Abstract: Implementations of the present disclosure provide a solution for cross-domain image translation. In this solution, a first learning network for geometric deformation from a first to a second image domain is determined based on first and second images in the first and second domains, images in the two domains having different styles and objects in the images having geometric deformation with respect to each other. Geometric deformation from the second to the first domains is performed on the second image or geometric deformation from the first to the second domains is performed on the first image, to generate an intermediate image. A second learning network for style transfer from the first to the second domains is determined based on the first and intermediate images or based on the second and intermediate images generated. Accordingly, processing accuracy of leaning networks for cross-domain image translation can be improved and complexity is lowered.

Abstract: Systems and methods for displaying and associating context images with zones or devices of a security system or a home automation system are provided. Such systems and methods may include associating each of a plurality of zones or devices of the security system or the home automation system with a respective context image and displaying the respective context image for one of the plurality of zones or devices in response to a user interface of the security system or the home automation system receiving user input.

Abstract: Systems and methods for object detection generate a feature pyramid corresponding to image data, and rescaling the feature pyramid to a scale corresponding to a median level of the feature pyramid, wherein the rescaled feature pyramid is a four-dimensional (4D) tensor. The 4D tensor is reshaped into a three-dimensional (3D) tensor having individual perspectives including scale features, spatial features, and task features corresponding to different dimensions of the 3D tensor. The 3D tensor is used with a plurality of attention layers to update a plurality of feature maps associated with the image data. Object detection is performed on the image data using the updated plurality of feature maps.

Abstract: The present disclosure provides a method of cleaning a wafer and a wafer cleaning apparatus. The method of cleaning a wafer includes: providing a wafer to be cleaned, the surface of the wafer having contaminants; and spraying a surfactant onto the surface of the wafer, and scrubbing the surface of the wafer with a polishing pad to remove the contaminants from the surface of the wafer.

Abstract: The disclosure herein enables tracking of multiple objects in a real-time video stream. For each individual frame received from the video stream, a frame type of the frame is determined. Based on the individual frame being an object detection frame type, a set of object proposals is detected in the individual frame, associations between the set of object proposals and a set of object tracks are assigned, and statuses of the set of object tracks are updated based on the assigned associations. Based on the individual frame being an object tracking frame type, single-object tracking is performed on the frame based on each object track of the set of object tracks and the set of object tracks is updated based on the performed single-object tracking. For each frame received, a real-time object location data stream is provided based on the set of object tracks.

Abstract: The disclosure herein enables tracking of multiple objects in a real-time video stream. For each individual frame received from the video stream, a frame type of the frame is determined. Based on the individual frame being an object detection frame type, a set of object proposals is detected in the individual frame, associations between the set of object proposals and a set of object tracks are assigned, and statuses of the set of object tracks are updated based on the assigned associations. Based on the individual frame being an object tracking frame type, single-object tracking is performed on the frame based on each object track of the set of object tracks and the set of object tracks is updated based on the performed single-object tracking. For each frame received, a real-time object location data stream is provided based on the set of object tracks.

Abstract: A computer device for automatic feature detection comprises a processor, a communication device, and a memory configured to hold instructions executable by the processor to instantiate a dynamic convolution neural network, receive input data via the communication network, and execute the dynamic convolution neural network to automatically detect features in the input data. The dynamic convolution neural network compresses the input data from an input space having a dimensionality equal to a predetermined number of channels into an intermediate space having a dimensionality less than the number of channels. The dynamic convolution neural network dynamically fuses the channels into an intermediate representation within the intermediate space and expands the intermediate representation from the intermediate space to an expanded representation in an output space having a higher dimensionality than the dimensionality of the intermediate space.

Abstract: A neural architecture search (NAS) with a weak predictor comprises: receiving network architecture scoring information; iteratively sampling a search space, wherein the sampling comprises: generating a set of candidate architectures within the search space; learning a first predictor; evaluating performance of the candidate architectures; and based on at least the performance of the set of candidate architectures and the network architecture scoring information, refining the search space to a smaller search space; based on at least the network architecture scoring information, thresholding the performance of candidate architectures to determine scored output candidate architectures; and reporting the scored output candidate architectures. In some examples, the candidate architectures each comprise a machine learning (ML) model, for example a neural network (NN).

Abstract: Training a multi-object tracking model includes: generating a plurality of training images based at least on scene generation information, each training image comprising a plurality of objects to be tracked; generating, for each training image, original simulated data based at least on the scene generation information, the original simulated data comprising tag data for a first object; locating, within the original simulated data, tag data for the first object, based on at least an anomaly alert (e.g., occlusion alert, proximity alert, motion alert) associated with the first object in the first training image; based at least on locating the tag data for the first object, modifying at least a portion of the tag data for the first object from the original simulated data, thereby generating preprocessed training data from the original simulated data; and training a multi-object tracking model with the preprocessed training data to produce a trained multi-object tracker.

Abstract: Training a multi-object tracking model includes: generating a plurality of training images based at least on scene generation information, each training image comprising a plurality of objects to be tracked; generating, for each training image, original simulated data based at least on the scene generation information, the original simulated data comprising tag data for a first object; locating, within the original simulated data, tag data for the first object, based on at least an anomaly alert (e.g., occlusion alert, proximity alert, motion alert) associated with the first object in the first training image; based at least on locating the tag data for the first object, modifying at least a portion of the tag data for the first object from the original simulated data, thereby generating preprocessed training data from the original simulated data; and training a multi-object tracking model with the preprocessed training data to produce a trained multi-object tracker.

