Patents by Inventor Seungyup Paek
Seungyup Paek 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: 9507779Abstract: The invention provides a system and method for integrating multimedia descriptions in a way that allows humans, software components or devices to easily identify, represent, manage, retrieve, and categorize the multimedia content. In this manner, a user who may be interested in locating a specific piece of multimedia content from a database, Internet, or broadcast media, for example, may search for and find the multimedia content. In this regard, the invention provides a system and method that receives multimedia content and separates the multimedia content into separate components which are assigned to multimedia categories, such as image, video, audio, synthetic and text. Within each of the multimedia categories, the multimedia content is classified and descriptions of the multimedia content are generated. The descriptions are then formatted, integrated, using a multimedia integration description scheme, and the multimedia integration description is generated for the multimedia content.Type: GrantFiled: December 14, 2015Date of Patent: November 29, 2016Assignees: AT&T Intellectual Property II, L.P., The Trustees of Columbia University in the city of New YorkInventors: Ana Belen Benitez, Shih-Fu Chang, Qian Huang, Seungyup Paek, Atul Puri
-
Publication number: 20160098401Abstract: The invention provides a system and method for integrating multimedia descriptions in a way that allows humans, software components or devices to easily identify, represent, manage, retrieve, and categorize the multimedia content. In this manner, a user who may be interested in locating a specific piece of multimedia content from a database, Internet, or broadcast media, for example, may search for and find the multimedia content. In this regard, the invention provides a system and method that receives multimedia content and separates the multimedia content into separate components which are assigned to multimedia categories, such as image, video, audio, synthetic and text. Within each of the multimedia categories, the multimedia content is classified and descriptions of the multimedia content are generated. The descriptions are then formatted, integrated, using a multimedia integration description scheme, and the multimedia integration description is generated for the multimedia content.Type: ApplicationFiled: December 14, 2015Publication date: April 7, 2016Applicant: The Trustees of Columbia University in the City of New YorkInventors: Ana Belen BENITEZ, Shih-Fu CHANG, Qian HUANG, Seungyup PAEK, Atul PURI
-
Patent number: 9239877Abstract: The invention provides a system and method for integrating multimedia descriptions in a way that allows humans, software components or devices to easily identify, represent, manage, retrieve, and categorize the multimedia content. In this manner, a user who may be interested in locating a specific piece of multimedia content from a database, Internet, or broadcast media, for example, may search for and find the multimedia content. In this regard, the invention provides a system and method that receives multimedia content and separates the multimedia content into separate components which are assigned to multimedia categories, such as image, video, audio, synthetic and text. Within each of the multimedia categories, the multimedia content is classified and descriptions of the multimedia content are generated. The descriptions are then formatted, integrated, using a multimedia integration description scheme, and the multimedia integration description is generated for the multimedia content.Type: GrantFiled: June 27, 2011Date of Patent: January 19, 2016Assignees: AT&T Intellectual Property II, L.P., The Trustees of Columbia University in the City of New YorkInventors: Ana Belen Benitez, Shih-Fu Chang, Qian Huang, Seungyup Paek, Atul Puri
-
Patent number: 8370869Abstract: Systems and methods for describing video content establish video description records which include an object set (24), an object hierarchy (26) and entity relation graphs (28). Video objects can include global objects, segment objects and local objects. The video objects are further defined by a number of features organized in classes, which in turn are further defined by a number of feature descriptors (36, 38, and 40). The relationships (44) between and among the objects in the object set (24) are defined by the object hierarchy (26) and entity relation graphs (28). The video description records provide a standard vehicle for describing the content and context of video information for subsequent access and processing by computer applications such as search engines, filters and archive systems.Type: GrantFiled: June 6, 2006Date of Patent: February 5, 2013Assignee: The Trustees of Columbia University in the City of New YorkInventors: Seungyup Paek, Ana Benitez, Shih-Fu Chang, Atul Puri, Qian Huang, Chung-Sheng Li, John R. Smith, Lawrence Bergman
-
Publication number: 20110258189Abstract: The invention provides a system and method for integrating multimedia descriptions in a way that allows humans, software components or devices to easily identify, represent, manage, retrieve, and categorize the multimedia content. In this manner, a user who may be interested in locating a specific piece of multimedia content from a database, Internet, or broadcast media, for example, may search for and find the multimedia content. In this regard, the invention provides a system and method that receives multimedia content and separates the multimedia content into separate components which are assigned to multimedia categories, such as image, video, audio, synthetic and text. Within each of the multimedia categories, the multimedia content is classified and descriptions of the multimedia content are generated. The descriptions are then formatted, integrated, using a multimedia integration description scheme, and the multimedia integration description is generated for the multimedia content.Type: ApplicationFiled: June 27, 2011Publication date: October 20, 2011Applicants: Columbia University in the City of New York, AT&T Intellectual Property II, L.P.Inventors: Ana Belen Benitez, Shih-Fu Chang, Qian Huang, Seungyup Paek, Atul Puri
