公开(公告)号：US20220132235A1

公开(公告)日：2022-04-28

申请号：US17498900

申请日：2021-10-12

Applicant: Google LLC

Inventor： Chen Wang

IPC: H04R1/10 ,  H04R1/02

Abstract: Though some basic electronic devices are not enabled for wireless pairing with audio accessories, such as earbuds, the present disclosure provides a mechanism for adapting such basic electronic devices. In particular, a wireless pairing transceiver is integrated into a case for the audio accessory. The case can be physically electronically connected to the basic audio device through a speaker jack in the basic audio device. Accordingly, audio signals from the basic electronic device can be output to the case and then wirelessly transmitted to the accessory. Similarly, audio input from the wireless accessory can be wirelessly transmitted to the case and then relayed to the basic electronic device.

公开(公告)号：US11115678B2

公开(公告)日：2021-09-07

申请号：US16861299

申请日：2020-04-29

Applicant: GOOGLE LLC

Inventor： Debargha Mukherjee ,  Emil Keyder ,  Michele Covell ,  Chen Wang ,  Sarah Parker ,  Ramin Zabih

IPC: H04N19/527 ,  H04N19/172 ,  H04N19/176 ,  H04N19/109 ,  G06T7/246 ,  H04N19/44 ,  H04N19/159 ,  H04N19/124 ,  H04N19/119 ,  H04N19/192 ,  H04N19/137 ,  H04N19/17 ,  H04N19/167 ,  H04N19/543 ,  H04N19/573 ,  H04N19/147 ,  H04N19/14 ,  H04N19/557

Abstract: An apparatus for encoding a current frame of a video. The apparatus includes a memory and a processor. The processor is configured to execute instructions stored in the memory to generate, for each reference frame of a subset of available reference frames, at least one respective candidate global motion model (GMM); partition the current frame into blocks; generate an aggregated residual frame for the current frame; and encode the respective residual blocks in a compressed bitstream. To generate the aggregated residual frame includes to select, for predicting each block of the blocks, a respective selected GMM, where the respective selected GMM corresponds to the one of the at least one respective candidate GMMs that minimizes a total error associated with the aggregated residual frame; and obtain respective residual blocks for the block.

公开(公告)号：US20190149841A1

公开(公告)日：2019-05-16

申请号：US16016857

申请日：2018-06-25

Applicant: GOOGLE LLC

Inventor： Debargha Mukherjee ,  Emil Keyder ,  Michele Covell ,  Chen Wang ,  Sarah Parker ,  Ramin Zabih

IPC: H04N19/527 ,  G06T7/246 ,  H04N19/172 ,  H04N19/176 ,  H04N19/159 ,  H04N19/124 ,  H04N19/44

Abstract: A method for encoding a current frame of a video includes jointly determining respective motion models for reference frames and encoding the current frame using the respective motion models. The reference frames are used for encoding the current frame. Jointly determining respective motion models for reference frames includes determining respective aggregated residuals for combinations of candidate motion models and selecting the combination of candidate motion models that corresponds to the smallest aggregated residual. The respective motion models correspond to the candidate motion models of the selected combination.

公开(公告)号：US20200260112A1

公开(公告)日：2020-08-13

申请号：US16861299

申请日：2020-04-29

Applicant: GOOGLE LLC

Inventor： Debargha Mukherjee ,  Emil Keyder ,  Michele Covell ,  Chen Wang ,  Sarah Parker ,  Ramin Zabih

IPC: H04N19/527 ,  H04N19/147 ,  H04N19/573 ,  H04N19/543 ,  H04N19/167 ,  H04N19/17 ,  H04N19/137 ,  H04N19/109 ,  H04N19/192 ,  H04N19/119 ,  H04N19/176 ,  H04N19/124 ,  H04N19/159 ,  H04N19/44 ,  H04N19/172 ,  G06T7/246

Abstract: An apparatus for encoding a current frame of a video. The apparatus includes a memory and a processor. The processor is configured to execute instructions stored in the memory to generate, for each reference frame of a subset of available reference frames, at least one respective candidate global motion model (GMM); partition the current frame into blocks; generate an aggregated residual frame for the current frame; and encode the respective residual blocks in a compressed bitstream. To generate the aggregated residual frame includes to select, for predicting each block of the blocks, a respective selected GMM, where the respective selected GMM corresponds to the one of the at least one respective candidate GMMs that minimizes a total error associated with the aggregated residual frame; and obtain respective residual blocks for the block.

