Patents by Inventor Xiaoheng Jiang
Xiaoheng Jiang has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11270441Abstract: Methods and apparatus, including computer program products, are provided for depth-aware object counting. In some example embodiments, there may be provided a method that includes processing, by the trained machine learning model, a first segment of an image and a second segment of the image, the first segment being processed using a first filter selected, based on depth information, to enable formation of a first density map, and the second segment being processed using a second filter selected, based on the depth information, to enable formation of a second density map; combining, by the trained machine learning model, the first density map and the second density map to form a density map for the image; and providing, by the trained machine learning model, an output based on the density map. Related systems, methods, and articles of manufacture are also described.Type: GrantFiled: November 1, 2017Date of Patent: March 8, 2022Assignee: Nokia Technologies OyInventor: Xiaoheng Jiang
-
Patent number: 10956788Abstract: According to an example aspect of the present invention, there is provided an apparatus comprising memory configured to store data defining, at least partly, an artificial neural network, and at least one processing core configured to train the artificial neural network by applying a test dataset to the artificial neural network with at least one stochastic rectified linear unit, the at least one stochastic rectified linear unit being configured to produce a positive output from a positive input by multiplying the input with a stochastically selected value.Type: GrantFiled: August 8, 2016Date of Patent: March 23, 2021Assignee: Nokia Technologies OyInventor: Xiaoheng Jiang
-
Publication number: 20200242777Abstract: Methods and apparatus, including computer program products, are provided for depth-aware object counting. In some example embodiments, there may be provided a method that includes processing, by the trained machine learning model, a first segment of an image and a second segment of the image, the first segment being processed using a first filter selected, based on depth information, to enable formation of a first density map, and the second segment being processed using a second filter selected, based on the depth information, to enable formation of a second density map; combining, by the trained machine learning model, the first density map and the second density map to form a density map for the image; and providing, by the trained machine learning model, an output based on the density map. Related systems, methods, and articles of manufacture are also described.Type: ApplicationFiled: November 1, 2017Publication date: July 30, 2020Inventor: Xiaoheng JIANG
-
Patent number: 10614339Abstract: According to an example aspect of the present invention, there is provided an apparatus comprising at least one processing core, at least one memory including computer program code, the at least one memory and the computer program code being configured to, with the at least one processing core, cause the apparatus at least to provide an input data item to a first convolutional layer of an artificial neural network comprising a set of convolutional layers, process the input data item in the set of convolutional layers, define, in a feature map output from a last convolutional layer of the set of convolutional layers, a first feature map patch and a second feature map patch, and provide the first feature map patch to a first classifier and the second feature map patch to a second classifier.Type: GrantFiled: July 29, 2015Date of Patent: April 7, 2020Assignee: Nokia Technologies OyInventor: Xiaoheng Jiang
-
Publication number: 20200005151Abstract: According to an example aspect of the present invention, there is provided a method, comprising: resizing a convolutional layer input of an artificial neural network with at least two different scales to obtain multiple groups of intermediate features maps, convolving the intermediate feature maps with a filter, resizing the convolution results to the size of the layer input, and concatenating the resized convolution results to form an output of the convolutional layer.Type: ApplicationFiled: December 30, 2016Publication date: January 2, 2020Inventor: Xiaoheng JIANG
-
Publication number: 20190180148Abstract: According to an example aspect of the present invention, there is provided an apparatus comprising memory configured to store data defining, at least partly, an artificial neural network, and at least one processing core configured to train the artificial neural network by applying a test dataset to the artificial neural network with at least one stochastic rectified linear unit, the at least one stochastic rectified linear unit being configured to produce a positive output from a positive input by multiplying the input with a stochastically selected value.Type: ApplicationFiled: August 8, 2016Publication date: June 13, 2019Inventor: Xiaoheng JIANG
-
Patent number: 10275688Abstract: According to an example aspect of the present invention, there is provided an apparatus comprising at least one processing core and at least one memory including computer program code, the at least one memory and the computer program code being configured to, with the at least one processing core, cause the apparatus at least to nm a convolutional neural network comprising an input layer arranged to provide signals to a first convolutional layer and a last convolutional layer, run a first intermediate classifier, the first intermediate classifier operating on a set of feature maps of the first convolutional layer, and decide to abort or to continue processing of a signal set based on a decision of the first intermediate classifier.Type: GrantFiled: December 17, 2014Date of Patent: April 30, 2019Assignee: Nokia Technologies OyInventor: Xiaoheng Jiang
-
Publication number: 20180211130Abstract: According to an example aspect of the present invention, there is provided an apparatus comprising at least one processing core, at least one memory including computer program code, the at least one memory and the computer program code being configured to, with the at least one processing core, cause the apparatus at least to provide an input data item to a first convolutional layer of an artificial neural network comprising a set of convolutional layers, process the input data item in the set of convolutional layers, define, in a feature map output from a last convolutional layer of the set of convolutional layers, a first feature map patch and a second feature map patch, and provide the first feature map patch to a first classifier and the second feature map patch to a second classifier.Type: ApplicationFiled: July 29, 2015Publication date: July 26, 2018Inventor: Xiaoheng JIANG
-
Publication number: 20170351936Abstract: According to an example aspect of the present invention, there is provided an apparatus comprising at least one processing core and at least one memory including computer program code, the at least one memory and the computer program code being configured to, with the at least one processing core, cause the apparatus at least to nm a convolutional neural network comprising an input layer arranged to provide signals to a first convolutional layer and a last convolutional layer, run a first intermediate classifier, the first intermediate classifier operating on a set of feature maps of the first convolutional layer, and decide to abort or to continue processing of a signal set based on a decision of the first intermediate classifier.Type: ApplicationFiled: December 17, 2014Publication date: December 7, 2017Inventor: Xiaoheng Jiang