Patents by Inventor Pavel Volkov
Pavel Volkov 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: 11915355Abstract: Provided are systems and methods for realistic head turns and face animation synthesis. An example method includes receiving a source frame of a source video, where the source frame includes a head and a face of a source actor, generating source pose parameters corresponding to a pose of the head and a facial expression of the source actor; receiving a target image including a target head and a target face of a target person, determining target identity information associated with the target head and the target face of the target person, replacing source identity information in the source pose parameters with the target identity information to obtain further source pose parameters, and generating an output frame of an output video that includes a modified image of the target face and the target head adopting the pose of the head and the facial expression of the source actor.Type: GrantFiled: August 5, 2022Date of Patent: February 27, 2024Assignee: Snap Inc.Inventors: Yurii Volkov, Pavel Savchenkov, Nikolai Smirnov, Aleksandr Mashrabov
-
Patent number: 9251294Abstract: Approximate string matching of a target string to a trie data structure in which the trie data structure has a root node and generations of child nodes, each node representing at least one character in an alphabet to provide a lexicon of words and word fragments. Traversing the trie data structure includes starting from the root node by comparing each node of a branch of the trie data structure to characters in the target string and adding characters traversed in a branch of the trie data structure to a gathered string to provide suggestions of approximate matches. If a node is reached that is flagged as a node for a word or a word fragment and, and if the target string is longer than the gathered string, the method loops back to the root node, and continues the traverse from the root node.Type: GrantFiled: July 4, 2010Date of Patent: February 2, 2016Assignee: International Business Machines CorporationInventors: Alexei Nevidomski, Pavel Volkov
-
Patent number: 8543913Abstract: The disclosure is directed to a method and system for accessing textual widgets. A method in accordance with an embodiment includes: entering a string expression into a document; invoking a spell-checker to check a spelling of the string expression; marking the string expression as misspelled; identifying a textual widget based on the misspelling of the string expression; evaluating the misspelled string expression using the identified textual widget, the identified textual widget returning at least one result of the evaluation; displaying the at least one result of the evaluation; selecting a result of the evaluation; and replacing the string expression in the document with the selected result of the evaluation.Type: GrantFiled: October 16, 2008Date of Patent: September 24, 2013Assignee: International Business Machines CorporationInventors: Daniel J. McCloskey, Alena Kucharenka, Pavel Volkov, Carol S. Zimmet
-
Patent number: 8234108Abstract: A method for building and contracting a linguistic dictionary, the linguistic dictionary comprising a list of surface forms and a list of normalized forms, each normalized form being associated with a surface form, the method comprising the steps of: comparing each character of a surface form with each character of the surface form's normalized form; in response to the comparing step, determining an edit operation for each character compared; and generating a transform code from the set of the edit operations in order to transform the surface form to its normalized form.Type: GrantFiled: December 11, 2011Date of Patent: July 31, 2012Assignee: International Business Machines CorporationInventors: Hisham Emad Elshishiny, Edel Greevy, Pai-Fang Franny Hsiao, Alexey Nevidomskiy, Alexander Troussov, Pavel Volkov
-
Patent number: 8219905Abstract: A method, system and computer program product for keyboard layout detection resulting in improving the quality of the spelling suggestions, and in another aspect, recognizing a keyboard mapping mismatch between a computer and a given remote user based on a defined finite dictionary. There is no extra Application Programming Interfaces (API) required to pass information between the text editor and a spellchecking engine in order to perform keyboard layout detection.Type: GrantFiled: November 17, 2008Date of Patent: July 10, 2012Assignee: International Business Machines CorporationInventors: Amine Akrout, Hisham El-Shishiny, Pavel Volkov
-
Publication number: 20120084077Abstract: A method for building and contracting a linguistic dictionary, the linguistic dictionary comprising a list of surface forms and a list of normalized forms, each normalized form being associated with a surface form, the method comprising the steps of: comparing each character of a surface form with each character of the surface form's normalized form; in response to the comparing step, determining an edit operation for each character compared; and generating a transform code from the set of the edit operations in order to transform the surface form to its normalized form.Type: ApplicationFiled: December 11, 2011Publication date: April 5, 2012Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: HISHAM EMAD ELSHISHINY, EDEL GREEVY, PAI-FANG FRANNY HSIAO, ALEXEY NEVIDOMSKIY, ALEXANDER TROUSSOV, PAVEL VOLKOV
