of recognition precision of neural networks.

Abstract: Methods, devices, systems, and apparatus for target object identification are provided. In one aspect, a method includes: performing classification on a to-be-identified target object in a target image to determine a prediction category of the to-be-identified target object, determining whether the prediction category is correct according to a hidden layer feature for the to-be-identified target object, and outputting prompt information in response to the prediction category being incorrect.

Abstract: The present disclosure relates to a network training method and device, an image processing method and device, the method comprising: performing pixel shuffling on a first image in a training set to obtain a second image, wherein the first image is an image subjected to pixel shuffling; performing, by a feature extraction network of a neural network, feature extraction on the first image to obtain a first image feature, and performing, by a feature extraction network, feature extraction on the second image to obtain a second image feature; performing, by a recognition network of the neural network, recognition on the first image feature to obtain a recognition result of the first image; and training the neural network according to the recognition result, the first image feature and the second image feature. Embodiments of the present disclosure enable improvement of recognition precision of neural networks.

Abstract: Methods, apparatuses, devices, program products, and media can improve the accuracy rate of searching for a target person. The method includes: obtaining an image of the target person; searching a face image library by using the image of the target person to obtain a first face image template matching the image of the target person, where the face image library includes a plurality of face image templates; and obtaining, according to the first face image template and a pedestrian image library, at least one target pedestrian image template matching the image of the target person, where the pedestrian image library includes a plurality of pedestrian image templates.

Abstract: The present disclosure relates to an image retrieval method and apparatus. The method includes: obtaining an image group including a query image and at least one candidate image; calculating an intermediate similarity between any two images in the image group; performing multi-scale feature fusion based on the intermediate similarity between the any two images to obtain a final similarity between the query image and each candidate image; and determining a target image corresponding to the query image from each candidate image based on the final similarity. The present disclosure can improve precision and robustness of image retrieval.

Abstract: A key point detection method includes: obtaining first feature maps of a plurality of scales for an input image, scales of the first feature maps having a multiple relationship; performing forward processing on each first feature map through a first pyramid neural network to obtain second feature maps in one-to-one correspondence to the first feature maps, each second feature map having the same scale as that of its respective first feature map; performing reverse processing on each second feature map through a second pyramid neural network to obtain third feature maps in one-to-one correspondence to the second feature maps, each third feature map having the same scale as that of its respective second feature map; and performing feature fusion processing on each third feature map, and obtaining the position of each key point in the input image through the feature map subjected to the feature fusion processing.

Abstract: Methods, apparatuses, devices, program products, and media can improve the accuracy rate of searching for a target person. The method includes: obtaining an image of the target person; searching a face image library by using the image of the target person to obtain a first face image template matching the image of the target person, where the face image library includes a plurality of face image templates; and obtaining, according to the first face image template and a pedestrian image library, at least one target pedestrian image template matching the image of the target person, where the pedestrian image library includes a plurality of pedestrian image templates.