公开(公告)号：US20230153629A1

公开(公告)日：2023-05-18

申请号：US17920623

申请日：2021-04-12

Applicant: Google LLC

Inventor： Dilip Krishnan ,  Prannay Khosla ,  Piotr Teterwak ,  Aaron Yehuda Sarna ,  Aaron Joseph Maschinot ,  Ce Liu ,  Philip John Isola ,  Yonglong Tian ,  Chen Wang

IPC: G06N3/09 ,  G06V10/74 ,  G06V10/776 ,  G06V10/82

CPC classification number: G06N3/09 ,  G06V10/761 ,  G06V10/776 ,  G06V10/82

Abstract: The present disclosure provides an improved training methodology that enables supervised contrastive learning to be simultaneously performed across multiple positive and negative training examples. In particular, example aspects of the present disclosure are directed to an improved, supervised version of the batch contrastive loss, which has been shown to be very effective at learning powerful representations in the self-supervised setting Thus, the proposed techniques adapt contrastive learning to the fully supervised setting and also enable learning to occur simultaneously across multiple positive examples.

公开(公告)号：US20210326660A1

公开(公告)日：2021-10-21

申请号：US17235992

申请日：2021-04-21

Applicant: Google LLC

Inventor： Dilip Krishnan ,  Prannay Khosla ,  Piotr Teterwak ,  Aaron Yehuda Sarna ,  Aaron Joseph Maschinot ,  Ce Liu ,  Phillip John Isola ,  Yonglong Tian ,  Chen Wang

IPC: G06K9/62 ,  G06N3/08

Abstract: The present disclosure provides an improved training methodology that enables supervised contrastive learning to be simultaneously performed across multiple positive and negative training examples. In particular, example aspects of the present disclosure are directed to an improved, supervised version of the batch contrastive loss, which has been shown to be very effective at learning powerful representations in the self-supervised setting. Thus, the proposed techniques adapt contrastive learning to the fully supervised setting and also enable learning to occur simultaneously across multiple positive examples.

公开(公告)号：US10681374B2

公开(公告)日：2020-06-09

申请号：US16016857

申请日：2018-06-25

Applicant: GOOGLE LLC

Inventor： Debargha Mukherjee ,  Emil Keyder ,  Michele Covell ,  Chen Wang ,  Sarah Parker ,  Ramin Zabih

IPC: H04N19/527 ,  G06T7/246 ,  H04N19/172 ,  H04N19/44 ,  H04N19/159 ,  H04N19/124 ,  H04N19/176 ,  H04N19/119 ,  H04N19/192 ,  H04N19/109 ,  H04N19/137 ,  H04N19/17 ,  H04N19/167 ,  H04N19/543 ,  H04N19/573 ,  H04N19/147 ,  H04N19/14 ,  H04N19/557

Abstract: A method for encoding a current frame of a video includes jointly determining respective motion models for reference frames and encoding the current frame using the respective motion models. The reference frames are used for encoding the current frame. Jointly determining respective motion models for reference frames includes determining respective aggregated residuals for combinations of candidate motion models and selecting the combination of candidate motion models that corresponds to the smallest aggregated residual. The respective motion models correspond to the candidate motion models of the selected combination.

公开(公告)号：US11347975B2

公开(公告)日：2022-05-31

申请号：US17235992

申请日：2021-04-21

Applicant: Google LLC

Inventor： Dilip Krishnan ,  Prannay Khosla ,  Piotr Teterwak ,  Aaron Yehuda Sarna ,  Aaron Joseph Maschinot ,  Ce Liu ,  Phillip John Isola ,  Yonglong Tian ,  Chen Wang

IPC: G06K9/62 ,  G06N3/08 ,  G06V10/82

Abstract: The present disclosure provides an improved training methodology that enables supervised contrastive learning to be simultaneously performed across multiple positive and negative training examples. In particular, example aspects of the present disclosure are directed to an improved, supervised version of the batch contrastive loss, which has been shown to be very effective at learning powerful representations in the self-supervised setting. Thus, the proposed techniques adapt contrastive learning to the fully supervised setting and also enable learning to occur simultaneously across multiple positive examples.

公开(公告)号：US20180349435A1

公开(公告)日：2018-12-06

申请号：US16101922

申请日：2018-08-13

Applicant: Google LLC

Inventor： Hui Xu ,  Erik Hendriks ,  Chen Wang

IPC: G06F17/30 ,  H04L29/08

CPC classification number: G06F17/30371 ,  G06F17/30864 ,  H04L67/303

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for verifying consistency between content of a native application and content of a corresponding resource that is provided separately from the content of the native application.