A device includes memory and a processor. The device receives biometric information. The device receives location information. The device analyzes the received biometric information with stored biometric information. The device analyzes the received location information with stored location information. The device determines whether the received biometric information matches the stored biometric information. The device determines whether the received location information matches the stored location information. The device sends an electronic communication that indicates whether the received biometric information matches the stored biometric information and whether the received local information matches the stored location information.

A method for optimizing a neural network is provided, including: (1) capturing, via a first sensor group having a first field of view, a first sample set having a first sensor domain corresponding to the first field of view; (2) capturing, via a second sensor group having a second field of view, a second sample set having a second sensor domain corresponding to the second field of view; (3) generating regions of interest of the second sample set; (4) translating the regions of interest to the first sensor domain; (5) identifying nodes of the neural network which correspond to the translated regions; and (6) optimizing the neural network by at least one of (a) increasing the weight value of the nodes corresponding to the one or more translated regions and (b) decreasing the weight value of the nodes not corresponding to the one or more translated regions.

An image data processing method and apparatus are provided. In a technical solution provided by embodiments of this disclosure, M object feature maps with different sizes are obtained by extracting a source image. While classification confidence levels corresponding to pixel points in each of the object feature maps are acquired, initial predicted polar radii corresponding to the pixel points in each of the object feature maps may also be acquired. The initial predicted polar radii are refined based on polar radius deviations corresponding to the contour sampling points in each of the object feature maps, to acquire target predicted polar radii corresponding to the pixel points in each of the object feature maps. Then the object edge shape of a target object contained in the source image can be determined based on the target predicted polar radii and the classification confidence levels.

Provided are an illegal building identification method and apparatus, a device, and a storage medium, which relate to the field of cloud computing. The specific implementation scheme is: acquiring a target image and a reference image associated with the target image; extracting a target building feature of the target image and a reference building feature of the reference image, respectively; and determining, according to the target building feature and the reference building feature, an illegal building identification result of the target image.

A method and an apparatus for retrieving a target are provided. The method may include: obtaining at least one image and a description text of a designated object; extracting image features of the image and text features of the description text by using a pre-trained cross-media feature extraction network; and matching the image features with the text features to determine an image that contains the designated object.

A content recommendation method that includes: acquiring content cover images corresponding to multiple pieces of content accessed by a user account; acquiring cover image features of the multiple content cover images, and determining user account features of the user account according to the cover image features of the multiple content cover images; on the basis of cover image features of content to be recommended and the user account features, determining an access probability value of the user account accessing the content to be recommended; and providing, according to the access probability value, the content to be recommended to the user account.

An automotive sensor integration module including a plurality of sensors which differ in at least one of a sensing period or an output data format, and a signal processing unit, which simultaneously outputs, as sensing data, pieces of detection data respectively output from the plurality of sensors on the basis of the sensing period of any one of the plurality of sensors, determines whether each region of an outer cover corresponding to a location of each of the plurality of sensors is contaminated on the basis of the pieces of detection data, and outputs a determination result as contamination data.

A plurality of images can be acquired from a plurality of sensors and a plurality of flattened patches can be extracted from the plurality of images. An image location in the plurality of images and a sensor type token identifying a type of sensor used to acquire an image in the plurality of images from which the respective flattened patch was acquired can be added to each of the plurality of flattened patches. The flattened patches can be concatenated into a flat tensor and add a task token indicating a processing task to the flat tensor, wherein the flat tensor is a one-dimensional array that includes two or more types of data. The flat tensor can be input to a first deep neural network that includes a plurality of encoder layers and a plurality of decoder layers and outputs transformer output. The transformer output can be input to a second deep neural network that determines an object prediction indicated by the token and the object predictions can be output.

Among other things, techniques are described for cross-modality active learning for object detection. In an example, a first set of predicted bounding boxes and a second set of predicted bounding boxes is generated. The first set of predicted bounding boxes and the second set of predicted bounding boxes are projected into a same representation. The projections are filtered, wherein predicted bounding boxes satisfying a maximum confidence score are selected for inconsistency calculations. Inconsistencies are calculated across the projected bounding boxes based on filtering the projections. An informative scene is extracted based on the calculated inconsistencies. A first object detection neural network or a second object detection neural network is trained using the informative scenes.

Systems and methods for detecting udder disease based on machine learning methods and complementary supporting techniques are presented. Included are methods for assembling time sequences of images of each animal of a herd or set for subsequent use in per-animal image analysis for disease detection. Methods presented also include image pre-processing methods used prior to image analysis, resulting in contrast and resolution optimization such as appropriate image intensity level adjustment and resolution downsampling for more rapid and more accurate disease detection. Combinatorial techniques for compositing whole-udder images or udder-quarter images from partial images captures are described. Methods are provided for power usage optimization in regard to computing resources used in the computing-intensive AI analysis methods. Location-based and animal history-based detection refinements are incorporated into described systems. Further presented are methods for multi-modal and multi-factor detection of udder disease, as well as methods for infection type classification.