Abstract: A method, computer program, and computer system are provided for performing multiple machine learning tasks through a shared framework. Data corresponding to a plurality of predetermined machine learning tasks is received. One or more steps of the machine learning tasks associated with the received data is performed on the received data by a shared backbone of a machine learning model. The predetermined plurality of machine learning tasks is completed on the received data by a plurality of sub-networks associated with each of the plurality of predetermined machine learning tasks.

Abstract: A method of training a target object detection model includes: extracting a plurality of feature maps of a sample image according to a training parameter, fusing the plurality of feature maps to obtain at least one fused feature map, and obtaining an information of a target object based on the at least one fused feature map, by using the target object detection model; determining a loss of the target object detection model based on the information of the target object and a tag information of the sample image, and adjusting the training parameter according to the loss of the target object detection model. A method of detecting a target object and an apparatus are also provided.

Abstract: A method for forming a staircase structure of 3D memory, including: forming an alternating layer stack on a substrate, forming a plurality of staircase regions where each staircase region has a staircase structure having a first number (M) of steps in a first direction; forming a first mask stack to expose a plurality of the staircase regions; removing (M) of the layer stacks in the exposed staircase regions; forming a second mask stack over the alternating layer stack to expose at least an edge of each of the staircase regions in a second direction; and repetitively, sequentially, removing a portion of (2M) of layer stacks and trimming the second mask stack.

Abstract: Provided are a method and apparatus for evaluating image relative definition, a device and a medium, relating to technologies such as computer vision, deep learning and intelligent medical. A specific implementation solution is: extracting a multi-scale feature of each image in an image set, where the multi-scale feature is used for representing definition features of objects having different sizes in an image; and scoring relative definition of each image in the image set according to the multi-scale feature by using a relative definition scoring model pre-trained, where the purpose for training the relative definition scoring model is to learn a feature related to image definition in the multi-scale feature.

Abstract: A method and an apparatus for controlling an unmanned aerial vehicle are provided. The method includes: detecting an abnormality occurring on the unmanned aerial vehicle in a flight process; obtaining a hover instruction in response to detecting the abnormality; and controlling, in response to the hover instruction, the unmanned aerial vehicle to hover based on the hover instruction.

Abstract: A method and an apparatus for controlling an unmanned aerial vehicle are provided. The method includes: detecting an abnormality occurring on the unmanned aerial vehicle in a flight process; obtaining a hover instruction in response to detecting the abnormality; and controlling, in response to the hover instruction, the unmanned aerial vehicle to hover based on the hover instruction.

Abstract: A chad containment bin includes a chad containment space formed by a pair of opposing longitudinally extending sidewalls connected by a pair of opposing, laterally extending sidewalls. A shredder head assembly is situated above the chad containment bin. A cabinet body supports the shredder head assembly while removeably housing the chad containment bin. A generally vertically oriented support member extends upwardly from a first of the longitudinally extending sidewalls. The support member includes a handle on an outer face for carrying the chad containment bin. A panel is pivotally connected to the chad containment bin for providing access to the chad containment space when the chad containment bin is suspended by the handle over a waste receptacle.

Abstract: A chad containment bin includes a chad containment space formed by a pair of opposing longitudinally extending sidewalls connected by a pair of opposing, laterally extending sidewalls. A shredder head assembly is situated above the chad containment bin. A cabinet body supports the shredder head assembly while removeably housing the chad containment bin. A generally vertically oriented support member extends upwardly from a first of the longitudinally extending sidewalls. The support member includes a handle on an outer face for carrying the chad containment bin. A panel is pivotally connected to the chad containment bin for providing access to the chad containment space when the chad containment bin is suspended by the handle over a waste receptacle.