-
Patent number: 8090571Abstract: A method for building and contracting a linguistic dictionary, the linguistic dictionary comprising a list of surface forms and a list of normalized forms, each normalized form being associated with a surface form, the method comprising the steps of: comparing each character of a surface form with each character of the surface form's normalized form; in response to the comparing step, determining an edit operation for each character compared; and generating a transform code from the set of the edit operations in order to transform the surface form to its normalized form.Type: GrantFiled: December 27, 2005Date of Patent: January 3, 2012Assignee: International Business Machines CorporationInventors: Hisham Emad Elshishiny, Edel Greevy, Pai-Fang Franny Hsiao, Alexey Nevidomskiy, Alexander Troussov, Pavel Volkov
-
Patent number: 8055498Abstract: The present invention automatically builds a contracted dictionary from a given list of multi-word proper names and performs fuzzy searches in the contracted dictionary. The contracted dictionary of proper names includes two linked trie-based dictionaries: a first dictionary is used to store single word names, each word name having an ID number; and a second dictionary is used to store multi-word names encoded with ID numbers. Information related to the multi-word names is also stored as a gloss to the terminal node of the multi-word entry of the trie-based dictionary. An approximate lookup for a multi-word name is conducted first for each word of the multi-word name using an approximate matching technique such as a phonetic proximity or a simple edit distance. Accordingly, N suggestions is determined for each word of the multi-word name under consideration. Then, multi-word candidates are assembled in ID notation.Type: GrantFiled: September 24, 2007Date of Patent: November 8, 2011Assignee: International Business Machines CorporationInventors: Hisham El-Shishiny, Pavel Volkov
-
Publication number: 20100268724Abstract: Approximate string matching of a target string to a trie data structure in which the trie data structure has a root node and generations of child nodes, each node representing at least one character in an alphabet to provide a lexicon of words and word fragments. Traversing the trie data structure includes starting from the root node by comparing each node of a branch of the trie data structure to characters in the target string and adding characters traversed in a branch of the trie data structure to a gathered string to provide suggestions of approximate matches. If a node is reached that is flagged as a node for a word or a word fragment and, and if the target string is longer than the gathered string, the method loops back to the root node, and continues the traverse from the root node.Type: ApplicationFiled: July 4, 2010Publication date: October 21, 2010Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Alexei Nevidomski, Pavel Volkov
-
Patent number: 7818165Abstract: A method and system for language identification are provided. The system includes a feature set of a plurality of character strings of varying length with associated information. The associated information includes one or more significance scores for a character string for one or more of a plurality of languages. Means are provided for detecting character strings from the feature set within a token from an input text. The system uses a finite-state device and the associated information is provided as glosses at the final nodes of the finite-state device for each character string. The associated information can also include significance scores based on linguistic rules.Type: GrantFiled: July 26, 2005Date of Patent: October 19, 2010Assignee: International Business Machines CorporationInventors: Richard Carlgren, Daniel McCloskey, Alexei Nevidomski, Brian O'Donovan, Mayo Takeuchi, Alexandre Troussov, Pavel Volkov
-
Patent number: 7809744Abstract: Approximate string matching of a target string to a trie data structure. The trie data structure has a root node and generations of child nodes each node representing at least one character in an alphabet to provide a lexicon of words and word fragments. The trie data structure is traversed starting from the root node by comparing each node of a branch of the trie data structure to characters in the target string and adding characters traversed in a branch of the trie data structure to a gathered string to provide suggestions of approximate matches. If a node is reached that is flagged as a node for a word or a word fragment and, if the target string is longer than the gathered string, the traversal loops back to the root node, and continues to traverse from the root node. This enables the trie data structure to use word fragments for compound words and to split non-delimited words where appropriate.Type: GrantFiled: June 16, 2005Date of Patent: October 5, 2010Assignee: International Business Machines CorporationInventors: Alexei Nevidomski, Pavel Volkov
-