-
Patent number: 7970822Abstract: The invention provides a system and method for integrating multimedia descriptions in a way that allows humans, software components or devices to easily identify, represent, manage, retrieve, and categorize the multimedia content. In this manner, a user who may be interested in locating a specific piece of multimedia content from a database, Internet, or broadcast media, for example, may search for and find the multimedia content. In this regard, the invention provides a system and method that receives multimedia content and separates the multimedia content into separate components which are assigned to multimedia categories, such as image, video, audio, synthetic and text. Within each of the multimedia categories, the multimedia content is classified and descriptions of the multimedia content are generated. The descriptions are then formatted, integrated, using a multimedia integration description scheme, and the multimedia integration description is generated for the multimedia content.Type: GrantFiled: February 17, 2009Date of Patent: June 28, 2011Assignees: AT&T Intellectual Property II, L.P., Columbia University in the City of New YorkInventors: Ana Belen Benitez, Shih-Fu Chang, Qian Huang, Seungyup Paek, Atul Puri
-
Patent number: 7809760Abstract: The invention provides a system and method for integrating multimedia descriptions in a way that allows humans, software components or devices to easily identify, represent, manage, retrieve, and categorize the multimedia content. In this manner, a user who may be interested in locating a specific piece of multimedia content from a database, Internet, or broadcast media, for example, may search for and find the multimedia content. In this regard, the invention provides a system and method that receives multimedia content and separates the multimedia content into separate components which are assigned to multimedia categories, such as image, video, audio, synthetic and text. Within each of the multimedia categories, the multimedia content is classified and descriptions of the multimedia content are generated. The descriptions are then formatted, integrated, using a multimedia integration description scheme, and the multimedia integration description is generated for the multimedia content.Type: GrantFiled: September 15, 2009Date of Patent: October 5, 2010Assignees: AT&T Intellectual Property II, L.P., Columbia University in the City of New YorkInventors: Ana Benitez, Shih-Fu Chang, Qian Huang, Seungyup Paek, Atul Puri
-
Publication number: 20100005121Abstract: The invention provides a system and method for integrating multimedia descriptions in a way that allows humans, software components or devices to easily identify, represent, manage, retrieve, and categorize the multimedia content. In this manner, a user who may be interested in locating a specific piece of multimedia content from a database, Internet, or broadcast media, for example, may search for and find the multimedia content. In this regard, the invention provides a system and method that receives multimedia content and separates the multimedia content into separate components which are assigned to multimedia categories, such as image, video, audio, synthetic and text. Within each of the multimedia categories, the multimedia content is classified and descriptions of the multimedia content are generated. The descriptions are then formatted, integrated, using a multimedia integration description scheme, and the multimedia integration description is generated for the multimedia content.Type: ApplicationFiled: September 15, 2009Publication date: January 7, 2010Applicants: AT &T Corp., Columbia University in the City of New YorkInventors: Ana Belen Benitez, Shih-Fu Chang, Qian Huang, Seungyup Paek, Atul Puri
-
Patent number: 7599965Abstract: The invention provides a system and method for integrating multimedia descriptions in a way that allows humans, software components or devices to easily identify, represent, manage, retrieve, and categorize the multimedia content. In this manner, a user who may be interested in locating a specific piece of multimedia content from a database, Internet, or broadcast media, for example, may search for and find the multimedia content. In this regard, the invention provides a system and method that receives multimedia content and separates the multimedia content into separate components which are assigned to multimedia categories, such as image, video, audio, synthetic and text. Within each of the multimedia categories, the multimedia content is classified and descriptions of the multimedia content are generated. The descriptions are then formatted, integrated, using a multimedia integration description scheme, and the multimedia integration description is generated for the multimedia content.Type: GrantFiled: December 27, 2006Date of Patent: October 6, 2009Assignees: AT&T Intellectual Property II, L.P., Columbia University in the City of New YorkInventors: Ana Benitez, Shih-Fu Chang, Qian Huang, Seungyup Paek, Atul Puri
-
Publication number: 20090157736Abstract: The invention provides a system and method for integrating multimedia descriptions in a way that allows humans, software components or devices to easily identify, represent, manage, retrieve, and categorize the multimedia content. In this manner, a user who may be interested in locating a specific piece of multimedia content from a database, Internet, or broadcast media, for example, may search for and find the multimedia content. In this regard, the invention provides a system and method that receives multimedia content and separates the multimedia content into separate components which are assigned to multimedia categories, such as image, video, audio, synthetic and text. Within each of the multimedia categories, the multimedia content is classified and descriptions of the multimedia content are generated. The descriptions are then formatted, integrated, using a multimedia integration description scheme, and the multimedia integration description is generated for the multimedia content.Type: ApplicationFiled: February 17, 2009Publication date: June 18, 2009Applicants: AT&T Corp., Columbia University in the City of New YorkInventors: Ana Belen Benitez, Shih-Fu Chang, Qian Huang, Seungyup Paek, Atul Puri
