Patents by Inventor Jonathan TOMPSON
Jonathan TOMPSON 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: 20260350399Abstract: An encoder neural network is described which can encode a data item, such as a frame of a video, to form a respective encoded data item. Data items of a first data sequence are associated with respective data items of a second sequence, by determining which of the encoded data items of the second sequence is closest to the encoded data item produced from each data item of the first sequence. Thus, the two data sequences are aligned. The encoder neural network is trained automatically using a training set of data sequences, by an iterative process of successively increasing cycle consistency between pairs of the data sequences.Type: ApplicationFiled: July 13, 2026Publication date: November 5, 2026Inventors: Yusuf Aytar, Debidatta Dwibedi, Andrew Zisserman, Jonathan Tompson, Pierre Sermanet
-
Publication number: 20260350959Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, comprising: obtaining an input image; processing the input image using an image encoder neural network that has been trained to process the input image to generate an image sequence of image embedding vectors characterizing the input image; obtaining data specifying a location of a first bounding box within the input image that depicts a first object; generating a bounding box embedding vector that represents the location of the first bounding box; generating an input sequence of input embedding vectors that includes the image sequence of image embedding vectors and the bounding box embedding vector; and processing the input sequence of input embedding vectors using a language model neural network to generate as output an output sequence of text tokens that represents a text caption that describes the first object depicted within the first bounding box.Type: ApplicationFiled: May 23, 2024Publication date: November 5, 2026Inventors: Debidatta Dwibedi, Jonathan Tompson, Andrew Zisserman, Yusuf Aytar
-
Patent number: 12711388Abstract: An encoder neural network is described which can encode a data item, such as a frame of a video, to form a respective encoded data item. Data items of a first data sequence are associated with respective data items of a second sequence, by determining which of the encoded data items of the second sequence is closest to the encoded data item produced from each data item of the first sequence. Thus, the two data sequences are aligned. The encoder neural network is trained automatically using a training set of data sequences, by an iterative process of successively increasing cycle consistency between pairs of the data sequences.Type: GrantFiled: November 21, 2019Date of Patent: August 18, 2026Assignee: GDM Holding LLCInventors: Yusuf Aytar, Debidatta Dwibedi, Andrew Zisserman, Jonathan Tompson, Pierre Sermanet
-
Patent number: 12469290Abstract: Techniques are disclosed that enable processing a video capturing a periodic activity using a repetition network to generate periodic output (e.g., a period length of the periodic activity captured in the video and/or a frame wise periodicity indication of the video capturing the periodic activity). Various implementations include a class agnostic repetition network which can be used to generate periodic output for a wide variety of periodic activities. Additional or alternative implementations include generating synthetic repetition videos which can be utilized to train the repetition network.Type: GrantFiled: June 10, 2020Date of Patent: November 11, 2025Assignee: GOOGLE LLCInventors: Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Andrew Zisserman, Pierre Sermanet
-
Publication number: 20250312914Abstract: Implementations are provided for learning dexterous tasks. In various implementations, a plurality of images may be retrieved that capture an environment in which a robot operates from multiple different perspectives. Data indicative of the plurality of images and a proprioceptive state of the robot may be processed using a diffusion model that includes a transformer-encoder and a transformer-decoder. The transformer-encoder may be used to generate latent embeddings representing the plurality of images and proprioceptive state of the robot. The transformer-decoder may be used to process the latent embeddings and data indicative of a diffusion timestep to generate robot control data. The robot control data may include a series of actions to be performed by the robot over a time interval. The robot may be operated in accordance with the robot control data.Type: ApplicationFiled: April 8, 2025Publication date: October 9, 2025Inventors: Zihao Zhao, Jonathan Tompson, Danny Michael Driess, Peter Raymond Florence, Chelsea Finn, Ayzaan Wahid
-
Publication number: 20230274548Abstract: Techniques are disclosed that enable processing a video capturing a periodic activity using a repetition network to generate periodic output (e.g., a period length of the periodic activity captured in the video and/or a frame wise periodicity indication of the video capturing the periodic activity). Various implementations include a class agnostic repetition network which can be used to generate periodic output for a wide variety of periodic activities. Additional or alternative implementations include generating synthetic repetition videos which can be utilized to train the repetition network.Type: ApplicationFiled: June 10, 2020Publication date: August 31, 2023Inventors: Debidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Andrew Zisserman, Pierre Sermanet
-
