Patents by Inventor Junjie Ke
Junjie Ke 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).
-
Publication number: 20240119555Abstract: The technology employs a patch-based multi-scale Transformer (300) that is usable with various imaging applications. This avoids constraints on image fixed input size and predicts the quality effectively on a native resolution image. A native resolution image (304) is transformed into a multi-scale representation (302), enabling the Transformer's self-attention mechanism to capture information on both fine-grained detailed patches and coarse-grained global patches. Spatial embedding (316) is employed to map patch positions to a fixed grid, in which patch locations at each scale are hashed to the same grid. A separate scale embedding (318) is employed to distinguish patches coming from different scales in the multiscale representation. Self-attention (508) is performed to create a final image representation. In some instances, prior to performing self-attention, the system may prepend a learnable classification token (322) to the set of input tokens.Type: ApplicationFiled: December 4, 2023Publication date: April 11, 2024Inventors: Junjie Ke, Feng Yang, Qifei Wang, Yilin Wang, Peyman Milanfar
-
Patent number: 11887270Abstract: The technology employs a patch-based multi-scale Transformer (300) that is usable with various imaging applications. This avoids constraints on image fixed input size and predicts the quality effectively on a native resolution image. A native resolution image (304) is transformed into a multi-scale representation (302), enabling the Transformer's self-attention mechanism to capture information on both fine-grained detailed patches and coarse-grained global patches. Spatial embedding (316) is employed to map patch positions to a fixed grid, in which patch locations at each scale are hashed to the same grid. A separate scale embedding (318) is employed to distinguish patches coming from different scales in the multiscale representation. Self-attention (508) is performed to create a final image representation. In some instances, prior to performing self-attention, the system may prepend a learnable classification token (322) to the set of input tokens.Type: GrantFiled: July 1, 2021Date of Patent: January 30, 2024Assignee: Google LLCInventors: Junjie Ke, Feng Yang, Qifei Wang, Yilin Wang, Peyman Milanfar
-
Publication number: 20230319327Abstract: Methods, systems, and media for determining perceptual quality indicators of video content items are provided.Type: ApplicationFiled: June 8, 2022Publication date: October 5, 2023Inventors: Yilin Wang, Balineedu Adsumilli, Junjie Ke, Hossein Talebi, Joong Yim, Neil Birkbeck, Peyman Milanfar, Feng Yang
-
Publication number: 20230267307Abstract: Systems and methods of the present disclosure are directed to a method for generating a machine-learned multitask model configured to perform tasks. The method can include obtaining a machine-learned multitask search model comprising candidate nodes. The method can include obtaining tasks and machine-learned task controller models associated with the tasks. As an example, for a task, the method can include using the task controller model to route a subset of the candidate nodes in a machine-learned task submodel for the corresponding task. The method can include inputting task input data to the task submodel to obtain a task output. The method can include generating, using the task output, a feedback value based on an objective function. The method can include adjusting parameters of the task controller model based on the feedback value.Type: ApplicationFiled: July 23, 2020Publication date: August 24, 2023Inventors: Qifei Wang, Junjie Ke, Grace Chu, Gabriel Mintzer Bender, Luciano Sbaiz, Feng Yang, Andrew Gerald Howard, Alec Michael Go, Jeffrey M. Gilbert, Peyman Milanfar, Joshua William Charles Greaves
-
Publication number: 20230222623Abstract: The technology employs a patch-based multi-scale Transformer (300) that is usable with various imaging applications. This avoids constraints on image fixed input size and predicts the quality effectively on a native resolution image. A native resolution image (304) is transformed into a multi-scale representation (302), enabling the Transformer's self-attention mechanism to capture information on both fine-grained detailed patches and coarse-grained global patches. Spatial embedding (316) is employed to map patch positions to a fixed grid, in which patch locations at each scale are hashed to the same grid. A separate scale embedding (318) is employed to distinguish patches coming from different scales in the multiscale representation. Self-attention (508) is performed to create a final image representation. In some instances, prior to performing self-attention, the system may prepend a learnable classification token (322) to the set of input tokens.Type: ApplicationFiled: July 1, 2021Publication date: July 13, 2023Inventors: Junjie Ke, Feng Yang, Qifei Wang, Yilin Wang, Peyman Milanfar
-
