Patents by Inventor Shengyang Dai
Shengyang Dai 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: 11829404Abstract: Some implementations related to archiving of functional images. In some implementations, a method includes accessing images and determining one or more functional labels corresponding to each of the images and one or more confidence scores corresponding to the functional labels. A functional image score is determined for each of the images based on the functional labels having a corresponding confidence score that meets a respective threshold for the functional labels. In response to determining that the functional image score meets a functional image score threshold, a functional image signal is provided that indicates that one or more of the images that meet the functional image score threshold are functional images. The functional images are determined to be archived, and are archived by associating an archive attribute with the functional images such that functional images having the archive attribute are excluded from display in views of the images.Type: GrantFiled: December 11, 2020Date of Patent: November 28, 2023Assignee: Google LLCInventors: Shinko Cheng, Eunyoung Kim, Shengyang Dai, Madhur Khandelwal, Kristina Eng, David Loxton
-
Patent number: 11816710Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for converting unstructured documents to structured key-value pairs. In one aspect, a method includes: providing an image of a document to a detection model, wherein: the detection model is configured to process the image to generate an output that defines one or more bounding boxes generated for the image; and each bounding box generated for the image is predicted to enclose a key-value pair including key textual data and value textual data, wherein the key textual data defines a label that characterizes the value textual data; and for each of the one or more bounding boxes generated for the image: identifying textual data enclosed by the bounding box using an optical character recognition technique; and determining whether the textual data enclosed by the bounding box defines a key-value pair.Type: GrantFiled: March 1, 2022Date of Patent: November 14, 2023Assignee: Google LLCInventors: Yang Xu, Jiang Wang, Shengyang Dai
-
Publication number: 20220414425Abstract: Methods, and systems, including computer programs encoded on computer storage media for neural network architecture search.Type: ApplicationFiled: August 19, 2022Publication date: December 29, 2022Applicant: Google LLCInventors: Ming-Hsuan Yang, Xiaojie Jin, Joshua Foster Slocum, Shengyang Dai, Jiang Wang
-
Publication number: 20220309549Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for converting unstructured documents to structured key-value pairs. In one aspect, a method includes: providing an image of a document to a detection model, wherein: the detection model is configured to process the image to generate an output that defines one or more bounding boxes generated for the image; and each bounding box generated for the image is predicted to enclose a key-value pair including key textual data and value textual data, wherein the key textual data defines a label that characterizes the value textual data; and for each of the one or more bounding boxes generated for the image: identifying textual data enclosed by the bounding box using an optical character recognition technique; and determining whether the textual data enclosed by the bounding box defines a key-value pair.Type: ApplicationFiled: March 1, 2022Publication date: September 29, 2022Applicant: Google LLCInventors: Yang Xu, Jiang Wang, Shengyang Dai
-
Patent number: 11443162Abstract: Methods, and systems, including computer programs encoded on computer storage media for neural network architecture search.Type: GrantFiled: August 23, 2019Date of Patent: September 13, 2022Assignee: Google LLCInventors: Ming-Hsuan Yang, Xiaojie Jin, Joshua Foster Slocum, Shengyang Dai, Jiang Wang
-
Publication number: 20220254137Abstract: A computing system for detecting objects in an image can perform operations including generating an image pyramid that includes a first level corresponding with the image at a first resolution and a second level corresponding with the image at a second resolution. The operations can include tiling the first level and the second level by dividing the first level into a first plurality of tiles and the second level into a second plurality of tiles; inputting the first plurality of tiles and the second plurality of tiles into a machine-learned object detection model; receiving, as an output of the machine-learned object detection model, object detection data that includes bounding boxes respectively defined with respect to individual ones of the first plurality of tiles and the second plurality of tiles; and generating image object detection output by mapping the object detection data onto an image space of the image.Type: ApplicationFiled: August 5, 2019Publication date: August 11, 2022Inventors: Jilin Tu, Jiang Wang, Huizhong Chen, Xiangxin Zhu, Shengyang Dai
