Provided are a label identification method and apparatus, a device, and a medium. The method includes: obtaining a target feature of a first image, in which the target feature characterizes a visual feature of the first image and a word feature of at least one label; and identifying a label of the first image from the at least one label based on the target feature. By characterizing the visual feature of the first image and the target feature of the word feature of the at least one label, the label of the first image is identified from the at least one label. Thus, identification accuracy of the label can be improved.

A method for generating at least one representation of a bird's eye view of at least a part of the environment of a system, based on at least one or more digital image representations obtained from at least one or more cameras of the system. The method comprises: a) obtaining a digital image representation (2) advantageously representing a single digital image, together with at least one camera parameter of the camera that captured the image, b) extracting at least one feature from the digital image representation, wherein features are generated in different scales, c) transforming the at least one feature from the image space into a bird's eye view space, to obtain at least one bird's eye view feature.

A method for detecting boxes includes receiving a plurality of image frame pairs for an area of interest including at least one target box. Each image frame pair includes a monocular image frame and a respective depth image frame. For each image frame pair, the method includes determining corners for a rectangle associated with the at least one target box within the respective monocular image frame. Based on the determined corners, the method includes the following: performing edge detection and determining faces within the respective monocular image frame; and extracting planes corresponding to the at least one target box from the respective depth image frame. The method includes matching the determined faces to the extracted planes and generating a box estimation based on the determined corners, the performed edge detection, and the matched faces of the at least one target box.

The present invention extends to methods, systems, and computer program products for classifying time series image data. Aspects of the invention include encoding motion information from video frames in an eccentricity map. An eccentricity map is essentially a static image that aggregates apparent motion of objects, surfaces, and edges, from a plurality of video frames. In general, eccentricity reflects how different a data point is from the past readings of the same set of variables. Neural networks can be trained to detect and classify actions in videos from eccentricity maps. Eccentricity maps can be provided to a neural network as input. Output from the neural network can indicate if detected motion in a video is or is not classified as an action, such as, for example, a hand gesture.

The present disclosure relates to the technical field of image processing, and in particular to an image description generation method, apparatus and system, and a medium and an electronic device. The method comprises: acquiring one or more image region features in a target image, and obtaining a current input vector by performing a mean pooling on the image region features; obtaining respective outer product vectors of the image region features by respectively linearly fusing the current input vector and each of the image region features; calculating, based on the respective outer product vectors of the image region features, an attention distribution of the image region features in a spatial dimension and an attention distribution of the image region features in a channel dimension; and generating an image description of the target image based on the attention distribution of the image region features in the spatial dimension and the attention distribution of the image region features in the channel dimension.

A method for performing a computer-aided diagnosis (CAD) includes: acquiring a medical image set; generating a three-dimensional (3D) tumor distance map corresponding to the medical image set, each voxel of the tumor distance map representing a distance from the voxel to a nearest boundary of a primary tumor present in the medical image set; and performing neural-network processing of the medical image set to generate a predicted probability map to predict presence and locations of oncology significant lymph nodes (OSLNs) in the medical image set, wherein voxels in the medical image set are stratified and processed according to the tumor distance map.

A fingerprint anti-counterfeiting method and an electronic device are provided. The fingerprint anti-counterfeiting method includes: After detecting a fingerprint input action of a user, an electronic device obtains a fingerprint image generated by the fingerprint input action, and obtains a vibration-sound signal generated by the fingerprint input action. The device determines, based on a fingerprint anti-counterfeiting model, whether the fingerprint input action is performed by a true finger. The fingerprint anti-counterfeiting model is a multi-dimensional network model obtained through learning based on fingerprint images for training and corresponding vibration-sound signals. The fingerprint anti-counterfeiting method in embodiments of this application helps improve a protection capability of the electronic device for a fake fingerprint attack.

An image processing and model training methods, an electronic device, and a storage medium are provided, and relate to the technical field of artificial intelligence, and in particular to the technical fields of computer vision and deep learning, which can be specifically applied to smart cities and intelligent cloud scenes. The image processing method includes: obtaining at least one first feature map of an image to be processed, wherein feature data of a target pixel in the first feature map is generated according to the target pixel and another pixel within a set range around the target pixel; determining a classification to which the target pixel belongs according to the feature data of the target pixel; and determining a target object corresponding to the target pixel and association information of the target object according to the classification to which the target pixel belongs.

The embodiments herein provide a method of obtaining a weighted combination of dynamic vision sensor (DVS) measurements and contact image sensor (CIS) measurements for determining visual inference in an electronic device, the method includes receiving, by the electronic device, a DVS image and a CIS image from the image sensor; determining, by the electronic device, a plurality of parameters associated with the DVS image and feature velocities of a plurality of CIS features present in the CIS image; determining, by the electronic device, a determined DVS feature confidence based on the plurality of parameters associated with the DVS image; determining, by the electronic device, a determined CIS feature confidence based on the feature velocities of the plurality of features present in the CIS image; and calculating, by the electronic device, a weighted visual inference based on the determined DVS feature confidence and the determined CIS feature confidence.

A method and apparatus for object recognition are provided. A processor-implemented method includes extracting feature maps including local feature representations from an input image, generating a global feature representation corresponding to the input image by fusing the local feature representations, and performing a recognition task on the input image based on the local feature representations and the global feature representation.