Abstract: The present disclosure provides a method performed by an electronic device, an electronic device, a storage medium and a program product, relating to the field of computer vision, image processing and artificial intelligence. The method includes: extracting at least one object center area and at least one object boundary area from a first image; and aligning the extracted object center area with the object boundary area to obtain an object segmentation result of the first image.

Abstract: Cached decoding systems and techniques are described. A system (e.g., decoder) receives an input token (e.g., input vector). The system applies a projection tensor (e.g., a projection matrix) to the input token to generate a feature tensor (e.g., a key tensor or a value tensor). The system processes at least the feature tensor and at least one previous feature tensor using at least one attention calculation to generate an output token. The at least one previous feature tensor is retrieved from a buffer. The at least one previous feature tensor can be stored in the buffer after having been previously calculated based on application of the projection tensor to a previous input token (e.g., from a previous iteration before the iteration in which the input token is received).

Abstract: A rendering method includes: receiving a first operation instruction from a user; rendering, according to the first operation instruction, a first image of an application corresponding to the first operation instruction; predicting a second operation instruction according to the first operation instruction; rendering, according to the second operation instruction, a second image of the application corresponding to the second operation instruction; if no operation instruction is received from the terminal device user within preset duration during running of an app after the first operation instruction is received, predicting a user operation according to the received operation instruction, where the operation instruction is an instruction that is generated through triggering by the user operation and that may trigger image switching of the app; rendering an app image based on a predicted user operation; and sending a rendered app image to the terminal device user.

Abstract: The present disclosure provides a medical hyperspectral image (MHSI) classification method based on a fast fully convolutional network (FCN), and relates to the technical field of MHSIs. The MHSI classification method includes: preprocessing and sampling an MHSI to obtain a training sample set; inputting the training sample set into an encoder-decoder-based FCN to train the MHSI; and inputting a to-be-classified pixel of the MHSI into a trained encoder-decoder-based FCN to obtain a classification result. The present disclosure provides the MHSI classification method based on a fast FCN. In order to resolve problems of low efficiency and insufficient performance of an existing MHSI classification method, the present disclosure designs a classification method based on the fast FCN, which avoids redundant computation in an overlapping region between image patches, greatly improving an inference speed.

Abstract: Techniques are described with regard to container image configuration in a computing environment. An associated computer-implemented method includes initializing a container image storage engine associated with a logical tree structure having a plurality of container image nodes, where each of the plurality of container image nodes includes a hash layer array and a hash data array. The method includes building at least one new container image node to incorporate into the plurality of container image nodes. The method further includes applying a software patch to a target container image node among the plurality of container image nodes. In an embodiment, the method further includes starting at least one container based upon a respective container image node among the plurality of container image nodes.

Abstract: This application relates to the field of artificial intelligence and the field of computer vision. The method includes performing feature extraction on an image to obtain a basic feature map of the image, and determining a proposal of a region possibly including a pedestrian in the image. The basic feature map of the image is then processed to obtain an object visibility map in which a response to a pedestrian visible part is greater than a response to a pedestrian blocked part and a background part. The method further performs weighted summation processing on the object visibility map and the basic feature map to obtain an enhanced feature map of the image, and determines, based on the proposal of the image and the enhanced feature map of the image, a bounding box including a pedestrian in the image and a confidence level of the bounding box including the pedestrian.

Abstract: Devices and techniques are generally described for providing a graphical user interface. In some examples, first image data may be sent to a computing device, that when rendered is effective to display a first combination of items disposed together in a first environment and a first selectable control. In some examples, first data may be received indicating a selection of the first selectable control. In various examples, a first computing device may determine first feature data representing the first image data. In some examples, the first computing device may determine second image data using the first feature data. In some examples, the second image data may be sent to a second computing device. The second image data, when rendered, may be effective to display a second combination of items disposed together in a second environment.

Abstract: Example neural architecture search methods and image processing methods and apparatuses in the field of computer vision in the field of artificial intelligence are provided. The example neural architecture search method includes determining search space and a plurality of construction units, superimposing the plurality of construction units to obtain a search network, adjusting, in the search space, network architectures of the construction units in the search network, to obtain optimized construction units, and establishing a target neural network based on the optimized construction units. In each construction unit, some channels of an output feature map of each node are processed by using a to-be-selected operation to obtain a processed feature map, and the processed feature map and a remaining feature map are stitched and then input to a next node.

Abstract: A processor-implemented method for a neural architecture search (NAS) starts by generating an over-parameterized super network having multiple layers. The super network has multiple operator types. Each of the layers includes a largest super kernel corresponding to a search space. The method also includes performing gradient descent to evolve a largest super kernel to a small kernel corresponding to the search space in order to generate a range of kernel encodings. The method further includes identifying a subset of kernel encodings from the range of kernel encodings, for each layer of the super network, based on the gradient descent. The method determines a set of candidate architectures based on the subset of kernel encodings, each of the candidate architectures having a different model size. The method selects a target model, from the set of architectures, based on meeting hardware specifications, and then applies the target model.

Abstract: A method for constructing an artificial intelligence (AI) integrated model is provided, including: obtaining a training dataset, an initial graph network model, and a plurality of base models; then iteratively training the initial graph network model by using training data in the training dataset and the plurality of base models, to obtain a graph network model; and then constructing the AI integrated model based on the graph network model and the plurality of base models, where an input of the graph network model is a graph structure consisting of outputs of the plurality of base models. Since the graph network model considers neighboring nodes of each node in the graph structure when processing the graph structure, the graph network model fully considers differences and correlations between the base models when fusing the outputs of the plurality of base models.