Publication number: 20220004883Abstract: An encoder neural network is described which can encode a data item, such as a frame of a video, to form a respective encoded data item. Data items of a first data sequence are associated with respective data items of a second sequence, by determining which of the encoded data items of the second sequence is closest to the encoded data item produced from each data item of the first sequence. Thus, the two data sequences are aligned. The encoder neural network is trained automatically using a training set of data sequences, by an iterative process of successively increasing cycle consistency between pairs of the data sequences.Type: ApplicationFiled: November 21, 2019Publication date: January 6, 2022Inventors: Yusuf Aytar, Debidatta Dwibedi, Andrew Zisserman, Jonathan Tompson, Pierre Sermanet
-
Patent number: 11181986Abstract: Systems and methods for context-sensitive hand interaction with an immersive environment are provided. An example method includes determining a contextual factor for a user and selecting an interaction mode based on the contextual factor. The example method may also include monitoring a hand of the user to determine a hand property and determining an interaction with an immersive environment based on the interaction mode and the hand property.Type: GrantFiled: August 19, 2020Date of Patent: November 23, 2021Assignee: GOOGLE LLCInventors: Shiqi Chen, Jonathan Tompson, Rahul Garg
-
Publication number: 20200379576Abstract: Systems and methods for context-sensitive hand interaction with an immersive environment are provided. An example method includes determining a contextual factor for a user and selecting an interaction mode based on the contextual factor. The example method may also include monitoring a hand of the user to determine a hand property and determining an interaction with an immersive environment based on the interaction mode and the hand property.Type: ApplicationFiled: August 19, 2020Publication date: December 3, 2020Inventors: Shiqi Chen, Jonathan Tompson, Rahul Garg
-
Patent number: 10782793Abstract: Systems and methods for context-sensitive hand interaction with an immersive environment are provided. An example method includes determining a contextual factor for a user and selecting an interaction mode based on the contextual factor. The example method may also include monitoring a hand of the user to determine a hand property and determining an interaction with an immersive environment based on the interaction mode and the hand property.Type: GrantFiled: August 10, 2018Date of Patent: September 22, 2020Assignee: GOOGLE LLCInventors: Shiqi Chen, Jonathan Tompson, Rahul Garg
-
Patent number: 10635161Abstract: In one aspect, a method and system are described for receiving input for a virtual user in a virtual environment. The input may be based on a plurality of movements performed by a user accessing the virtual environment. Based on the plurality of movements, the method and system can include detecting that at least one portion of the virtual user is within a threshold distance of a collision zone, the collision zone being associated with at least one virtual object. The method and system can also include selecting a collision mode for the virtual user based on the at least one portion and the at least one virtual object and dynamically modifying the virtual user based on the selected collision mode.Type: GrantFiled: August 4, 2016Date of Patent: April 28, 2020Assignee: GOOGLE LLCInventors: Manuel Christian Clement, Alexander James Faaborg, Rahul Garg, Jonathan Tompson, Shiqi Chen
-
Patent number: 10599211Abstract: In one aspect, a method and system are described for receiving input for a virtual user in a virtual environment. The input may be based on a plurality of movements performed by a user accessing the virtual environment. Based on the plurality of movements, the method and system can include detecting that at least one portion of the virtual user is within a threshold distance of a collision zone, the collision zone being associated with at least one virtual object. The method and system can also include selecting a collision mode for the virtual user based on the at least one portion and the at least one virtual object and dynamically modifying the virtual user based on the selected collision mode.Type: GrantFiled: August 4, 2016Date of Patent: March 24, 2020Assignee: GOOGLE LLCInventors: Manuel Christian Clement, Alexander James Faaborg, Rahul Garg, Jonathan Tompson, Shiqi Chen
-
Publication number: 20190050062Abstract: Systems and methods for context-sensitive hand interaction with an immersive environment are provided. An example method includes determining a contextual factor for a user and selecting an interaction mode based on the contextual factor. The example method may also include monitoring a hand of the user to determine a hand property and determining an interaction with an immersive environment based on the interaction mode and the hand property.Type: ApplicationFiled: August 10, 2018Publication date: February 14, 2019Inventors: Shiqi Chen, Jonathan Tompson, Rahul Garg
-
Publication number: 20170038830Abstract: In one aspect, a method and system are described for receiving input for a virtual user in a virtual environment. The input may be based on a plurality of movements performed by a user accessing the virtual environment. Based on the plurality of movements, the method and system can include detecting that at least one portion of the virtual user is within a threshold distance of a collision zone, the collision zone being associated with at least one virtual object. The method and system can also include selecting a collision mode for the virtual user based on the at least one portion and the at least one virtual object and dynamically modifying the virtual user based on the selected collision mode.Type: ApplicationFiled: August 4, 2016Publication date: February 9, 2017Inventors: Manuel Christian CLEMENT, Alexander James FAABORG, Rahul GARG, Jonathan TOMPSON, Shiqi CHEN