Patents by Inventor Irfan Aziz Essa
Irfan Aziz Essa 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: 11900517Abstract: A method for generating an output image from an input image and an input text instruction that specifies a location and a modification of an edit applied to the input image using a neural network is described. The neural network includes an image encoder, an image decoder, and an instruction attention network. The method includes receiving the input image and the input text instruction; extracting, from the input image, an input image feature that represents features of the input image using the image encoder; generating a spatial feature and a modification feature from the input text instruction using the instruction attention network; generating an edited image feature from the input image feature, the spatial feature and the modification feature; and generating the output image from the edited image feature using the image decoder.Type: GrantFiled: December 20, 2022Date of Patent: February 13, 2024Assignee: Google LLCInventors: Tianhao Zhang, Weilong Yang, Honglak Lee, Hung-Yu Tseng, Irfan Aziz Essa, Lu Jiang
-
Publication number: 20230177754Abstract: A method for generating an output image from an input image and an input text instruction that specifies a location and a modification of an edit applied to the input image using a neural network is described. The neural network includes an image encoder, an image decoder, and an instruction attention network. The method includes receiving the input image and the input text instruction; extracting, from the input image, an input image feature that represents features of the input image using the image encoder; generating a spatial feature and a modification feature from the input text instruction using the instruction attention network; generating an edited image feature from the input image feature, the spatial feature and the modification feature; and generating the output image from the edited image feature using the image decoder.Type: ApplicationFiled: December 20, 2022Publication date: June 8, 2023Inventors: Tianhao Zhang, Weilong Yang, Honglak Lee, Hung-Yu Tseng, Irfan Aziz Essa, Lu Jiang
-
Patent number: 11562518Abstract: A method for generating an output image from an input image and an input text instruction that specifies a location and a modification of an edit applied to the input image using a neural network is described. The neural network includes an image encoder, an image decoder, and an instruction attention network. The method includes receiving the input image and the input text instruction; extracting, from the input image, an input image feature that represents features of the input image using the image encoder; generating a spatial feature and a modification feature from the input text instruction using the instruction attention network; generating an edited image feature from the input image feature, the spatial feature and the modification feature; and generating the output image from the edited image feature using the image decoder.Type: GrantFiled: June 7, 2021Date of Patent: January 24, 2023Assignee: Google LLCInventors: Tianhao Zhang, Weilong Yang, Honglak Lee, Hung-Yu Tseng, Irfan Aziz Essa, Lu Jiang
-
Publication number: 20210383584Abstract: A method for generating an output image from an input image and an input text instruction that specifies a location and a modification of an edit applied to the input image using a neural network is described. The neural network includes an image encoder, an image decoder, and an instruction attention network. The method includes receiving the input image and the input text instruction; extracting, from the input image, an input image feature that represents features of the input image using the image encoder; generating a spatial feature and a modification feature from the input text instruction using the instruction attention network; generating an edited image feature from the input image feature, the spatial feature and the modification feature; and generating the output image from the edited image feature using the image decoder.Type: ApplicationFiled: June 7, 2021Publication date: December 9, 2021Inventors: Tianhao Zhang, Weilong Yang, Honglak Lee, Hung-Yu Tseng, Irfan Aziz Essa, Lu Jiang
-
Patent number: 10635979Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining a clustering of images into a plurality of semantic categories. In one aspect, a method comprises: training a categorization neural network, comprising, at each of a plurality of iterations: processing an image depicting an object using the categorization neural network to generate (i) a current prediction for whether the image depicts an object or a background region, and (ii) a current embedding of the image; determining a plurality of current cluster centers based on the current values of the categorization neural network parameters, wherein each cluster center represents a respective semantic category; and determining a gradient of an objective function that includes a classification loss and a clustering loss, wherein the clustering loss depends on a similarity between the current embedding of the image and the current cluster centers.Type: GrantFiled: July 15, 2019Date of Patent: April 28, 2020Assignee: Google LLCInventors: Steven Hickson, Anelia Angelova, Irfan Aziz Essa, Rahul Sukthankar
-
Publication number: 20200027002Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining a clustering of images into a plurality of semantic categories. In one aspect, a method comprises: training a categorization neural network, comprising, at each of a plurality of iterations: processing an image depicting an object using the categorization neural network to generate (i) a current prediction for whether the image depicts an object or a background region, and (ii) a current embedding of the image; determining a plurality of current cluster centers based on the current values of the categorization neural network parameters, wherein each cluster center represents a respective semantic category; and determining a gradient of an objective function that includes a classification loss and a clustering loss, wherein the clustering loss depends on a similarity between the current embedding of the image and the current cluster centers.Type: ApplicationFiled: July 15, 2019Publication date: January 23, 2020Inventors: Steven Hickson, Anelia Angelova, Irfan Aziz Essa, Rahul Sukthankar
-
Patent number: 9600760Abstract: Described herein are methods, systems, apparatuses and products for utilizing motion fields to predict evolution in dynamic scenes. One aspect provides for accessing active object position data including positioning information of a plurality of individual active objects; extracting a plurality of individual active object motions from the active object position data; constructing a motion field using the plurality of individual active object motions; and using the motion field to predict one or more points of convergence at one or more spatial locations that active objects are proceeding towards at a future point in time. Other embodiments are disclosed.Type: GrantFiled: March 30, 2011Date of Patent: March 21, 2017Assignee: Disney Enterprises, Inc.Inventors: Irfan Aziz Essa, Matthias Grundmann, Jessica Kate Hodgins, Kihwan Kim, Iain Alexander Matthews, Ariel Shamir
-
Publication number: 20110242326Abstract: Described herein are methods, systems, apparatuses and products for utilizing motion fields to predict evolution in dynamic scenes. One aspect provides for accessing active object position data including positioning information of a plurality of individual active objects; extracting a plurality of individual active object motions from the active object position data; constructing a motion field using the plurality of individual active object motions; and using the motion field to predict one or more points of convergence at one or more spatial locations that active objects are proceeding towards at a future point in time. Other embodiments are disclosed.Type: ApplicationFiled: March 30, 2011Publication date: October 6, 2011Applicant: Disney Enterprises, Inc.Inventors: Irfan Aziz Essa, Matthias Grundmann, Jessica Kate Hodgins, Kihwan Kim, Iain Alexander Matthews, Ariel Shamir