Abstract: A training method for a human body attribute detection model includes: acquiring positive sample sub-images and negative sample sub-images respectively corresponding to a plurality of human body attribute categories; determining a plurality of first annotation attributes respectively corresponding to the plurality of positive sample sub-images; and a plurality of second annotation attributes respectively corresponding to the plurality of negative sample sub-images; and training an artificial intelligence model according to the plurality of positive sample sub-images, the plurality of negative sample sub-images, the plurality of first annotation attributes and the plurality of second annotation attributes to obtain the human body attribute detection model, so that the human body attribute detection model obtained by training can effectively model fine-grained attributes of the human body.

Abstract: A method for recognizing a category of an image includes: acquiring a spectral image; training an image recognition model based on the spectral image, in which the image recognition model acquires a spectral semantic feature of each pixel, a minimum distance between each pixel and each category, and a spectral distance between a first spectrum of each pixel and a second spectrum of each category; splices them; and performs classification and recognition based on the spliced feature to output a recognition probability of each pixel under each category; determining a loss function of the image recognition model, adjusting the image recognition model based on the loss function, and returning to training the adjusted image recognition model based on the spectral image until training ends; recognizing a maximum recognition probability, output from a target image recognition model, and using a category corresponding to the maximum recognition probability as a target category.

Abstract: An electronic device includes a back frame, a first heat source, a second heat source, a guiding member and a fan. The first heat source is disposed on a first side of the back frame. The second heat source is disposed on a second side of the back frame. The guiding member is disposed on the second side of the back frame. The fan is disposed corresponding to the guiding member. At least part of an airflow path is formed between the first heat source and the second heat source.

Abstract: A semiconductor device package includes a redistribution layer, a plurality of conductive pillars, a reinforcing layer and an encapsulant. The conductive pillars are in direct contact with the first redistribution layer. The reinforcing layer surrounds a lateral surface of the conductive pillars. The encapsulant encapsulates the first redistribution layer and the reinforcing layer. The conductive pillars are separated from each other by the reinforcing layer.

Abstract: The present application discloses a method and an apparatus for detecting wearing of a safety helmet, a device and a storage medium. The method for detecting wearing of a safety helmet includes: acquiring a first image collected by a camera device, where the first image includes at least one human body image; determining the at least one human body image and at least one head image in the first image; determining a human body image corresponding to each head image in the at least one human body image according to an area where the at least one human body image is located and an area where the at least one head image is located; and processing the human body image corresponding to the at least one head image according to a type of the at least one head image.

Abstract: An approach is provided in which the approach captures a first user activity log of a first user accessing multiple systems and captures a set of second user activity logs of a set of second users accessing the multiple systems. The approach determines a set of system monitoring preferences based the first user activity log and the set of second user activity logs, and scores the multiple systems based on the set of system monitoring preferences. The approach generates a recommended system monitoring list based on the scored multiple systems, and transmits the recommended system monitoring list to the first user.

Abstract: A method is provided that includes: segmenting an image to be detected into a plurality of image blocks; generating a feature representation of the image to be detected based on the plurality of image blocks; mapping the feature representation by using a preset parameter set to obtain a plurality of feature maps of the image to be detected; and determining a position and a class of a target object in the image to be detected based on the plurality of feature maps.

Abstract: A method for generating a road annotation, a device, and a storage medium are provided. The method may include: generating a road quantity and a road width in a tag picture; generating, for each road in the tag picture, a start point and an end point of the road; generating at least one point between the start point and the end point; drawing, for two adjacent points, a line segment from a previous point to a next point, where a width of the line segment is equal to the road width; and generating slanted box annotation information based on a coordinate of the previous point and a coordinate of the next point, where the slanted box annotation information includes an intersection point of diagonal lines, a width, a height and a slant angle of a slanted box.

Abstract: A method for forming a current collector is provided. At least two carbon nanostructure reinforced copper composite substrates are provided. The at least two carbon nanostructure reinforced copper composite substrates are stacked to form a composite substrate. An active metal layer is disposed on a surface of the composite substrate to form a first a composite structure. The first composite structure is pressed to form a second composite structure. The second composite structure is annealed to form a third composite structure. The third composite structure is de-alloyed to form a porous copper composite.

Abstract: A pressure protector for a high-voltage self-healing capacitor. is composed of a box shell, a cover plate, a core, filled resin, a pressure protector and wiring terminals. The pressure protector is arranged in the capacitor, and the pressure protector is mainly composed of fixed studs, a protector shell, a movable bolt assembly, a fixed electrode assembly, a movable electrode assembly, first fixed bolts and a limiting bolt. The pressure protector for a high-voltage self-healing capacitor is simple in structure and convenient to install and use, the technical problem of relay protection of internal faults of the self-healing capacitor can be solved. Accidents can be effectively avoided, and the requirement for safe operation of the capacitor can be met.

