公开(公告)号：US20240029436A1

公开(公告)日：2024-01-25

申请号：US18375941

申请日：2023-10-02

Applicant: DeepMind Technologies Limited

Inventor： Joao Carreira ,  Carl Doersch ,  Andrew Zisserman

IPC: G06V20/40 ,  G06V10/25 ,  G06N3/045

CPC classification number: G06V20/46 ,  G06V10/25 ,  G06V20/41 ,  G06N3/045

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying actions in a video. One of the methods obtaining a feature representation of a video clip; obtaining data specifying a plurality of candidate agent bounding boxes in the key video frame; and for each candidate agent bounding box: processing the feature representation through an action transformer neural network.

公开(公告)号：US11776269B2

公开(公告)日：2023-10-03

申请号：US17295329

申请日：2019-11-20

Applicant: DeepMind Technologies Limited

Inventor： Joao Carreira ,  Carl Doersch ,  Andrew Zisserman

IPC: G06V20/40 ,  G06V10/25 ,  G06N3/045

CPC classification number: G06V20/46 ,  G06N3/045 ,  G06V10/25 ,  G06V20/41

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying actions in a video. One of the methods obtaining a feature representation of a video clip; obtaining data specifying a plurality of candidate agent bounding boxes in the key video frame; and for each candidate agent bounding box: processing the feature representation through an action transformer neural network.

公开(公告)号：US20240303897A1

公开(公告)日：2024-09-12

申请号：US18600552

申请日：2024-03-08

Applicant: DeepMind Technologies Limited

Inventor： Carl Doersch ,  Yi Yang ,  Mel Vecerik ,  Dilara Gokay ,  Ankush Gupta ,  Yusuf Aytar ,  Joao Carreira ,  Andrew Zisserman

IPC: G06T13/80 ,  G06T3/18 ,  G06T7/70 ,  G06T9/00

CPC classification number: G06T13/80 ,  G06T3/18 ,  G06T7/70 ,  G06T9/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for animating images using point trajectories.

公开(公告)号：US12254693B2

公开(公告)日：2025-03-18

申请号：US18375941

申请日：2023-10-02

Applicant: DeepMind Technologies Limited

Inventor： Joao Carreira ,  Carl Doersch ,  Andrew Zisserman

IPC: G06V20/40 ,  G06N3/045 ,  G06V10/25

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying actions in a video. One of the methods obtaining a feature representation of a video clip; obtaining data specifying a plurality of candidate agent bounding boxes in the key video frame; and for each candidate agent bounding box: processing the feature representation through an action transformer neural network.

公开(公告)号：US20220019807A1

公开(公告)日：2022-01-20

申请号：US17295329

申请日：2019-11-20

Applicant: DeepMind Technologies Limited

Inventor： Joao Carreira ,  Carl Doersch ,  Andrew Zisserman

IPC: G06K9/00 ,  G06N3/04 ,  G06K9/32

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying actions in a video. One of the methods obtaining a feature representation of a video clip; obtaining data specifying a plurality of candidate agent bounding boxes in the key video frame; and for each candidate agent bounding box: processing the feature representation through an action transformer neural network.

公开(公告)号：US20240232580A1

公开(公告)日：2024-07-11

申请号：US18284595

申请日：2022-05-27

Applicant: DEEPMIND TECHNOLOGIES LIMITED

Inventor： Andrew Coulter Jaegle ,  Jean-Baptiste Alayrac ,  Sebastian Borgeaud Dit Avocat ,  Catalin-Dumitru Ionescu ,  Carl Doersch ,  Fengning Ding ,  Oriol Vinyals ,  Olivier Jean Hénaff ,  Skanda Kumar Koppula ,  Daniel Zoran ,  Andrew Brock ,  Evan Gerard Shelhamer ,  Andrew Zisserman ,  Joao Carreira

IPC: G06N3/0455

CPC classification number: G06N3/0455

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a network output using a neural network. In one aspect, a method comprises: obtaining: (i) a network input to a neural network, and (ii) a set of query embeddings; processing the network input using the neural network to generate a network output that comprises a respective dimension corresponding to each query embedding in the set of query embeddings, comprising: processing the network input using an encoder block of the neural network to generate a representation of the network input as a set of latent embeddings; and processing: (i) the set of latent embeddings, and (ii) the set of query embeddings, using a cross-attention block that generates each dimension of the network output by cross-attention of a corresponding query embedding over the set of latent embeddings.

公开(公告)号：US20210383226A1

公开(公告)日：2021-12-09

申请号：US17338809

申请日：2021-06-04

Applicant: DeepMind Technologies Limited

Inventor： Carl Doersch ,  Ankush Gupta ,  Andrew Zisserman

IPC: G06N3/08 ,  G06N3/04

Abstract: There is described a neural network system for determining a similarity measure between a query data item and a set of support data items. The neural network system is implemented by one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations comprising receiving the query data item and obtaining a support set of one or more support data items comprising a support key embedding and a support value embedding for each respective support data item in the support set. The operations further comprise generating a query key embedding for the query data item using a key embedding neural network subsystem configured to process a data item to generate a key embedding.