Patents by Inventor Dahua Lin
Dahua Lin 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: 20190138798Abstract: Time domain action detecting methods and systems, electronic devices, and computer storage medium are provided. The method includes: obtaining a time domain interval in a video with an action instance and at least one adjacent segment in the time domain interval; separately extracting action features of at least two video segments in candidate segments, where the candidate segments comprises video segment corresponding to the time domain interval and adjacent segments thereof; pooling the action features of the at least two video segments in the candidate segments, to obtain a global feature of the video segment corresponding to the time domain interval; and determining, based on the global feature, an action integrity score of the video segment corresponding to the time domain interval. The embodiments of the present disclosure benefit accurately determining whether a time domain interval comprises an integral action instance, and improve the accuracy rate of action integrity identification.Type: ApplicationFiled: December 28, 2018Publication date: May 9, 2019Applicant: Beijing SenseTime Technology Development Co., LtdInventors: Xiaoou TANG, Yuanjun XIONG, Yue ZHAO, Limin WANG, Zhirong WU, Dahua LIN
-
Patent number: 10275714Abstract: A method described herein includes receiving a digital image, wherein the digital image includes a first element that corresponds to a first domain and a second element that corresponds to a second domain. The method also includes automatically assigning a label to the first element in the digital image based at least in part upon a computed probability that the label corresponds to the first element, wherein the probability is computed through utilization of a first model that is configured to infer labels for elements in the first domain and a second model that is configured to infer labels for elements in the second domain. The first model receives data that identifies learned relationships between elements in the first domain and elements in the second domain, and the probability is computed by the first model based at least in part upon the learned relationships.Type: GrantFiled: January 9, 2014Date of Patent: April 30, 2019Assignee: Microsoft Technology Licensing, LLCInventors: Simon John Baker, Ashish Kapoor, Gang Hua, Dahua Lin
-
Publication number: 20180276542Abstract: A recommendation result generation method, where the method includes obtaining article content information of at least one article and user score information of at least one user, where user score information of a first user of the at least one user includes a historical score of the first user for the at least one article, encoding the article content information and the user score information using an article neural network and a user neural network respectively to obtain a target article latent vector of each of the at least one article and a target user latent vector of each of the at least one user, and calculating a recommendation result for each user according to the article latent vector and the user latent vector.Type: ApplicationFiled: May 30, 2018Publication date: September 27, 2018Inventors: Jiefeng Cheng, Zhenguo Li, Xiuqiang He, Dahua Lin
-
Patent number: 9183436Abstract: Text in web pages or other text documents may be classified based on the images or other objects within the webpage. A system for identifying and classifying text related to an object may identify one or more web pages containing the image or similar images, determine topics from the text of the document, and develop a set of training phrases for a classifier. The classifier may be trained and then used to analyze the text in the documents. The training set may include both positive examples and negative examples of text taken from the set of documents. A positive example may include captions or other elements directly associated with the object, while negative examples may include text taken from the documents, but from a large distance from the object. In some cases, the system may iterate on the classification process to refine the results.Type: GrantFiled: August 5, 2013Date of Patent: November 10, 2015Assignee: Microsoft Technology Licensing, LLCInventors: Simon Baker, Dahua Lin, Anitha Kannan, Qifa Ke
-
Patent number: 8838432Abstract: An image in a web page may be annotated after deriving information about an image when the image may be displayed on multiple web pages. The web pages that show the image may be analyzed in light of each other to determine metadata about the image, then various additional content may be added to the image. The additional content may be hyperlinks to other webpages. The additional content may be displayed as annotations on top of the images and in other manners. Many embodiments may perform searching, analysis, and classification of images prior to the web page being served.Type: GrantFiled: February 6, 2012Date of Patent: September 16, 2014Assignee: Microsoft CorporationInventors: Simon John Baker, Juliet Anne Bernstein, Krishnan Ramnath, Anitha Kannan, Dahua Lin, Qifa Ke, Matthew Uyttendaele
-
Publication number: 20140129489Abstract: A method described herein includes receiving a digital image, wherein the digital image includes a first element that corresponds to a first domain and a second element that corresponds to a second domain. The method also includes automatically assigning a label to the first element in the digital image based at least in part upon a computed probability that the label corresponds to the first element, wherein the probability is computed through utilization of a first model that is configured to infer labels for elements in the first domain and a second model that is configured to infer labels for elements in the second domain. The first model receives data that identifies learned relationships between elements in the first domain and elements in the second domain, and the probability is computed by the first model based at least in part upon the learned relationships.Type: ApplicationFiled: January 9, 2014Publication date: May 8, 2014Applicant: MICROSOFT CORPORATIONInventors: Simon John Baker, Ashish Kapoor, Gang Hua, Dahua Lin
