This disclosure discloses a perception network. The perception network may be applied to the artificial intelligence field, and includes a feature extraction network. A first block in the feature extraction network is configured to perform convolution processing on input data, to obtain M target feature maps; at least one second block in the feature extraction network is configured to perform convolution processing on M1 target feature maps in the M target feature maps, to obtain M1 first feature maps; a target operation in the feature extraction network is used to process M2 target feature maps in the M target feature maps, to obtain M2 second feature maps; and a concatenation operation in the feature extraction network is used to concatenate the M1 first feature maps and the M2 second feature maps, to obtain a concatenated feature map.

Embodiments of this application disclose an image fusion method performed by a computing device. The method includes the following steps: obtaining source face image data of a current to-be-fused image and resource configuration information of a current to-be-fused resource, performing image recognition processing on the source face image data, to obtain source face feature points corresponding to the source face image data, and generating a source face three-dimensional grid of the source face image data according to the source face feature points, performing grid fusion by using a resource face three-dimensional grid and the source face three-dimensional grid to generate a target face three-dimensional grid, and performing face complexion fusion by using source complexion data of the source face image data and resource complexion data of resource face image data on the target face three-dimensional grid, to generate fused target face image data.

The present disclosure describes methods, devices, and storage medium for generating a natural language description for a media object. The method includes respectively processing, by a device, a media object by using a plurality of natural language description models to obtain a plurality of first feature vectors corresponding to a plurality of feature types. The device includes a memory storing instructions and a processor in communication with the memory. The method also includes fusing, by the device, the plurality of first feature to obtain a second feature vector; and generating, by the device, a natural language description for the media object according to the second feature vector, the natural language description being used for expressing the media object in natural language. The present disclosure resolves the technical problem that natural language description generated for a media object can only give an insufficiently accurate description of the media object.

An image information processing method is provided. The method includes obtaining a to-be-processed image, and preprocessing the to-be-processed image to obtain target image information, extracting facial feature point information from the target image information, and integrating the facial feature point information to a target region image to obtain an integrated image, the target region image being part of a playback image in a preset playback interval of a video, and displaying the integrated image on the video in response to detecting that the video is played to the preset playback interval.

A method for classifying objects which comprises a provision of measuring data from a sensor for a feature extraction unit as well as extraction of modality-independent features from the measuring data by means of the feature extraction unit, wherein the modality-independent features are independent of a sensor modality of the sensor, so that a conclusion to the sensor modality of the sensor is not possible from the modality-independent features.

Embodiments of the present disclosure provide a method of matching image, an apparatus of matching image, a device, and a computer-readable storage medium. The method includes: acquiring an image to be matched; determining a key point feature similarity between any image in an image library and the image to be matched, and determining a color feature similarity between the any image and the image to be matched; determining a fusion similarity between the any image and the image to be matched according to the key point feature similarity and the color feature similarity; and determining whether an image matching the image to be matched exists in the image library or not according to the fusion similarity between each of at least one image in the image library and the image to be matched.

A map building apparatus includes a memory storing instructions, and a processor executing the instructions to obtain a plurality of frames of images that carry image information of a target environment, obtain a motion parameter of the image capture component at a capture location of each frame of the plurality of frames of images, obtain a relative displacement between capture locations of each two frames of images based on the motion parameter of the image capture component, obtain, based on the plurality of frames of images and the relative displacement, a map layer including feature points in the plurality of frames of images, and send the map layer and the relative displacement to a server. The plurality of frames of images are captured by an image capture component. The motion parameter indicates a motion status of the image capture component. The map layer is useable to build a map.

A human detection method and apparatus, a computer device and a storage medium are provided. The method includes that: an image to be detected is acquired; position information of skeletal key points configured to represent a human skeletal structure and position information of contour key points configured to represent a human contour are determined based on the image to be detected; and a human detection result is generated based on the position information of the skeletal key points and the position information of the contour key points.

A method and an apparatus for pattern recognition is provided in the present invention, applied to the field of artificial intelligence. The method includes: acquiring a two-dimensional image of a target object and a two-dimensional feature of the target object according to the two-dimensional image of the target object; and acquiring a three-dimensional image of the target object and a three-dimensional feature of the target object according to the three-dimensional image of the target object; identifying the target object according to the two-dimensional feature and the three-dimensional feature of the target object. The method can reduce restrictions on acquiring the image of the target object, for example, reduce the restrictions on the image of the target object in terms of postures, lighting, expressions, make-up and occlusion, thereby improving an accuracy of recognizing the target object and improving a recognition rate and reducing recognition time at the same time.

Provided are an identifying device, an identification method, an identification system, and a database structure capable of identifying species of organisms including animals, insects, and plants. The identifying device for identifying organisms includes a reception unit for receiving feature information including at least one of a location, date and time, image data, attribution information of the image data, and a keyword representing a feature of the organism transmitted from a user terminal, and an identification unit for identifying the species of the organism based on the feature information received by the reception unit by referring to a database in which species of organisms are stored in association with the feature information.