Abstract: In a facial expression recognition method, facial key points are identified as graph nodes. A facial graph structure for a first image is constructed with edges between pairs of the graph nodes based on relationships between the facial key points corresponding to the graph nodes. A first feature of a facial texture is extracted from color information of pixels in the first image. A second feature of the first image is extracted by processing the facial graph structure using a graph neural network (GNN). The first feature and the second feature are combined, to obtain a fused feature. A first expression type of a face in the first image that corresponds to the fused feature is determined. The first expression type is determined from a plurality of facial expression types.

Abstract: A facial expression recognition method includes extracting a first feature from color information of pixels in a first image, and extracting a second feature of facial key points from the first image. The method further includes combining the first feature and the second feature, to obtain a fused feature, and determining, by processing circuitry of an electronic device, a first expression.

Abstract: A model training method and apparatus for image recognition, and a non-transitory storage medium are provided. The model training method includes: obtaining a multi-label image training set including a plurality of training images each annotated with a plurality of sample labels; selecting target training images from the multi-label image training set for training a current model; performing label prediction on each target training image using the current model, to obtain a plurality of predicted labels of the each target training image; obtaining a cross-entropy loss function corresponding to the plurality of sample labels of the each target training image, a positive label loss being greater than a negative label loss and having a weight greater than 1; converging the predicted labels and the sample labels of the each target training image according to the cross-entropy loss function, and updating parameters of the current model, to obtain a trained model.

Abstract: A computer device obtains a first face image (IMA) and a second face image (IFA). The device obtains M first image blocks corresponding to facial features from the first face image (IMA), and obtains N second image blocks corresponding to facial features from the second face image (IFA). The device transforms the M first image blocks and the N second image blocks to a feature space to generate M first feature blocks and N second feature blocks. The device selects a subset of the first feature blocks and a subset of the second feature blocks according to a specified control vector. The device generates a first composite feature map based the selected subset of the first feature blocks and the selected subset of the second feature blocks. The device inversely transforms the first composite feature map back to an image space to generate a third face image.

Abstract: A method of establishing an image set for image recognition includes obtaining a single-label image set comprising an image annotated with a single label, and a multi-label image set comprising an image annotated with a plurality of labels; converting content of each label into a corresponding word identifier according to a semantic network, to obtain a word identifier set, a converted single-label image set, and a converted multi-label image set; and constructing a hierarchical semantic structure according to the word identifier set and the semantic network. The method also includes performing label supplementation on the image in the converted single-label image set to obtain a supplemented single-label image set; performing label supplementation on the supplemented single-label image set to obtain a final supplemented image set; and establishing a target multi-label image set to train an image recognition model by using the target multi-label image set.

Abstract: Aspects of the disclosure are directed to a training method and apparatus of an adversarial attack model, a generating method and apparatus of an adversarial image, an electronic device, and a storage medium. The adversarial attack model can include a generator network, and the training method can include using the generator network to generate an adversarial attack image based on a training digital image, and performing an adversarial attack on a target model based on the adversarial attack image, to obtain an adversarial attack result. The training method can further include obtaining a physical image corresponding to the training digital image, and training the generator network based on the training digital image, the adversarial attack image, the adversarial attack result, and the physical image.

Abstract: A facial expression recognition method includes extracting a first feature from color information of pixels in a first image, and extracting a second feature of facial key points from the first image.

Abstract: A computer device obtains a first face image (IMA) and a second face image (IFA). The device obtains M first image blocks corresponding to facial features from the first face image (IMA), and obtains N second image blocks corresponding to facial features from the second face image (IFA). The device transforms the M first image blocks and the N second image blocks to a feature space to generate M first feature blocks and N second feature blocks. The device selects a subset of the first feature blocks and a subset of the second feature blocks according to a specified control vector. The device generates a first composite feature map based the selected subset of the first feature blocks and the selected subset of the second feature blocks. The device inversely transforms the first composite feature map back to an image space to generate a third face image.

Abstract: A model training method and apparatus for image recognition, and a non-transitory storage medium are provided. The model training method includes: obtaining a multi-label image training set including a plurality of training images each annotated with a plurality of sample labels; selecting target training images from the multi-label image training set for training a current model; performing label prediction on each target training image using the current model, to obtain a plurality of predicted labels of the each target training image; obtaining a cross-entropy loss function corresponding to the plurality of sample labels of the each target training image, a positive label loss being greater than a negative label loss and having a weight greater than 1; converging the predicted labels and the sample labels of the each target training image according to the cross-entropy loss function, and updating parameters of the current model, to obtain a trained model.

Abstract: A method of establishing an image set for image recognition includes obtaining a single-label image set comprising an image annotated with a single label, and a multi-label image set comprising an image annotated with a plurality of labels; converting content of each label into a corresponding word identifier according to a semantic network, to obtain a word identifier set, a converted single-label image set, and a converted multi-label image set; and constructing a hierarchical semantic structure according to the word identifier set and the semantic network. The method also includes performing label supplementation on the image in the converted single-label image set to obtain a supplemented single-label image set; performing label supplementation on the supplemented single-label image set to obtain a final supplemented image set; and establishing a target multi-label image set to train an image recognition model by using the target multi-label image set.

Abstract: Disclosed are a smart television playing method and a smart television playing device, applied to a smart television of the WebKit-based WebOS, the smart television playing method including: when the smart television is turned on, starting a WebKit kernel process based on a Linux kernel and a driver layer; starting a state management daemon to detect a control command received by the smart television; and sending the control command to a daemon corresponding to the control command via the WebKit kernel process, allowing the daemon to perform control operation corresponding to the control command.

Abstract: Disclosed are a smart television playing method and a smart television playing device, applied to a smart television of the WebKit-based WebOS, the smart television playing method including: when the smart television is turned on, starting a WebKit kernel process based on a Linux kernel and a driver layer; starting a state management daemon to detect a control command received by the smart television; and sending the control command to a daemon corresponding to the control command via the WebKit kernel process, allowing the daemon to perform control operation corresponding to the control command.