Publication number: 20100125725Abstract: A method, system and computer program product for keyboard layout detection resulting in improving the quality of the spelling suggestions, and in another aspect, recognizing a keyboard mapping mismatch between a computer and a given remote user based on a defined finite dictionary. There is no extra Application Programming Interfaces (API) required to pass information between the text editor and a spellchecking engine in order to perform keyboard layout detection.Type: ApplicationFiled: November 17, 2008Publication date: May 20, 2010Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Amine Akrout, Hisham El-Shishiny, Pavel Volkov
-
Publication number: 20100100816Abstract: The disclosure is directed to a method and system for accessing textual widgets. A method in accordance with an embodiment includes: entering a string expression into a document; invoking a spell-checker to check a spelling of the string expression; marking the string expression as misspelled; identifying a textual widget based on the misspelling of the string expression; evaluating the misspelled string expression using the identified textual widget, the identified textual widget returning at least one result of the evaluation; displaying the at least one result of the evaluation; selecting a result of the evaluation; and replacing the string expression in the document with the selected result of the evaluation.Type: ApplicationFiled: October 16, 2008Publication date: April 22, 2010Inventors: Daniel J. McCloskey, Alena Kucharenka, Pavel Volkov, Carol S. Zimmet
-
Publication number: 20080091413Abstract: The present invention automatically builds a contracted dictionary from a given list of multi-word proper names and performs fuzzy searches in the contracted dictionary. The contracted dictionary of proper names includes two linked trie-based dictionaries: a first dictionary is used to store single word names, each word name having an ID number; and a second dictionary is used to store multi-word names encoded with ID numbers. Information related to the multi-word names is also stored as a gloss to the terminal node of the multi-word entry of the trie-based dictionary. An approximate lookup for a multi-word name is conducted first for each word of the multi-word name using an approximate matching technique such as a phonetic proximity or a simple edit distance. Accordingly, N suggestions is determined for each word of the multi-word name under consideration. Then, multi-word candidates are assembled in ID notation.Type: ApplicationFiled: September 24, 2007Publication date: April 17, 2008Inventors: Hisham El-Shishiny, Pavel Volkov
-
Publication number: 20060293880Abstract: A method for building and contracting a linguistic dictionary, the linguistic dictionary comprising a list of surface forms and a list of normalized forms, each normalized form being associated with a surface form, the method comprising the steps of: comparing each character of a surface form with each character of the surface form's normalized form; in response to the comparing step, determining an edit operation for each character compared; and generating a transform code from the set of the edit operations in order to transform the surface form to its normalized form.Type: ApplicationFiled: December 27, 2005Publication date: December 28, 2006Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Hisham Elshishiny, Edel Greevy, Pai-Fang Hsiao, Alexey Nevidomskiy, Alexander Troussov, Pavel Volkov
-
Publication number: 20060229865Abstract: A method and system for language identification are provided. The system includes a feature set of a plurality of character strings of varying length with associated information. The associated information includes one or more significance scores for a character string for one or more of a plurality of languages. Means are provided for detecting character strings from the feature set within a token from an input text. The system uses a finite-state device and the associated information is provided as glosses at the final nodes of the finite-state device for each character string. The associated information can also include significance scores based on linguistic rules.Type: ApplicationFiled: July 26, 2005Publication date: October 12, 2006Inventors: Richard Carlgren, Daniel McCloskey, Alexei Nevidomski, Brian O'Donovan, Mayo Takeuchi, Alexandre Troussov, Pavel Volkov
-
Publication number: 20060004744Abstract: A method and system are provided for approximate string matching of a target string to a trie data structure. The trie data structure has a root node and generations of child nodes each node representing at least one character in an alphabet to provide a lexicon of words and word fragments. The method involves traversing the trie data structure starting from the root node by comparing each node of a branch of the trie data structure to characters in the target string and adding characters traversed in a branch of the trie data structure to a gathered string to provide suggestions of approximate matches. If the method reaches a node flagged as a node for a word or a word fragment and, if the target string is longer than the gathered string, the method loops back to the root node, and continues the traverse from the root node. This enables the trie data structure to use word fragments for compound words and to split non-delimited words where appropriate.Type: ApplicationFiled: June 16, 2005Publication date: January 5, 2006Inventors: Alexei Nevidomski (Alex Nevidomski), Pavel Volkov