-
Publication number: 20220172456Abstract: The present disclosure provides systems and methods that include or otherwise leverage an object detection training model for training a machine-learned object detection model. In particular, the training model can obtain first training data and train the machine-learned object detection model using the first training data. The training model can obtain second training data and input the second training data into the machine-learned object detection model, and receive as an output of the machine-learned object detection model, data that describes the location of a detected object of a target category within images from the second training data. The training model can determine mined training data based on the output of the machine-learned object detection model, and train the machine-learned object detection model based on the mined training data.Type: ApplicationFiled: March 8, 2019Publication date: June 2, 2022Inventors: Jiang Wang, Jiyang Gao, Shengyang Dai
-
Patent number: 11288719Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for converting unstructured documents to structured key-value pairs. In one aspect, a method comprises: providing an image of a document to a detection model, wherein: the detection model is configured to process the image to generate an output that defines one or more bounding boxes generated for the image; and each bounding box generated for the image is predicted to enclose a key-value pair comprising key textual data and value textual data, wherein the key textual data defines a label that characterizes the value textual data; and for each of the one or more bounding boxes generated for the image: identifying textual data enclosed by the bounding box using an optical character recognition technique; and determining whether the textual data enclosed by the bounding box defines a key-value pair.Type: GrantFiled: February 27, 2020Date of Patent: March 29, 2022Assignee: Google LLCInventors: Yang Xu, Jiang Wang, Shengyang Dai
-
Patent number: 11146520Abstract: Implementations relate to sharing images and image albums over a communication network. In some implementations, a computer-implemented method includes determining that a shared album data structure is accessible by a device and includes references to album images. The device determines one or more suggested images from a collection of stored images associated with a user, based on determining sharing scores for the stored images. The sharing scores are based on comparing one or more characteristics of the stored images to one or more corresponding characteristics of the album images. The method includes causing display of the one or more suggested images by the device, receiving a selection of at least one selected image of the suggested images based on received user input, and causing an update of the shared album data structure with the at least one selected image to be accessible over a communication network by recipient users.Type: GrantFiled: November 6, 2019Date of Patent: October 12, 2021Assignee: Google LLCInventors: David Lieb, James Gallagher, Kedar Jayant Kanitkar, Teresa Ko, Loren Puchalla Fiore, Jason Chang, Nan Wang, Jingyu Cui, Shengyang Dai
-
Publication number: 20210097353Abstract: Some implementations related to archiving of functional images. In some implementations, a method includes accessing images and determining one or more functional labels corresponding to each of the images and one or more confidence scores corresponding to the functional labels. A functional image score is determined for each of the images based on the functional labels having a corresponding confidence score that meets a respective threshold for the functional labels. In response to determining that the functional image score meets a functional image score threshold, a functional image signal is provided that indicates that one or more of the images that meet the functional image score threshold are functional images. The functional images are determined to be archived, and are archived by associating an archive attribute with the functional images such that functional images having the archive attribute are excluded from display in views of the images.Type: ApplicationFiled: December 11, 2020Publication date: April 1, 2021Applicant: Google LLCInventors: Shinko CHENG, Eunyoung KIM, Shengyang DAI, Madhur KHANDELWAL, Kristina ENG, David LOXTON
-
Publication number: 20210056378Abstract: Methods, and systems, including computer programs encoded on computer storage media for neural network architecture search.Type: ApplicationFiled: August 23, 2019Publication date: February 25, 2021Inventors: Ming-Hsuan Yang, Xiaojie Jin, Joshua Foster Slocum, Shengyang Dai, Jiang Wang
-
