Patents by Inventor Bojana Gajic
Bojana Gajic 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: 11861999Abstract: Various embodiments described herein provide for detection of a particular object within a scene depicted by image data by using a coarse-to-fine approach/strategy based on one or more relationships of objects depicted within the scene.Type: GrantFiled: June 11, 2021Date of Patent: January 2, 2024Assignee: Alarm.com IncorporatedInventors: Ariel Amato, Angel Domingo Sappa, Carlo Gatta, Bojana Gajic, Brent Boekestein
-
Publication number: 20220076083Abstract: Various embodiments described herein provide for detection of a particular object within a scene depicted by image data by using a coarse-to-fine approach/strategy based on one or more relationships of objects depicted within the scene.Type: ApplicationFiled: June 11, 2021Publication date: March 10, 2022Inventors: Ariel Amato, Angel Domingo Sappa, Carlo Gatta, Bojana Gajic, Brent Boekestein
-
Patent number: 11138469Abstract: A method for re-identification of a subject in an image by pre-training a convolutional neural network to recognize individuals within a closed set of possible identifications and further pre-training the convolutional neural network using classification loss; training the pre-trained convolutional neural network by sequentially processing a plurality of triplet of images, each triplet containing a query image degraded by adding random noise to a region of the query image, a positive image corresponding to an image of a same subject as in the query image, and a negative image corresponding to an image of a different subject as in the query image by (a) ranking the triplets by the triplet loss computed, (b) selecting a subset of triplets among the plurality of triplets, and (c) retraining the pre-trained convolutional neural network on each of the triplets of the subset of triplets.Type: GrantFiled: November 6, 2019Date of Patent: October 5, 2021Inventors: Jon Almazan, Bojana Gajic, Naila Murray, Diane Larlus-Larrondo
-
Patent number: 11055585Abstract: Various embodiments described herein provide for detection of a particular object within a scene depicted by image data by using a coarse-to-fine approach/strategy based on one or more relationships of objects depicted within the scene.Type: GrantFiled: September 26, 2019Date of Patent: July 6, 2021Assignee: Vintra, Inc.Inventors: Ariel Amato, Angel Domingo Sappa, Carlo Gatta, Bojana Gajic, Brent Boekestein
-
Publication number: 20210097354Abstract: Various embodiments described herein provide for detection of a particular object within a scene depicted by image data by using a coarse-to-fine approach/strategy based on one or more relationships of objects depicted within the scene.Type: ApplicationFiled: September 26, 2019Publication date: April 1, 2021Inventors: Ariel Amato, Angel Domingo Sappa, Carlo Gatta, Bojana Gajic, Brent Boekestein
-
Publication number: 20200226421Abstract: A method for re-identification of a subject in an image from a set of images, by pre-training, by a data processor in a first server, a convolutional neural network with ImageNet to recognize individuals within a closed set of possible identifications and further pre-training the convolutional neural network using classification loss to realize person identification; training, by the data processor in the first server, the pre-trained convolutional neural network by sequentially processing a plurality of triplet of images and allowing a different size input for each image, each triplet containing a query image degraded by adding random noise to a region of the query image, a positive image corresponding to an image of a same subject as in the query image, and a negative image corresponding to an image of a different subject as in the query image by (a) ranking the triplets by the triplet loss computed (b) selecting a subset of triplets among the plurality of triplets, the subset of triplets having the largestType: ApplicationFiled: November 6, 2019Publication date: July 16, 2020Applicant: Naver CorporationInventors: Jon Almazan, Bojana Gajic, Naila Murray, Diane Larlus-Larrondo
-
Patent number: 9536524Abstract: Speech recognition models are dynamically re-configurable based on user information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. The techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition.Type: GrantFiled: May 1, 2014Date of Patent: January 3, 2017Assignee: AT&T Intellectual Property II, L.P.Inventors: Richard C. Rose, Bojana Gajic
-
Patent number: 9058810Abstract: Speech recognition models are dynamically re-configurable based on user information, application information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. Word recognition lattices are generated for each data field of an application and dynamically concatenated into a single word recognition lattice. A language model is applied to the concatenated word recognition lattice to determine the relationships between the word recognition lattices and repeated until the generated word recognition lattices are acceptable or differ from a predetermined value only by a threshold amount. These techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition.Type: GrantFiled: March 26, 2012Date of Patent: June 16, 2015Assignee: AT&T Intellectual Property II, L.P.Inventors: Bojana Gajic, Shrikanth Sambasivan Narayanan, Sarangarajan Parthasarathy, Richard Cameron Rose, Aaron Edward Rosenberg
-
Publication number: 20140244251Abstract: Speech recognition models are dynamically re-configurable based on user information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. The techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition.Type: ApplicationFiled: May 1, 2014Publication date: August 28, 2014Applicant: AT&T Intellectual Property II, L.P.Inventors: Richard C. Rose, Bojana Gajic
-