Publication number: 20220358537Abstract: Systems, devices, methods, and computer readable medium for evaluating visual quality of digital content are disclosed. Methods can include identifying content assets including one or more images that are combined to create different digital components distributed to one or more client devices. A quality of each of the one or more images is evaluated using one or more machine learning models trained to evaluate one or more visual aspects that are deemed indicative of visual quality. An aggregate quality for the content assets is determined based, at least in part, on an output of the one or more machine learning models indicating the visual quality of each of the one or more images. A graphical user interface of a first computing device is updated to present a visual indication of the aggregate quality of the content assets.Type: ApplicationFiled: August 6, 2020Publication date: November 10, 2022Inventors: Catherine Shyu, Luying Li, Feng Yang, Junjie Ke, Xiyang Luo, Hao Feng, Chao-Hung Chen, Wenjing Kang, Zheng Xia, Shun-Chuan Chen, Yicong Tian, Xia Li, Han Ke
-
Publication number: 20220301141Abstract: Systems, devices, methods, and computer readable medium for evaluating visual quality of digital content are disclosed. Methods can include training machine learning models on images. A request is received to evaluate quality of an image included in a current version of a digital component generated by the computing device. The machine learning models are deployed on the image to generate a score for each quality characteristic of the image. A weight is assigned to each score to generate weighted scores. The weighted scores are combined to generate a combined score for the image. The combined score is compared to one or more thresholds to generate a quality of the image.Type: ApplicationFiled: August 6, 2020Publication date: September 22, 2022Inventors: Catherine Shyu, Xiyang Luo, Feng Yang, Junjie Ke, Yicong Tian, Chao-Hung Chen, Xia Li, Luying Li, Wenjing Kang, Shun-Chuan Chen
-
Patent number: 10769441Abstract: The technology relates to navigating imagery that is organized into clusters based on common patterns exhibited when imagery is captured. For example, a set of captured images which satisfy a predetermined pattern may be determined. The images in the set of set of captured images may be grouped into one or more clusters according to the predetermined pattern. A request to display a first cluster of the one or more clusters may be received and, in response, a first captured image from the requested first cluster may be selected. The selected first captured image may then be displayed.Type: GrantFiled: July 17, 2017Date of Patent: September 8, 2020Assignee: Google LLCInventors: Guiheng Zhou, Liyong Chen, Hui Lou, Junjie Ke, Hao Chen, Deben Kong, David Robert Gallup
-
Publication number: 20180005036Abstract: The technology relates to navigating imagery that is organized into clusters based on common patterns exhibited when imagery is captured. For example, a set of captured images which satisfy a predetermined pattern may be determined. The images in the set of set of captured images may be grouped into one or more clusters according to the predetermined pattern. A request to display a first cluster of the one or more clusters may be received and, in response, a first captured image from the requested first cluster may be selected. The selected first captured image may then be displayed.Type: ApplicationFiled: July 17, 2017Publication date: January 4, 2018Inventors: Guiheng Zhou, Liyong Chen, Hui Lou, Junjie Ke, Hao Chen, Deben Kong, David Robert Gallup
-
Patent number: 9740936Abstract: The technology relates to navigating imagery that is organized into clusters based on common patterns exhibited when imagery is captured. For example, a set of captured images which satisfy a predetermined pattern may be determined. The images in the set of set of captured images may be grouped into one or more clusters according to the predetermined pattern. A request to display a first cluster of the one or more clusters may be received and, in response, a first captured image from the requested first cluster may be selected. The selected first captured image may then be displayed.Type: GrantFiled: March 27, 2015Date of Patent: August 22, 2017Assignee: Google Inc.Inventors: Guiheng Zhou, Liyong Chen, Hui Lou, Junjie Ke, Hao Chen, Deben Kong, David Robert Gallup
-
Publication number: 20160283826Abstract: The technology relates to navigating imagery that is organized into clusters based on common patterns exhibited when imagery is captured. For example, a set of captured images which satisfy a predetermined pattern may be determined. The images in the set of set of captured images may be grouped into one or more clusters according to the predetermined pattern. A request to display a first cluster of the one or more clusters may be received and, in response, a first captured image from the requested first cluster may be selected. The selected first captured image may then be displayed.Type: ApplicationFiled: March 27, 2015Publication date: September 29, 2016Inventors: Guiheng Zhou, Liyong Chen, Hui Lou, Junjie Ke, Hao Chen, Deben Kong, David Robert Gallup