Patent number: 10891526Abstract: Some implementations related to archiving of functional images. In some implementations, a method includes accessing images and determining one or more functional labels corresponding to each of the images and one or more confidence scores corresponding to the functional labels. A functional image score is determined for each of the images based on the functional labels having a corresponding confidence score that meets a respective threshold for the functional labels. In response to determining that the functional image score meets a functional image score threshold, a functional image signal is provided that indicates that one or more of the images that meet the functional image score threshold are functional images. The functional images are determined to be archived, and are archived by associating an archive attribute with the functional images such that functional images having the archive attribute are excluded from display in views of the images.Type: GrantFiled: December 21, 2018Date of Patent: January 12, 2021Assignee: Google LLCInventors: Shinko Cheng, Eunyoung Kim, Shengyang Dai, Madhur Khandelwal, Kristina Eng, David Loxton
-
Publication number: 20200273078Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for converting unstructured documents to structured key-value pairs. In one aspect, a method comprises: providing an image of a document to a detection model, wherein: the detection model is configured to process the image to generate an output that defines one or more bounding boxes generated for the image; and each bounding box generated for the image is predicted to enclose a key-value pair comprising key textual data and value textual data, wherein the key textual data defines a label that characterizes the value textual data; and for each of the one or more bounding boxes generated for the image: identifying textual data enclosed by the bounding box using an optical character recognition technique; and determining whether the textual data enclosed by the bounding box defines a key-value pair.Type: ApplicationFiled: February 27, 2020Publication date: August 27, 2020Inventors: Yang Xu, Jiang Wang, Shengyang Dai
-
Patent number: 10685680Abstract: A method includes grouping media items associated with a user into segments based on a timestamp associated with each media item and a total number of media items. The method also includes selecting target media from the media items for each of the segments based on media attributes associated with the media item. The method also includes generating a video that includes the target media for each of the segments by generating a first animation that illustrates a first transition from a first item from the target media to a second item from the target media with movement of the first item from an onscreen location to an offscreen location, wherein the first item is adjacent to the second item in the first animation and determining whether the target media includes one or more additional items. The method also includes adding a song to the video.Type: GrantFiled: March 20, 2019Date of Patent: June 16, 2020Assignee: Google LLCInventors: Shengyang Dai, Timothy Sepkoski St. Clair, Koji Ashida, Jingyu Cui, Jay Steele, Qi Gu, Erik Murphy-Chutorian, Ivan Neulander, Flavio Lerda, Eric Charles Henry, Shinko Yuanhsien Cheng, Aravind Krishnaswamy, David Cohen, Pardis Beikzadeh
-
Publication number: 20200076756Abstract: Implementations relate to sharing images and image albums over a communication network. In some implementations, a computer-implemented method includes determining that a shared album data structure is accessible by a device and includes references to album images. The device determines one or more suggested images from a collection of stored images associated with a user, based on determining sharing scores for the stored images. The sharing scores are based on comparing one or more characteristics of the stored images to one or more corresponding characteristics of the album images. The method includes causing display of the one or more suggested images by the device, receiving a selection of at least one selected image of the suggested images based on received user input, and causing an update of the shared album data structure with the at least one selected image to be accessible over a communication network by recipient users.Type: ApplicationFiled: November 6, 2019Publication date: March 5, 2020Applicant: Google LLCInventors: David LIEB, James GALLAGHER, Kedar Jayant KANITKAR, Teresa KO, Loren PUCHALLA FIORE, Jason CHANG, Nan WANG, Jingyu CUI, Shengyang DAI
-
