公开(公告)号：US20240346824A1

公开(公告)日：2024-10-17

申请号：US18634794

申请日：2024-04-12

Applicant: Google LLC

Inventor： Alexey Alexeevich Gritsenko ,  Xuehan Xiong ,  Josip Djolonga ,  Mostafa Dehghani ,  Chen Sun ,  Mario Lucic ,  Cordelia Luise Schmid ,  Anurag Arnab

IPC: G06V20/40 ,  G06T7/73 ,  G06V10/62 ,  G06V10/764 ,  G06V10/77 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82

CPC classification number: G06V20/46 ,  G06T7/73 ,  G06V10/62 ,  G06V10/764 ,  G06V10/7715 ,  G06V10/774 ,  G06V10/776 ,  G06V10/82 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing action localization on an input video. In particular, a system maintains a set of query vectors and uses the input video and the set of query vectors to generate an action localization output for the input video. The action localization output includes, for each of one or more agents depicted in the video, data specifying, for each of one or more video frames in the video, a respective bounding box in the video frame that depicts the agent and a respective action from a set of actions that is being performed by the agent in the video frame.

公开(公告)号：US20240256835A1

公开(公告)日：2024-08-01

申请号：US18424420

申请日：2024-01-26

Applicant: Google LLC

Inventor： Mostafa Dehghani ,  Josip Djolonga ,  Jonathan Heek ,  Basil Mustafa ,  Piotr Michal Padlewski ,  Justin Morgan Gilmer ,  Neil Matthew Tinmouth Houlsby

IPC: G06N3/0455 ,  G06N3/088

CPC classification number: G06N3/0455 ,  G06N3/088

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing an input through each of a plurality of layers of a neural network to generate an output using a plurality of hardware accelerators. The plurality of layers comprise a fully connected layer having a plurality of parameters arranged in a row dimension and a column dimension. One of the methods comprises: generating a plurality of parameter blocks by partitioning the plurality of parameters along the row dimension and the column dimension; determining a ratio of a number of parameters along the row dimension relative to a number of parameters along the column dimension; and determining whether to use row sharding or column sharding with the plurality of hardware accelerators to calculate an output for the fully connected layer and then calculating the output for the fully connected layer using either row sharding or column sharding.