An object recognition method includes: obtaining a candidate object set having a plurality of candidate objects; obtaining a plurality of pieces of candidate object information of the candidate objects on a plurality of dimensions, performing feature extraction on the candidate object information to obtain candidate object features, fusing the candidate object features to obtain object extraction features corresponding to the candidate objects, and performing object category probability recognition based on the object extraction features to obtain a recognition probability that the candidate objects belong to a target object category; clustering the object extraction features to obtain sub extraction feature sets corresponding to clustering categories, and forming one sub object set from candidate objects corresponding to the object extraction features; and obtaining representative objects by selecting from the sub object sets respectively based on recognition probabilities corresponding to the candidate objects in the sub object sets.

Provided is a system and method for fusion recognition using an active stick filter. The system for fusion recognition using the active stick filter includes a data input unit configured to receive input information for calibration between an image and a heterogeneous sensor, a matrix calculation unit configured to calculate a correlation for projection of information of the heterogeneous sensor, a projection unit configured to project the information of the heterogeneous sensor onto an image domain using the correlation, and a two-dimensional (2D) heterogeneous sensor fusion unit configured to perform stick calibration modeling and design and apply a stick calibration filter.

A data processing method and apparatus, a computer device, a readable storage medium, and a computer program product are provided. The method includes: displaying a shot picture in a shooting interface, the shot picture being captured by a shooting component and including a target object; displaying a first virtual rendering area of the target object in the shooting interface in response to a first trigger operation for the target object in the shooting interface; and displaying media data in the first virtual rendering area, the media data being associated with an object classification of the target object.

Systems, methods, apparatuses, and computer program products for providing multimodal emotion recognition. The method may include receiving raw input from an input source. The method may also include extracting one or more feature vectors from the raw input. The method may further include determining an effectiveness of the one or more feature vectors. Further, the method may include performing, based on the determination, multiplicative fusion processing on the one or more feature vectors. The method may also include predicting, based on results of the multiplicative fusion processing, one or more emotions of the input source.

A method for large scene elastic semantic representation and self-supervised light field reconstruction is provided. The method includes acquiring a first depth map set corresponding to a target scene, in which the first depth map set includes a first depth map corresponding to at least one 5 angle of view; inputting the first depth map set into a target elastic semantic reconstruction model to obtain a second depth map set, in which the second depth map set includes a second depth map corresponding to the at least one angle of view; and fusing the second depth map corresponding to the at least one angle of view to obtain a target scene point cloud corresponding to the target scene.

A spoofing detection apparatus includes a face image obtaining unit that obtains a first image frame that includes the face of a person when emitting light and a second image frame that includes the face of the person when not emitting light, a face information extraction unit that extract, from the first image frame, a first face information specifying a face portion, and extract, from the second image frame, a second face information specifying a face portion, a feature calculation unit that extracts a portion that includes a bright point in an iris region of an eye based on the first face information, extracts a portion corresponding to the portion that includes the bright point based on the second face information, and calculates a feature that is independent of the position of the bright point, and a spoofing determination unit that determines authenticity of person based on the feature.

Implementations of the present disclosure relate to methods, devices, and computer program products of extracting a feature for multimedia data that comprises a plurality of medium types. In a method, a first feature is determined for a first medium type in the plurality of medium types by masking a portion in a first medium object with the first medium type. A second feature is determined for a second medium type other than the first medium type in the plurality of medium types. The feature is generated for the multimedia data based on the first and second features. With these implementations, multiple medium types are considered in the feature extraction, and thus the feature may fully reflect various aspects of the multimedia data in an accurate way.

A method and system for training a neural network are provided. The method includes receiving an input image, selecting at least one data augmentation method from a pool of data augmentation methods, generating an augmented image by applying the selected at least one data augmentation method to the input image, and generating a mixed image from the input image and the augmented image.

A method includes: obtaining heat maps including a predetermined number of key points of a human body; performing depth separable convolution on a feature map corresponding to one of the heat maps corresponding to each of the key points and a convolution kernel of a corresponding channel of the human body posture recognition model to determine a key point feature map corresponding to each channel of the human body posture recognition model; performing local feature fusion processing and/or global feature fusion processing on the key point feature map corresponding to each channel to obtain fusion posture feature maps; determining a linear relationship between the channels of the human body posture recognition model based on the fusion posture feature maps; and updating weight coefficients of the corresponding channels of the human body posture recognition model by using the linear relationship between the channels of the human body posture recognition model.

A method includes: An electronic device determines a category of a first object. The electronic device collects a first image of the first object by using a first camera, where the first image is a micro image. The electronic device obtains a hygiene status of the first object based on the category and the first image of the first object. The electronic device may obtain, based on the micro image of the first object, information such as a category and a quantity of bacteria existing on the first object, or may obtain information such as a color and luster, texture, and an air hole of the first object. In this way, the electronic device can perform comprehensive analysis with reference to the category of the object and the micro image of the object, determine the hygiene status of the object, and output an intelligent prompt.