Patent number: 10476827Abstract: Implementations relate to sharing images and image albums over a communication network. In some implementations, a computer-implemented method includes determining that a shared album data structure is accessible by a device and includes references to album images. The device determines one or more suggested images from a collection of stored images associated with a user, based on determining sharing scores for the stored images. The sharing scores are based on comparing one or more characteristics of the stored images to one or more corresponding characteristics of the album images. The method includes causing display of the one or more suggested images by the device, receiving a selection of at least one selected image of the suggested images based on received user input, and causing an update of the shared album data structure with the at least one selected image to be accessible over a communication network by recipient users.Type: GrantFiled: September 27, 2016Date of Patent: November 12, 2019Assignee: Google LLCInventors: David Lieb, James Gallagher, Kedar Jayant Kanitkar, Teresa Ko, Loren Puchalla Fiore, Jason Chang, Nan Wang, Jingyu Cui, Shengyang Dai
-
Publication number: 20190252001Abstract: A method includes grouping media items associated with a user into segments based on a timestamp associated with each media item and a total number of media items. The method also includes selecting target media from the media items for each of the segments based on media attributes associated with the media item. The method also includes generating a video that includes the target media for each of the segments by generating a first animation that illustrates a first transition from a first item from the target media to a second item from the target media with movement of the first item from an onscreen location to an offscreen location, wherein the first item is adjacent to the second item in the first animation and determining whether the target media includes one or more additional items. The method also includes adding a song to the video.Type: ApplicationFiled: March 20, 2019Publication date: August 15, 2019Applicant: Google LLCInventors: Shengyang DAI, Timothy Sepkoski ST. CLAIR, Koji ASHIDA, Jingyu CUI, Jay STEELE, Qi GU, Erik MURPHY-CHUTORIAN, Ivan NEULANDER, Flavio LERDA, Eric Charles HENRY, Shinko Yuanhsien CHENG, Aravind KRISHNASWAMY, David COHEN, Pardis BEIKZADEH
-
Publication number: 20190197364Abstract: Some implementations related to archiving of functional images. In some implementations, a method includes accessing images and determining one or more functional labels corresponding to each of the images and one or more confidence scores corresponding to the functional labels. A functional image score is determined for each of the images based on the functional labels having a corresponding confidence score that meets a respective threshold for the functional labels. In response to determining that the functional image score meets a functional image score threshold, a functional image signal is provided that indicates that one or more of the images that meet the functional image score threshold are functional images. The functional images are determined to be archived, and are archived by associating an archive attribute with the functional images such that functional images having the archive attribute are excluded from display in views of the images.Type: ApplicationFiled: December 21, 2018Publication date: June 27, 2019Applicant: Google LLCInventors: Shinko CHENG, Eunyoung KIM, Shengyang DAI, Madhur KHANDELWAL, Kristina ENG, David LOXTON
-
Patent number: 10242711Abstract: A method includes grouping media items associated with a user into segments based on a timestamp associated with each media item and a total number of media items. The method also includes selecting target media from the media items for each of the segments based on media attributes associated with the media item. The method also includes generating a video that includes the target media for each of the segments by generating a first animation that illustrates a first transition from a first item from the target media to a second item from the target media with movement of the first item from an onscreen location to an offscreen location, wherein the first item is adjacent to the second item in the first animation and determining whether the target media includes one or more additional items. The method also includes adding a song to the video.Type: GrantFiled: June 26, 2017Date of Patent: March 26, 2019Assignee: Google LLCInventors: Shengyang Dai, Timothy Sepkoski St. Clair, Koji Ashida, Jingyu Cui, Jay Steele, Qi Gu, Erik Murphy-Chutorian, Ivan Neulander, Flavio Lerda, Eric Charles Henry, Shinko Yuanhsien Cheng, Aravind Krishnaswamy, David Cohen, Pardis Beikzadeh
-
Patent number: 9965882Abstract: Implementations generally relate to generating image compositions. In some implementations, a method includes receiving a plurality of photos from a user and determining one or more composition types from the photos. The method further includes generating one or more compositions from the received photos based on the one or more determined composition types, where each composition is based on modified foregrounds of the photos. The method further includes providing the one or more generated compositions to the user.Type: GrantFiled: October 3, 2016Date of Patent: May 8, 2018Assignee: Google LLCInventors: Erik Murphy-Chutorian, Matthew Steiner, Vahid Kazemi, Shengyang Dai