An image classification method and apparatus, and a style transfer model training method and apparatus are provided, which are relate to the field of deep learning, cloud computing and computer vision in artificial intelligence. The image classification method comprises: inputting an image of a first style into a style transfer model, to obtain an image of a second style corresponding to the image of the first style; and inputting the image of the second style into an image classification model, to obtain a classification result of the image of the second style, wherein the style transfer model is obtained through training on the basis of a sample image of the first style and a sample image of the second style; and the image classification model is obtained through training on the basis of the sample image of the second style.

There are provided computing devices and methods, etc. to controllably transform an image of a face, including a high resolution image, to simulate continuous aging. Ethnicity-specific aging information and weak spatial supervision are used to guide the aging process defined through training a model comprising a GANs based generator. Aging maps present the ethnicity-specific aging information as skin sign scores or apparent age values. The scores are located in the map in association with a respective location of the skin sign zone of the face associated with the skin sign. Patch-based training, particularly in association with location information to differentiate similar patches from different parts of the face, is used to train on high resolution images while minimize resource usage.

An object information registration apparatus that registers information of a first object that is a reference object of object recognition holds a first object image that is an image of the first object and recognition method information related to the first object, selects one or more partial regions included in the first object image, sets a recognition method corresponding to each of the one or more partial regions, acquires feature information of each of the one or more partial regions from the first object image based on the set recognition method, and stores the one or more partial regions, the set recognition method, and the acquired feature information in the recognition method information in association with each other.

A method is provided for Cross Video Temporal Difference (CVTD) learning. The method adapts a source domain video to a target domain video using a CVTD loss. The source domain video is annotated, and the target domain video is unannotated. The CVTD loss is computed by quantizing clips derived from the source and target domain videos by dividing the source domain video into source domain clips and the target domain video into target domain clips. The CVTD loss is further computed by sampling two clips from each of the source domain clips and the target domain clips to obtain four sampled clips including a first source domain clip, a second source domain clip, a first target domain clip, and a second target domain clip. The CVTD loss is computed as |(second source domain clip−first source domain clip)−(second target domain clip−first target domain clip)|.

A method of classifying a media includes receiving a media file and extracting therefrom first and second data streams including first and second media content, respectively, the media content being associated with the media item. First and second feature vectors describing the first and second media content, respectively, are generated. At least a first single feature vector representing the first sequence of first feature vectors and the second sequence of second feature vectors is generated, or at least a first single feature vector representing at least the first sequence of first feature vectors is generated. A second feature vector representing at least the second sequence of second feature vectors is generated. A probability vector from the first single feature vector, or from the first and second single feature vectors is generated. A user profile suitability class is assigned to the media item based on the probability vector.

An object position region detection unit of an object detection device detects a position region of an object included in an input image on the basis of a first class definition in which a plurality of classes is defined in advance. A class identification unit identifies a class out of a plurality of classes to which the object belongs on the basis of the first class definition. An object detection result output unit outputs class information of the object as a detection result of the object on the basis of a second class definition in which a plurality of classes is defined in advance, the second class definition associated with the first class definition. The number of classes defined in the second class definition is smaller than the number of classes defined in the first class definition.

There is provided a method of image classification. The method includes: providing a set of category mapping discriminators, each corresponding to a respective category, wherein each category mapping discriminator of the set of category mapping discriminators is configured for discriminating features relating to input images that belong to the respective category of the category mapping discriminator; extracting a plurality of features from an input image using a machine learning model; determining, for each of the set of category mapping discriminators, an output value based on the plurality of extracted features using the category mapping discriminator; and determining a classification of the input image based on the output values of the set of category mapping discriminators.

The present disclosure provides an apparatus and method for evaluate the quality of a three dimensional (3D) point cloud. The apparatus comprises an image segmenter to generate a segmented two-dimensional (2D) image for each of the plurality of images; a 2D mask generator to generate a 2D mask for each of the plurality of images from the 3D point cloud; a comparator to compare the segmented 2D image with the 2D mask to obtain a comparison result for each image; and an evaluator to evaluate the quality of the 3D point cloud based on aggregated comparison results for the plurality of images.

A weakly supervised image semantic segmentation method based on an intra-class discriminator includes: constructing two levels of intra-class discriminators for each image-level class to determine whether pixels belonging to the image class belong to a target foreground or a background, and using weakly supervised data for training; generating a pixel-level image class label based on the two levels of intra-class discriminators, and generating and outputting a semantic segmentation result; and further training an image semantic segmentation module or network by using the label to obtain a final semantic segmentation model for an unlabeled input image. By means of the new method, intra-class image information implied in a feature code is fully mined, foreground and background pixels are accurately distinguished, and performance of a weakly supervised semantic segmentation model is significantly improved under the condition of only relying on an image-level annotation.

An image processing apparatus includes an image synthesizer configured to correct input images based on first-correction data to generate corrected images, and to generate a synthesized image by stitching the corrected images together, a determiner configured to determine whether the corrected images are appropriately stitched together in the synthesized image by using a first-trained model learned whether images are appropriately stitched together, a second-correction-data generator configured to generate second-correction data by supplying the input images to a second-trained model learned relationships between correction data used to correct source images to generate corrected images appropriately stitched together and the source images, and an image updater configured to output the synthesized image when a determination result of the determiner is affirmative and output an updated synthesized image generated by causing the image synthesizer to update the synthesized image based on the second-correction data when the determination result of the determiner is negative.