-
Patent number: 7506024Abstract: The invention provides a system and method for integrating multimedia descriptions in a way that allows humans, software components or devices to easily identify, represent, manage, retrieve, and categorize the multimedia content. In this manner, a user who may be interested in locating a specific piece of multimedia content from a database, Internet, or broadcast media, for example, may search for and find the multimedia content. In this regard, the invention provides a system and method that receives multimedia content and separates the multimedia content into separate components which are assigned to multimedia categories, such as image, video, audio, synthetic and text. Within each of the multimedia categories, the multimedia content is classified and descriptions of the multimedia content are generated. The descriptions are then formatted, integrated, using a multimedia integration description scheme, and the multimedia integration description is generated for the multimedia content.Type: GrantFiled: April 4, 2006Date of Patent: March 17, 2009Assignees: AT&T Intellectual Property II, L.P., Columbia University in the city of New YorkInventors: Ana Benitez, Shih-Fu Chang, Qian Huang, Seungyup Paek, Atul Puri
-
Publication number: 20070245400Abstract: Systems and methods for describing video content establish video description records which include an object set (24), an object hierarchy (26) and entity relation graphs (28). Video objects can include global objects, segment objects and local objects. The video objects are further defined by a number of features organized in classes, which in turn are further defined by a number of feature descriptors (36, 38, and 40). The relationships (44) between and among the objects in the object set (24) are defined by the object hierarchy (26) and entity relation graphs (28). The video description records provide a standard vehicle for describing the content and context of video information for subsequent access and processing by computer applications such as search engines, filters and archive systems.Type: ApplicationFiled: June 6, 2006Publication date: October 18, 2007Inventors: Seungyup Paek, Ana Benitez, Shih-Fu Chang, Atul Puri, Qian Huang, Chung-Sheng Li, John Smith, Lawrence Bergman
-
Patent number: 7185049Abstract: The invention provides a system and method for integrating multimedia descriptions in a way that allows humans, software components or devices to easily identify, represent, manage, retrieve, and categorize the multimedia content. In this manner, a user who may be interested in locating a specific piece of multimedia content from a database, Internet, or broadcast media, for example, may search for and find the multimedia content. In this regard, the invention provides a system and method that receives multimedia content and separates the multimedia content into separate components which are assigned to multimedia categories, such as image, video, audio, synthetic and text. Within each of the multimedia categories, the multimedia content is classified and descriptions of the multimedia content are generated. The descriptions are then formatted, integrated, using a multimedia integration description scheme, and the multimedia integration description is generated for the multimedia content.Type: GrantFiled: February 1, 2000Date of Patent: February 27, 2007Assignee: AT&T Corp.Inventors: Ana Belen Benitez, Shih-Fu Chang, Qian Huang, Seungyup Paek, Atul Puri
-
Patent number: 7143434Abstract: The present invention relates to a system for generating a description record from multimedia information including, e.g., video data. A multimedia information input interface is used to receive multimedia information. A computer processor receives the multimedia information, processes the video information by performing video object extraction processing to generate video object descriptions from the video information, processes the generated video object descriptions by object hierarchy construction and extraction processing to generate video object hierarchy descriptions, and processes the generated video object descriptions by entity relation graph descriptions.Type: GrantFiled: November 5, 1999Date of Patent: November 28, 2006Inventors: Seungyup Paek, Ana Benitez, Shih-Fu Chang, Atul Puri, Chung-Sheng Li, John R. Smith, Lawrence Bergman
-
Publication number: 20060167876Abstract: The invention provides a system and method for integrating multimedia descriptions in a way that allows humans, software components or devices to easily identify, represent, manage, retrieve, and categorize the multimedia content. In this manner, a user who may be interested in locating a specific piece of multimedia content from a database, Internet, or broadcast media, for example, may search for and find the multimedia content. In this regard, the invention provides a system and method that receives multimedia content and separates the multimedia content into separate components which are assigned to multimedia categories, such as image, video, audio, synthetic and text. Within each of the multimedia categories, the multimedia content is classified and descriptions of the multimedia content are generated. The descriptions are then formatted, integrated, using a multimedia integration description scheme, and the multimedia integration description is generated for the multimedia content.Type: ApplicationFiled: April 4, 2006Publication date: July 27, 2006Applicant: AT&T Corp.Inventors: Ana Benitez, Shih-Fu Chang, Qian Huang, Seungyup Paek, Atul Puri