Abstract: In accordance with implementations of the subject matter described herein, there is proposed a solution of visual stylization of stereoscopic images. In the solution, a first feature map for a first source image and a second feature map for a second source image are extracted. The first and second source images correspond to first and second views of a stereoscopic image, respectively. A first unidirectional disparity from the first source image to the second source image is determined based on the first and second source images. First and second target images having a specified visual style are generated by processing the first and second feature maps based on the first unidirectional disparity. Through the solution, a disparity between two source images of a stereoscopic image are taken into account when performing the visual style transfer, thereby maintaining a stereoscopic effect in the stereoscopic image consisting of the target images.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for a virtual objection distribution method are provided. One of the methods includes: performing an image scanning to a local environment of a user; conducting image identification to an acquired image; acquiring an electronic certificate from a server if an image identifier is identified in the image; saving the electronic certificate; and, in response to a determination that a category count of the received electronic certificates reaches the threshold, sending to the server a virtual object distribution request to cause the server to distribute a virtual object to the user. This method significantly increases interactivity and entertainingness of a virtual object distribution process.

Abstract: Training a multi-object tracking model includes: generating a plurality of training images based at least on scene generation information, each training image comprising a plurality of objects to be tracked; generating, for each training image, original simulated data based at least on the scene generation information, the original simulated data comprising tag data for a first object; locating, within the original simulated data, tag data for the first object, based on at least an anomaly alert (e.g., occlusion alert, proximity alert, motion alert) associated with the first object in the first training image; based at least on locating the tag data for the first object, modifying at least a portion of the tag data for the first object from the original simulated data, thereby generating preprocessed training data from the original simulated data; and training a multi-object tracking model with the preprocessed training data to produce a trained multi-object tracker.

Abstract: Implementations of the present disclosure provide a solution for cross-domain image translation. In this solution, a first learning network for geometric deformation from a first to a second image domain is determined based on first and second images in the first and second domains, images in the two domains having different styles and objects in the images having geometric deformation with respect to each other. Geometric deformation from the second to the first domains is performed on the second image or geometric deformation from the first to the second domains is performed on the first image, to generate an intermediate image. A second learning network for style transfer from the first to the second domains is determined based on the first and intermediate images or based on the second and intermediate images generated. Accordingly, processing accuracy of leaning networks for cross-domain image translation can be improved and complexity is lowered.

Abstract: The present application discloses a woody rootstock for efficient grafting of solanaceous vegetables and an efficient grafting and seedling culture method thereof. According to the present application, a woody rootstock clone with high consistency is provided through tissue culture, efficient grafting is completed through sleeve grafting technology, and the grafting survival rate is improved by regulating the healing environment. A new idea for efficient industrial grafting of solanaceous vegetables is provided, scions are imparted with new features through distant grafting, and the problems of low grafting efficiency and low survival rate are solved. The method has the advantages of strong operability, simplicity, high efficiency and low cost, and provides a technical support for the industrial production of grafted seedlings of solanaceous vegetables.

Abstract: The disclosure herein enables tracking of multiple objects in a real-time video stream. For each individual frame received from the video stream, a frame type of the frame is determined. Based on the individual frame being an object detection frame type, a set of object proposals is detected in the individual frame, associations between the set of object proposals and a set of object tracks are assigned, and statuses of the set of object tracks are updated based on the assigned associations. Based on the individual frame being an object tracking frame type, single-object tracking is performed on the frame based on each object track of the set of object tracks and the set of object tracks is updated based on the performed single-object tracking. For each frame received, a real-time object location data stream is provided based on the set of object tracks.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for a virtual objection distribution method are provided. One of the methods includes: performing an image scanning to a local environment of a user; conducting image identification to an acquired image; acquiring an electronic certificate from a server if an image identifier is identified in the image; saving the electronic certificate; and, in response to a determination that a category count of the received electronic certificates reaches the threshold, sending to the server a virtual object distribution request to cause the server to distribute a virtual object to the user. This method significantly increases interactivity and entertainingness of a virtual object distribution process.

Abstract: An “Adaptive Exposure Corrector” performs automated real-time exposure correction of individual images or image sequences of arbitrary length. “Exposure correction” is defined herein as automated adjustments or corrections to any combination of shadows, highlights, high-frequency features, and color saturation of images. The Adaptive Exposure Corrector outputs perceptually improved images based on image ISO and camera ISO capabilities in combination with camera noise characteristics via exposure corrections by a variety of noise-aware image processing functions. An initial calibration process adapts these noise aware image processing functions to noise characteristics of particular camera models and types in combination with particular camera ISO settings. More specifically, this calibration process precomputes a Noise Aware Scaling Function (NASF) and a Color Scalar Function (CSF).

Abstract: An “Adaptive Exposure Corrector” performs automated real-time exposure correction of individual images or image sequences of arbitrary length. “Exposure correction” is defined herein as automated adjustments or corrections to any combination of shadows, highlights, high-frequency features, and color saturation of images. The Adaptive Exposure Corrector outputs perceptually improved images based on image ISO and camera ISO capabilities in combination with camera noise characteristics via exposure corrections by a variety of noise-aware image processing functions. An initial calibration process adapts these noise aware image processing functions to noise characteristics of particular camera models and types in combination with particular camera ISO settings. More specifically, this calibration process precomputes a Noise Aware Scaling Function (NASF) and a Color Scalar Function (CSF).

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for a virtual objection distribution method are provided. One of the methods includes: performing an image scanning to a local environment of a user; conducting image identification to an acquired image; acquiring an electronic certificate from a server if an image identifier is identified in the image; saving the electronic certificate; and, in response to a determination that a category count of the received electronic certificates reaches the threshold, sending to the server a virtual object distribution request to cause the server to distribute a virtual object to the user. This method significantly increases interactivity and entertainingness of a virtual object distribution process.