Abstract: An antenna structure, an electronic device, and a wireless network system are provided, and relate to the field of antenna technologies. A patch antenna array includes four patch antennas. The four patch antennas are arranged in two rows and two columns. One of the feeding structures is included between two of the patch antennas in each row. One of the feeding structures is included between two of the patch antennas in each column. The feeding structure located between the two patch antennas in each column is connected to the first feeding port, so that the four patch antennas all generate polarization in a first direction. The feeding structure located between the two patch antennas in each row is connected to the second feeding port, so that the four patch antennas all generate polarization in a second direction.

Abstract: The present invention belongs to the technical field of preparing isocyanate derivatives, and particularly relates to a storage-stable polyisocyanate composition and a preparation method therefor. The method comprises: in the presence of a catalyst system, subjecting an isocyanate monomer to a polymerization reaction; terminating the reaction after a suitable conversion rate is reached, so as to obtain a polyisocyanate reaction solution; and then performing heat treatment on the obtained polyisocyanate reaction solution to obtain a heat-treated polyisocyanate mixture, wherein the heat treatment temperature is 10-30° C. higher than the heat-sensitive temperature of the obtained polyisocyanate product, and the heat treatment time is 5-30 min; and then performing separation treatment on the heat-treated polyisocyanate mixture. When the polyisocyanate composition of the present invention is stored at 50° C.

Abstract: This application relates to the field of image annotation and recognition in the field of artificial intelligence technologies, and in particular, to a data annotation method. The method includes: using at least two different classification models; pretraining one of the classification models as an initial classification model, and annotating a label for data in a to-be-annotated source dataset as initial data by using the pretrained classification model; and controlling the classification models to perform alternating training and data annotation a quantity of times. Operations of current training and current data annotation include: obtaining data that is re-annotated with a label by a previously trained classification model, selecting a first part of the data to train a current classification model, and re-annotating, by the trained current classification model, a label for a second part of data that is not selected.

Abstract: A model training method and a related apparatus are provided, which may be used in computer vision to perform image detection. The method includes: extracting feature information in a target image; further separately extracting features of a target object from the feature information by using a Gaussian mask to obtain a first local feature and a second local feature; determining a feature loss by using the first local feature and the second local feature; performing prediction by using the first network and the second network based on a same region proposal set to obtain a first classification predicted value and a second classification predicted value, and obtaining a classification loss based on the first classification predicted value and the second classification predicted value; and training the second network based on the classification loss and the feature loss to obtain a target network.

Abstract: This application relates to the field of artificial intelligence, and specifically, to the field of computer vision. The method includes: performing feature extraction on an image to obtain a basic feature map of the image; determining a proposal of a region possibly including a pedestrian in the image; processing the basic feature map of the image to obtain an object visibility map in which a response to a pedestrian visible part is greater than a response to a pedestrian blocked part and a background part; performing weighted summation processing on the object visibility map and the basic feature map to obtain an enhanced feature map of the image; and determining, based on the proposal of the image and the enhanced feature map of the image, a bounding box including a pedestrian in the image and a confidence level of the bounding box including the pedestrian in the image.

Abstract: Example neural architecture search methods and image processing methods and apparatuses in the field of computer vision in the field of artificial intelligence are provided. The example neural architecture search method includes determining search space and a plurality of construction units, superimposing the plurality of construction units to obtain a search network, adjusting, in the search space, network architectures of the construction units in the search network, to obtain optimized construction units, and establishing a target neural network based on the optimized construction units. In each construction unit, some channels of an output feature map of each node are processed by using a to-be-selected operation to obtain a processed feature map, and the processed feature map and a remaining feature map are stitched and then input to a next node.

Abstract: In an approach for debugging and simulating application runtime execution, a processor loads source code and logs into a debug tool. A processor generates log debug information including a log map, a log variable cross reference table, and a method call stack tree. A processor determines a plurality of log blocks based on log context in the logs and the method call stack tree. A processor maps the source code to the logs for each log block. A processor suggests a starting point and a breakpoint based on the log variable cross reference table and the log blocks. A processor compares a source code variable value to a log variable value and a source code execution path to a log execution path based on the mapping set between the source code and the logs. A processor simulates the source code variable value with the log variable value.

Abstract: A keyword extraction method is provided. In the method, a candidate keyword set in a target text is obtained by processing circuitry of a server. An extraction degree of the candidate keyword is determined by the processing circuitry based on subject similarity and a text conversion frequency of a candidate keyword in the candidate keyword set. The subject similarity is between the candidate keyword and the target text. The extraction degree indicates a probability at which the candidate keyword used as a keyword matching the target text is extracted. The keyword is extracted by the processing circuitry from the candidate keyword set according to the extraction degree.

Abstract: Sensing of scene-based occurrences is disclosed. In one example, a vision sensor system comprises (1) dedicated computer vision (CV) computation hardware configured to receive sensor data from at least one sensor array and capable of computing CV features using readings from multiple neighboring sensor pixels and (2) a first processing unit communicatively coupled with the dedicated CV computation hardware. The vision sensor system is configured to, in response to processing of the one or more computed CV features indicating a presence of one or more irises in a scene captured by the at least one sensor array, generate data in support of iris-related operations to be performed by a second processing unit and send the generated data to the second processing unit.

Abstract: Use of pupillary response to visible light for iris authentication is disclosed. One example involves (a) capturing an initial image of an eye including an inner circular boundary between a pupil region and an iris region and an outer circular boundary between the iris region and a sclera region, (b) determining a first size measurement indicative of the inner circular boundary, (c) responsive to at least the first size measurement, modulating one or more visible light sources to output visible light toward the eye of the user, (d) capturing a subsequent image of the eye of the user during a period of pupillary response, (e) obtaining an iris data record of the user, and (f) comparing the iris data record of the user to one or more registered iris data records to authenticate the user.