Abstract: The present disclosure provides a method for incrementing a sample image, an electronic device, and a computer readable storage medium. A specific implementation comprises: acquiring a first convolutional feature of an original sample image; determining, according to a region generation network and the first convolutional feature, a candidate region and a first probability that the candidate region contains a target object; determining a target candidate region from the candidate region based on the first probability, and mapping the target candidate region back to the original sample image to obtain an intermediate image; and performing image enhancement processing on a portion of the intermediate image corresponding to the target candidate region and/or performing image blur processing on a portion of the intermediate image corresponding to a non-target candidate region to obtain an incremental sample image.

Abstract: A method of training an image-text retrieval model, a method of multimodal image retrieval, an electronic device and a storage medium, each relating to the technical field of artificial intelligence, and in particular, to fields of computer vision and deep learning technologies. Sample data including a sample text and a sample image is acquired. The sample text includes a sample text in a first language and a sample text in a second language. The sample text in the first language and the sample text in the second language are processed by using the text encoding sub-model to obtain a sample text feature of the sample data. The sample image is processed by using the image encoding sub-model to obtain a sample image feature of the sample data. The image-text retrieval model is trained according to the sample text feature and the sample image feature.

Abstract: A semiconductor device package includes a redistribution layer, a plurality of conductive pillars, a reinforcing layer and an encapsulant. The conductive pillars are in direct contact with the first redistribution layer. The reinforcing layer surrounds a lateral surface of the conductive pillars. The encapsulant encapsulates the first redistribution layer and the reinforcing layer. The conductive pillars are separated from each other by the reinforcing layer.

Abstract: Package structures and methods for manufacturing the same are provided. The package structure includes a first bump structure formed over a first substrate. The first bump structure includes a first pillar layer formed over the first substrate and a first barrier layer formed over the first pillar layer. In addition, the first barrier layer has a first protruding portion laterally extending outside a first edge of the first pillar layer. The package structure further includes a second bump structure bonded to the first bump structure through a solder joint. In addition, the second bump structure includes a second pillar layer formed over a second substrate and a second barrier layer formed over the second pillar layer. The first protruding portion of the first barrier layer is spaced apart from the solder joint.

Abstract: An electronic device package and a method for manufacturing an electronic device package are provided. The electronic device package includes electronic device structure which includes a first electronic device and a first encapsulant, a second electronic device, and a second encapsulant. The first encapsulant encapsulates the first electronic device. The second electronic device is adjacent to the electronic device structure. The second encapsulant encapsulates the electronic device structure and the second electronic device. A first extension line along a lateral surface of the first electronic device and a second extension line along a lateral surface of the first encapsulant define a first angle, the second extension line along the lateral surface of the first encapsulant and a third extension line along a lateral surface of the second electronic device define a second angle, and the first angle is different from the second angle.

Abstract: A method for forming a package structure includes forming an under bump metallization (UBM) layer over a metal pad and forming a photoresist layer over the UBM layer. The method further includes patterning the photoresist layer to form an opening in the photoresist layer. The method also includes forming a first bump structure over the first portion of the UBM layer. The first bump structure includes a first barrier layer over a first pillar layer. The method includes placing a second bump structure over the first bump structure. The second bump structure includes a second barrier layer over a second pillar layer. The method further includes reflowing the first bump structure and the second bump structure to form a solder joint between a first inter intermetallic compound (IMC) and a second IMC.

Abstract: A method for generating a sample image includes: obtaining an initial image size of an initial image; obtaining a plurality of reference images by processing the initial image based on different reference processing modes; obtaining an image to be processed by fusing the plurality of reference images; and determining a target sample image from images to be processed based on the initial image size.

Abstract: According to various embodiments, a collimator includes a substrate defining a plurality of channels through the substrate. The substrate includes a first surface and a second surface opposite the first surface. Each of the channels includes a first aperture exposed from the first surface, a second aperture between the first surface and the second surface, and a third aperture exposed from the second surface. The first aperture and the third aperture are larger than the second aperture.

Abstract: The disclosure provides a method for detecting a change of a building, an apparatus for detecting a change of a building, an electronic device, a storage medium and a computer program product. The method includes: obtaining a remote-sensing image sequence of a to-be-detected region; obtaining a building probability map corresponding to each remote-sensing image in the remote-sensing image sequence; determining a sub-region located by each building in the to-be-detected region based on the building probability map corresponding to each remote-sensing image; for each building, determining an existence probability of the building in each remote-sensing image based on the sub-region located by the building and the building probability map corresponding to each remote-sensing image; and determining a change condition of the building based on the existence probability of the building in each remote-sensing image.

Abstract: Provided are a training method and apparatus for a target detection model, a device and a storage medium. The training method is described below. A feature map of a sample image is processed through a classification network of an initial model and a heat map and a classification prediction result of the feature map are obtained, a classification loss value is determined according to the classification prediction result and classification supervision data of the sample image, and a category probability of pixels in the feature map is determined according to the heat map of the feature map and a probability distribution map of the feature map is obtained; the feature map is processed through a regression network of the initial model and a regression prediction result is obtained, and a regression loss value is determined.