Patents by Inventor Simon John Baker
Simon John Baker 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: 11544588Abstract: 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: April 3, 2019Date of Patent: January 3, 2023Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Simon John Baker, Ashish Kapoor, Gang Hua, Dahua Lin
-
Publication number: 20220138404Abstract: Images stored in an information repository are prepared for browsing. For each image in the repository, text in the repository is mined to extract snippets of text about the image which are semantically relevant to the image, and for each of these snippets of text, keyterms are detected in the snippet of text which represent either concepts that are related to the image or entities that are related to the image, and the snippet of text and keyterms are associated with the image. Each keyterm that is associated with each image in the repository is hyperlinked to each other image in the repository that has this keyterm associated therewith. A graphical user interface allows a user to browse the images in the repository by using their associated snippets of text and hyperlinked keyterms.Type: ApplicationFiled: January 12, 2022Publication date: May 5, 2022Applicant: Microsoft Technology Licensing, LLCInventors: Simon John BAKER, Anitha KANNAN, Krishnan RAMNATH
-
Patent number: 11250203Abstract: Images stored in an information repository are prepared for browsing. For each image in the repository, text in the repository is mined to extract snippets of text about the image which are semantically relevant to the image, and for each of these snippets of text, keyterms are detected in the snippet of text which represent either concepts that are related to the image or entities that are related to the image, and the snippet of text and keyterms are associated with the image. Each keyterm that is associated with each image in the repository is hyperlinked to each other image in the repository that has this keyterm associated therewith. A graphical user interface allows a user to browse the images in the repository by using their associated snippets of text and hyperlinked keyterms.Type: GrantFiled: August 12, 2013Date of Patent: February 15, 2022Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Simon John Baker, Anitha Kannan, Krishnan Ramnath
-
Publication number: 20210229601Abstract: Systems and methods for a self-adjusting vehicle mirror. The mirror automatically locates the face of the driver or another passenger, and orients the mirror to provide the driver/passenger face with a desired view from the mirror. The mirror may continue to reorient itself as the driver or passenger shifts position, to continuously provide a desired field of view even as he or she changes position over time. In certain embodiments, the mirror system of the disclosure can be a self-contained system, with the mirror, mirror actuator, camera, and computing device all contained within the mirror housing as a single integrated unit.Type: ApplicationFiled: January 27, 2020Publication date: July 29, 2021Inventors: Feng Hu, Niranjan Avadhanam, Ratin Kumar, Simon John Baker
-
Publication number: 20190362247Abstract: 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: April 3, 2019Publication date: November 28, 2019Inventors: Simon John Baker, Ashish Kapoor, Gang Hua, 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
-
Patent number: 10248865Abstract: The presentation style of a video is identified. A set of features that represents the video is computed. A pre-learned video presentation style classifier is then used to weight each of the features in the set of features and determine a presentation style that is predominately employed in the video based on the weighting of the features.Type: GrantFiled: April 12, 2017Date of Patent: April 2, 2019Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Anitha Kannan, Simon John Baker
-
Publication number: 20170220867Abstract: The presentation style of a video is identified. A set of features that represents the video is computed. A pre-learned video presentation style classifier is then used to weight each of the features in the set of features and determine a presentation style that is predominately employed in the video based on the weighting of the features.Type: ApplicationFiled: April 12, 2017Publication date: August 3, 2017Inventors: Anitha Kannan, Simon John Baker
-
Patent number: 9652675Abstract: The presentation style of a video is identified. A set of features that represents the video is computed. A pre-learned video presentation style classifier is then used to weight each of the features in the set of features and determine a presentation style that is predominately employed in the video based on the weighting of the features.Type: GrantFiled: July 23, 2014Date of Patent: May 16, 2017Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Anitha Kannan, Simon John Baker
-
Publication number: 20160026872Abstract: The presentation style of a video is identified. A set of features that represents the video is computed. A pre-learned video presentation style classifier is then used to weight each of the features in the set of features and determine a presentation style that is predominately employed in the video based on the weighting of the features.Type: ApplicationFiled: July 23, 2014Publication date: January 28, 2016Inventors: Anitha Kannan, Simon John Baker
