Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for collaboratively training an interaction prediction machine learning model using a plurality of user devices in a manner that respects user privacy. In one aspect, the machine learning model is configured to process an input comprising: (i) a search query, and (ii) a data element, to generate an output which characterizes a likelihood that a given user would interact with the data element if the data element were presented to the given user on a webpage identified by a search result responsive to the search query.

There is provided an encoding device, encoding method, decoding device, and decoding method that make it possible to improve the coding efficiency. The encoding device and the decoding device each perform classification of classifying a pixel of interest of a decoding in-progress image into any of a plurality of classes by using an inclination feature amount, and perform a filter arithmetic operation with the decoding in-progress image by using a tap coefficient of a class of the pixel of interest among tap coefficients of the respective classes. The inclination feature amount indicates a tangent direction of a contour line of pixel values of the pixel of interest. The decoding in-progress image is obtained by adding a residual of predictive coding and a predicted image together. The tap coefficients of the respective classes are each obtained through learning for minimizing an error by using the decoding in-progress image and an original image. The original image corresponds to the decoding in-progress image. The present technology is applicable in a case where an image is encoded or decoded.

Methods and image processing systems are provided for determining a dominant gradient orientation for a target region within an image. A plurality of gradient samples are determined for the target region, wherein each of the gradient samples represents a variation in pixel values within the target region. The gradient samples are converted into double-angle gradient vectors, and the double-angle gradient vectors are combined so as to determine a dominant gradient orientation for the target region.

In exemplary embodiments, methods and systems are provided for controlling an auto high beam functionality for headlights of a vehicle. In an exemplary embodiment, a method includes: obtaining camera data pertaining to an object in front of the vehicle; identifying, via a processor, a radial gradient of pixels in a region of interest from the camera data; and automatically controlling, via the processor, the auto high beam functionality for the headlights based on the radial gradient.

The present disclosure relates to systems and methods for image processing. The system may obtain at least one image of an object. For each of the at least one image, the system may determine a recognition result of the image. The recognition result may include an image type of the image, a type of a lesion in the image, a region of the lesion in the image, and/or an image feature of the image. Further, the system may process the at least one image of the object based on at least one recognition result corresponding to the at least one image.

In exemplary embodiments, methods and systems are provided for controlling an auto high beam functionality for headlights of a vehicle. In an exemplary embodiment, a method includes: obtaining camera data pertaining to an object in front of the vehicle; identifying, via a processor, a radial gradient of pixels in a region of interest from the camera data; and automatically controlling, via the processor, the auto high beam functionality for the headlights based on the radial gradient.

A system and process for extracting information from filled form images is described. In one example, the claimed invention first extracts textual information and the hierarchy in a blank form. This information is then used to extract and understand the content of filled forms. In this way, the system does not have to analyze from the beginning each filled form. The system is designed so that it remains as generic as possible. The number of hard-coded rules in the whole pipeline was minimized to offer an adaptive solution able to address the largest number of forms, with various structures and typography. The system is also created to be integrated as a built-in function in a larger pipeline. The form understanding pipeline could be the starting point of any advanced Natural Language Processing application.

A computer-implemented method for training a normalizing flow. The normalizing flow predicts a first density value based on a first input image. The first density value characterizes a likelihood of the first input image to occur. The first density value is predicted based on an intermediate output of a first convolutional layer of the normalizing flow. The intermediate output is determined based on a plurality of weights of the first convolutional layer. The method for training includes: determining a second input image; determining an output, wherein the output is determined by providing the second input image to the normalizing flow and providing an output of the normalizing flow as output; determining a second density value based on the output tensor and on the plurality of weights; determining a natural gradient of the plurality of weights with respect to the second density value; adapting the weights according to the natural gradient.

A system and process for extracting information from filled form images is described. In one example the claimed invention first extracts textual information and the hierarchy in a blank form. This information is then used to extract and understand the content of filled forms. In this way, the system does not have to analyze from the beginning each filled form. The system is designed so that it remains as generic as possible. The number of hard coded rules in the whole pipeline was minimized to offer an adaptive solution able to address the largest number of forms, with various structures and typography. The system is also created to be integrated as a built-in function in a larger pipeline. The form understanding pipeline could be the starting point of any advanced Natural Language Processing application.

The present disclosure provides a face image quality evaluating method as well as an apparatus and a computer-readable storage medium using the same. The method includes: obtaining a face image; determining a local bright area in the face image, wherein the local bright area is formed by an illumination source in the face image, and the brightness of the local bright area is greater than the brightness of a face area in the face image; removing the local bright area from the face image; and evaluating a quality of the face image based on the face image having removed the local bright area. In the above-mentioned manner, the present disclosure improves the accuracy of the quality evaluation of the face image.