Patent number: 8719017Abstract: Speech recognition models are dynamically re-configurable based on user information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. The techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition.Type: GrantFiled: May 15, 2008Date of Patent: May 6, 2014Assignee: AT&T Intellectual Property II, L.P.Inventors: Richard C Rose, Bojana Gajic
-
Publication number: 20120185237Abstract: Speech recognition models are dynamically re-configurable based on user information, application information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. Word recognition lattices are generated for each data field of an application and dynamically concatenated into a single word recognition lattice. A language model is applied to the concatenated word recognition lattice to determine the relationships between the word recognition lattices and repeated until the generated word recognition lattices are acceptable or differ from a predetermined value only by a threshold amount. These techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition.Type: ApplicationFiled: March 26, 2012Publication date: July 19, 2012Applicant: AT&T Intellectual Property II, L.P.Inventors: Bojana GAJIC, Shrikanth Sambasivan Narayanan, Sarangarajan Parthasarathy, Richard Cameron Rose, Aaron Edward Rosenberg
-
Patent number: 8145481Abstract: Speech recognition models are dynamically re-configurable based on user information, application information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. Word recognition lattices are generated for each data field of an application and dynamically concatenated into a single word recognition lattice. A language model is applied to the concatenated word recognition lattice to determine the relationships between the word recognition lattices and repeated until the generated word recognition lattices are acceptable or differ from a predetermined value only by a threshold amount. These techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition.Type: GrantFiled: September 9, 2008Date of Patent: March 27, 2012Assignee: AT&T Intellectual Property II, L.P.Inventors: Bojana Gajic, Shrikanth Sambasivan Narayanan, Sarangarajan Parthasarathy, Richard Cameron Rose, Aaron Edward Rosenberg
-
Publication number: 20090006088Abstract: Speech recognition models are dynamically re-configurable based on user information, application information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. Word recognition lattices are generated for each data field of an application and dynamically concatenated into a single word recognition lattice. A language model is applied to the concatenated word recognition lattice to determine the relationships between the word recognition lattices and repeated until the generated word recognition lattices are acceptable or differ from a predetermined value only by a threshold amount. These techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition.Type: ApplicationFiled: September 9, 2008Publication date: January 1, 2009Applicant: AT&T Corp.Inventors: Bojana Gajic, Shrikanth Sambasivan Narayanan, Sarangarajan Parthasarathy, Richard Cameron Rose, Aaron Edward Rosenberg
-
Patent number: 7457750Abstract: Speech recognition models are dynamically re-configurable based on user information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. The techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition.Type: GrantFiled: October 10, 2001Date of Patent: November 25, 2008Assignee: AT&T Corp.Inventors: Richard C. Rose, Bojana Gajic
-
Patent number: 7451081Abstract: Speech recognition models are dynamically re-configurable based on user information, application information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. Word recognition lattices are generated for each data field of an application and dynamically concatenated into a single word recognition lattice. A language model is applied to the concatenated word recognition lattice to determine the relationships between the word recognition lattices and repeated until the generated word recognition lattices are acceptable or differ from a predetermined value only by a threshold amount. These techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition.Type: GrantFiled: March 13, 2007Date of Patent: November 11, 2008Assignee: AT&T Corp.Inventors: Bojana Gajic, Shrikanth Sambasivan Narayanan, Sarangarajan Parthasarathy, Richard Cameron Rose, Aaron Edward Rosenberg
-
Publication number: 20080221887Abstract: Speech recognition models are dynamically re-configurable based on user information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. The techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition.Type: ApplicationFiled: May 15, 2008Publication date: September 11, 2008Applicant: AT&T Corp.Inventors: Richard C. Rose, Bojana Gajic
-
Patent number: 7209880Abstract: Speech recognition models are dynamically re-configurable based on user information, application information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. Word recognition lattices are generated for each data field of an application and dynamically concatenated into a single word recognition lattice. A language model is applied to the concatenated word recognition lattice to determine the relationships between the word recognition lattices and repeated until the generated word recognition lattices are acceptable or differ from a predetermined value only by a threshold amount. These techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition.Type: GrantFiled: March 6, 2002Date of Patent: April 24, 2007Assignee: AT&T Corp.Inventors: Bojana Gajic, Shrikanth Sambasivan Narayanan, Sarangarajan Parthasarathy, Richard Cameron Rose, Aaron Edward Rosenberg
-
Publication number: 20020046022Abstract: Speech recognition models are dynamically re-configurable based on user information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. The techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition.Type: ApplicationFiled: October 10, 2001Publication date: April 18, 2002Applicant: AT&T CORP.Inventors: Richard C. Rose, Bojana Gajic