Abstract: An image processing method, performed by a computer device, includes: obtaining an input image to be processed; performing face detection on the input image to obtain an input face image to be processed including at least one defect element relating to a skin element; and inputting the input face image into an image processing model to obtain a target face image corresponding to the input face image without a first defect element amongst the at least one defect element, wherein a training sample of the image processing model includes a first face image with a first face distortion degree less than a preset threshold and that is annotated with the first defect element.

Abstract: In an image optimization method, an image generation network, a to-be-optimized image, and a plurality of preset image features are obtained. A target feature is selected from the plurality of preset image features based on (i) the target feature and the to-be-optimized image and (ii) a preset similarity condition. The target feature and an initial offset parameter are input to the image generation network. The initial offset parameter is adjusted according to a difference between an output of the image generation network and the to-be-optimized image, to obtain a target offset parameter. The target feature and the target offset parameter are input to the image generation network, to generate an optimized image. Apparatus and non-transitory computer-readable storage medium counterpart embodiments are also contemplated.

Abstract: An action recognition method includes: obtaining original feature submaps of each of temporal frames on a plurality of convolutional channels by using a multi-channel convolutional layer; calculating, by using each of the temporal frames as a target temporal frame, motion information weights of the target temporal frame on the convolutional channels according to original feature submaps of the target temporal frame and original feature submaps of a next temporal frame, and obtaining motion information feature maps of the target temporal frame on the convolutional channels according to the motion information weights; performing temporal convolution on the motion information feature maps of the target temporal frame to obtain temporal motion feature maps of the target temporal frame; and recognizing an action type of a moving object in image data of the target temporal frame according to the temporal motion feature maps of the target temporal frame on the convolutional channels.

Abstract: A video processing method includes: obtaining a first video frame and a second video frame in a target video, the first video frame being a previous frame of the second video frame; inputting the first video frame and the second video frame to a target neural network, and obtaining a target intermediate video frame output by the target neural network, the target neural network being trained based on an optical flow distillation constraint and a feature consistency constraint; and interpolating the target intermediate video frame between the first video frame and the second video frame.

Abstract: The present subject matter discloses an action recognition method, apparatus and device, a storage medium, and a computer program product, belonging to the field of image recognition. Multiple video frames in a target video are obtained. Feature extraction is performed on the multiple video frames respectively according to multiple dimensions to obtain multiple multi-channel feature patterns. Each video frame corresponds to one multi-channel feature pattern. Each channel represents one dimension. An attention weight of each multi-channel feature pattern is determined based on a similarity between every two multi-channel feature patterns. The attention weight is used for representing a degree of correlation between a corresponding multi-channel feature pattern and an action performed by an object in the target video. A type of the action is determined based on the multiple multi-channel feature patterns and the determined multiple attention weights.

Abstract: An action recognition method includes: obtaining original feature submaps of each of temporal frames on a plurality of convolutional channels by using a multi-channel convolutional layer; calculating, by using each of the temporal frames as a target temporal frame, motion information weights of the target temporal frame on the convolutional channels according to original feature submaps of the target temporal frame and original feature submaps of a next temporal frame, and obtaining motion information feature maps of the target temporal frame on the convolutional channels according to the motion information weights; performing temporal convolution on the motion information feature maps of the target temporal frame to obtain temporal motion feature maps of the target temporal frame; and recognizing an action type of a moving object in image data of the target temporal frame according to the temporal motion feature maps of the target temporal frame on the convolutional channels.