-
Patent number: 8645287Abstract: A method described herein includes receiving a digital image, wherein the digital image includes a first element that corresponds to a first domain and a second element that corresponds to a second domain. The method also includes automatically assigning a label to the first element in the digital image based at least in part upon a computed probability that the label corresponds to the first element, wherein the probability is computed through utilization of a first model that is configured to infer labels for elements in the first domain and a second model that is configured to infer labels for elements in the second domain. The first model receives data that identifies learned relationships between elements in the first domain and elements in the second domain, and the probability is computed by the first model based at least in part upon the learned relationships.Type: GrantFiled: February 4, 2010Date of Patent: February 4, 2014Assignee: Microsoft CorporationInventors: Simon John Baker, Ashish Kapoor, Gang Hua, Dahua Lin
-
Publication number: 20130315480Abstract: Text in web pages or other text documents may be classified based on the images or other objects within the webpage. A system for identifying and classifying text related to an object may identify one or more web pages containing the image or similar images, determine topics from the text of the document, and develop a set of training phrases for a classifier. The classifier may be trained and then used to analyze the text in the documents. The training set may include both positive examples and negative examples of text taken from the set of documents. A positive example may include captions or other elements directly associated with the object, while negative examples may include text taken from the documents, but from a large distance from the object. In some cases, the system may iterate on the classification process to refine the results.Type: ApplicationFiled: August 5, 2013Publication date: November 28, 2013Applicant: Microsoft CorporationInventors: Simon Baker, Dahua Lin, Anitha Kannan, Qifa Ke
-
Publication number: 20130204608Abstract: An image in a web page may be annotated after deriving information about an image when the image may be displayed on multiple web pages. The web pages that show the image may be analyzed in light of each other to determine metadata about the image, then various additional content may be added to the image. The additional content may be hyperlinks to other webpages. The additional content may be displayed as annotations on top of the images and in other manners. Many embodiments may perform searching, analysis, and classification of images prior to the web page being served.Type: ApplicationFiled: February 6, 2012Publication date: August 8, 2013Applicant: Microsoft CorporationInventors: Simon John BAKER, Juliet Anne BERNSTEIN, Krishnan RAMNATH, Anitha KANNAN, Dahua LIN, Qifa KE, Matthew UYTTENDAELE
-
Patent number: 8503769Abstract: Text in web pages or other text documents may be classified based on the images or other objects within the webpage. A system for identifying and classifying text related to an object may identify one or more web pages containing the image or similar images, determine topics from the text of the document, and develop a set of training phrases for a classifier. The classifier may be trained and then used to analyze the text in the documents. The training set may include both positive examples and negative examples of text taken from the set of documents. A positive example may include captions or other elements directly associated with the object, while negative examples may include text taken from the documents, but from a large distance from the object. In some cases, the system may iterate on the classification process to refine the results.Type: GrantFiled: December 28, 2010Date of Patent: August 6, 2013Assignee: Microsoft CorporationInventors: Simon Baker, Dahua Lin, Anitha Kannan, Qifa Ke
-
Publication number: 20120163707Abstract: Text in web pages or other text documents may be classified based on the images or other objects within the webpage. A system for identifying and classifying text related to an object may identify one or more web pages containing the image or similar images, determine topics from the text of the document, and develop a set of training phrases for a classifier. The classifier may be trained and then used to analyze the text in the documents. The training set may include both positive examples and negative examples of text taken from the set of documents. A positive example may include captions or other elements directly associated with the object, while negative examples may include text taken from the documents, but from a large distance from the object. In some cases, the system may iterate on the classification process to refine the results.Type: ApplicationFiled: December 28, 2010Publication date: June 28, 2012Applicant: MICROSOFT CORPORATIONInventors: Simon BAKER, Dahua LIN, Anitha Kannan, Qifa Ke
-
Publication number: 20110191271Abstract: A method described herein includes receiving a digital image, wherein the digital image includes a first element that corresponds to a first domain and a second element that corresponds to a second domain. The method also includes automatically assigning a label to the first element in the digital image based at least in part upon a computed probability that the label corresponds to the first element, wherein the probability is computed through utilization of a first model that is configured to infer labels for elements in the first domain and a second model that is configured to infer labels for elements in the second domain. The first model receives data that identifies learned relationships between elements in the first domain and elements in the second domain, and the probability is computed by the first model based at least in part upon the learned relationships.Type: ApplicationFiled: February 4, 2010Publication date: August 4, 2011Applicant: Microsoft CorporationInventors: Simon John Baker, Ashish Kapoor, Gang Hua, Dahua Lin