-
Patent number: 9111349Abstract: The claimed subject matter provides for systems and/or methods for identification of instances of an object of interest in 2D images by creating a database of 3D curve models of each desired instance and comparing an image of an object of interest against such 3D curve models of instances. The present application describes identifying and verifying the make and model of a car from a possibly single image—after the models have been populated with training data of test images of many makes and models of cars. In one embodiment, an identification system may be constructed by generating a 3D curve model by back-projecting edge points onto a visual hull reconstruction from silhouettes of an instance. The system and methods employ chamfer distance and orientation distance provides reasonable verification performance, as well as an appearance model for the taillights of the car to increase the robustness of the system.Type: GrantFiled: December 16, 2011Date of Patent: August 18, 2015Assignee: Microsoft Technology Licensing, LLCInventors: Richard Stephan Szeliski, Edward Hsiao, Sudipta Narayan Sinha, Krishnan Ramnath, Charles Lawrence Zitnick, III, Simon John Baker
-
Publication number: 20150046781Abstract: Images stored in an information repository are prepared for browsing. For each image in the repository, text in the repository is mined to extract snippets of text about the image which are semantically relevant to the image, and for each of these snippets of text, keyterms are detected in the snippet of text which represent either concepts that are related to the image or entities that are related to the image, and the snippet of text and keyterms are associated with the image. Each keyterm that is associated with each image in the repository is hyperlinked to each other image in the repository that has this keyterm associated therewith. A graphical user interface allows a user to browse the images in the repository by using their associated snippets of text and hyperlinked keyterms.Type: ApplicationFiled: August 12, 2013Publication date: February 12, 2015Applicant: Microsoft CorporationInventors: Simon John Baker, Anitha Kannan, Krishnan Ramnath
-
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: 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
-
Publication number: 20130156329Abstract: The claimed subject matter provides for systems and/or methods for identification of instances of an object of interest in 2D images by creating a database of 3D curve models of each desired instance and comparing an image of an object of interest against such 3D curve models of instances. The present application describes identifying and verifying the make and model of a car from a possibly single image—after the models have been populated with training data of test images of many makes and models of cars. In one embodiment, an identification system may be constructed by generating a 3D curve model by back-projecting edge points onto a visual hull reconstruction from silhouettes of an instance. The system and methods employ chamfer distance and orientation distance provides reasonable verification performance, as well as an appearance model for the taillights of the car to increase the robustness of the system.Type: ApplicationFiled: December 16, 2011Publication date: June 20, 2013Applicant: MICROSOFT CORPORATIONInventors: Richard Stephan Szeliski, Edward Hsiao, Sudipta Narayan Sinha, Krishnan Ramnath, Charles Lawrence Zitnick, III, Simon John Baker
-
Patent number: 8274603Abstract: Deinterlacing of video involves converting interlaced video to progressive video by interpolating a missing pixel in the interlaced video from other pixels in the video. A plurality of interpolants are provided, each of which interpolates a pixel value from other pixels that are nearby in space and/or time. The data costs of using the various interpolants is calculated. A particular one of the interpolants is chosen based on the data costs associated with the various interpolants. The chosen interpolant is used to interpolate the value of the missing pixel. The interpolated pixel value may be refined based on exemplars. The exemplars may be taken from the video that is being deinterlaced.Type: GrantFiled: March 28, 2008Date of Patent: September 25, 2012Assignee: Microsoft CorporationInventors: Shengyang Dai, Simon John Baker, Sing Bing Kang
-
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
-
Publication number: 20090244367Abstract: Deinterlacing of video involves converting interlaced video to progressive video by interpolating a missing pixel in the interlaced video from other pixels in the video. A plurality of interpolants are provided, each of which interpolates a pixel value from other pixels that are nearby in space and/or time. The data costs of using the various interpolants is calculated. A particular one of the interpolants is chosen based on the data costs associated with the various interpolants. The chosen interpolant is used to interpolate the value of the missing pixel. The interpolated pixel value may be refined based on exemplars. The exemplars may be taken from the video that is being deinterlaced.Type: ApplicationFiled: March 28, 2008Publication date: October 1, 2009Applicant: Microsoft CorporationInventors: Shengyang Dai, Simon John Baker, Sing Bing Kang