公开(公告)号：US20200027002A1

公开(公告)日：2020-01-23

申请号：US16511637

申请日：2019-07-15

Applicant: Google LLC

Inventor： Steven Hickson ,  Anelia Angelova ,  Irfan Aziz Essa ,  Rahul Sukthankar

IPC: G06N3/08 ,  G06N20/00 ,  G06K9/62 ,  G06T7/50

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining a clustering of images into a plurality of semantic categories. In one aspect, a method comprises: training a categorization neural network, comprising, at each of a plurality of iterations: processing an image depicting an object using the categorization neural network to generate (i) a current prediction for whether the image depicts an object or a background region, and (ii) a current embedding of the image; determining a plurality of current cluster centers based on the current values of the categorization neural network parameters, wherein each cluster center represents a respective semantic category; and determining a gradient of an objective function that includes a classification loss and a clustering loss, wherein the clustering loss depends on a similarity between the current embedding of the image and the current cluster centers.

公开(公告)号：US20240212246A1

公开(公告)日：2024-06-27

申请号：US18400629

申请日：2023-12-29

Applicant: Google LLC

Inventor： Tianhao Zhang ,  Weilong Yang ,  Honglak Lee ,  Hung-Yu Tseng ,  Irfan Aziz Essa ,  Lu Jiang

IPC: G06T11/60 ,  G06N3/045 ,  G06N3/088 ,  G06T3/02 ,  G06T3/40 ,  G06T9/00

CPC classification number: G06T11/60 ,  G06N3/045 ,  G06N3/088 ,  G06T3/02 ,  G06T3/40 ,  G06T9/002

Abstract: A method for generating an output image from an input image and an input text instruction that specifies a location and a modification of an edit applied to the input image using a neural network is described. The neural network includes an image encoder, an image decoder, and an instruction attention network. The method includes receiving the input image and the input text instruction; extracting, from the input image, an input image feature that represents features of the input image using the image encoder; generating a spatial feature and a modification feature from the input text instruction using the instruction attention network; generating an edited image feature from the input image feature, the spatial feature and the modification feature; and generating the output image from the edited image feature using the image decoder.

公开(公告)号：US11900517B2

公开(公告)日：2024-02-13

申请号：US18085487

申请日：2022-12-20

Applicant: Google LLC

Inventor： Tianhao Zhang ,  Weilong Yang ,  Honglak Lee ,  Hung-Yu Tseng ,  Irfan Aziz Essa ,  Lu Jiang

IPC: G06T11/60 ,  G06T9/00 ,  G06T3/00 ,  G06N3/088 ,  G06T3/40 ,  G06N3/045

CPC classification number: G06T11/60 ,  G06N3/045 ,  G06N3/088 ,  G06T3/0006 ,  G06T3/40 ,  G06T9/002

Abstract: A method for generating an output image from an input image and an input text instruction that specifies a location and a modification of an edit applied to the input image using a neural network is described. The neural network includes an image encoder, an image decoder, and an instruction attention network. The method includes receiving the input image and the input text instruction; extracting, from the input image, an input image feature that represents features of the input image using the image encoder; generating a spatial feature and a modification feature from the input text instruction using the instruction attention network; generating an edited image feature from the input image feature, the spatial feature and the modification feature; and generating the output image from the edited image feature using the image decoder.

公开(公告)号：US20230177754A1

公开(公告)日：2023-06-08

申请号：US18085487

申请日：2022-12-20

Applicant: Google LLC

Inventor： Tianhao Zhang ,  Weilong Yang ,  Honglak Lee ,  Hung-Yu Tseng ,  Irfan Aziz Essa ,  Lu Jiang

IPC: G06T11/60 ,  G06T3/00 ,  G06N3/088 ,  G06T3/40 ,  G06T9/00 ,  G06N3/045

CPC classification number: G06T11/60 ,  G06T3/0006 ,  G06N3/088 ,  G06T3/40 ,  G06T9/002 ,  G06N3/045

Abstract: A method for generating an output image from an input image and an input text instruction that specifies a location and a modification of an edit applied to the input image using a neural network is described. The neural network includes an image encoder, an image decoder, and an instruction attention network. The method includes receiving the input image and the input text instruction; extracting, from the input image, an input image feature that represents features of the input image using the image encoder; generating a spatial feature and a modification feature from the input text instruction using the instruction attention network; generating an edited image feature from the input image feature, the spatial feature and the modification feature; and generating the output image from the edited image feature using the image decoder.

公开(公告)号：US20250095690A1

公开(公告)日：2025-03-20

申请号：US18886486

申请日：2024-09-16

Applicant: Google LLC

Inventor： Pei-Yu Chi ,  Sen-Po Hu ,  Irfan Aziz Essa ,  Tao Dong

IPC: G11B27/031 ,  G06F40/166 ,  G06F40/40 ,  G06T13/20 ,  G06T13/40 ,  G06V20/50 ,  G06V40/16 ,  G11B27/34

Abstract: Provided are systems and methods for the automatic generation of support videos from a source video. For example, the support video can more deeply explain or elaborate upon content included in source video. In particular, a computing system can obtain a source video and extract one or more sets of textual content associated with the source video. For example, the sets of textual content can include a transcript of speech that occurs within the source video. The computing system can process the one or more sets of textual content with a generative sequence processing model to generate, as an output of the generative sequence processing model, additional textual content for a support video.

公开(公告)号：US11562518B2

公开(公告)日：2023-01-24

申请号：US17340671

申请日：2021-06-07

Applicant: Google LLC

Inventor： Tianhao Zhang ,  Weilong Yang ,  Honglak Lee ,  Hung-Yu Tseng ,  Irfan Aziz Essa ,  Lu Jiang

IPC: G06T11/60 ,  G06T3/00 ,  G06N3/04 ,  G06N3/08 ,  G06T3/40 ,  G06T9/00

Abstract: A method for generating an output image from an input image and an input text instruction that specifies a location and a modification of an edit applied to the input image using a neural network is described. The neural network includes an image encoder, an image decoder, and an instruction attention network. The method includes receiving the input image and the input text instruction; extracting, from the input image, an input image feature that represents features of the input image using the image encoder; generating a spatial feature and a modification feature from the input text instruction using the instruction attention network; generating an edited image feature from the input image feature, the spatial feature and the modification feature; and generating the output image from the edited image feature using the image decoder.

公开(公告)号：US20210383584A1

公开(公告)日：2021-12-09

申请号：US17340671

申请日：2021-06-07

Applicant: Google LLC

Inventor： Tianhao Zhang ,  Weilong Yang ,  Honglak Lee ,  Hung-Yu Tseng ,  Irfan Aziz Essa ,  Lu Jiang

IPC: G06T11/60 ,  G06T3/00 ,  G06T3/40 ,  G06N3/08 ,  G06N3/04

Abstract: A method for generating an output image from an input image and an input text instruction that specifies a location and a modification of an edit applied to the input image using a neural network is described. The neural network includes an image encoder, an image decoder, and an instruction attention network. The method includes receiving the input image and the input text instruction; extracting, from the input image, an input image feature that represents features of the input image using the image encoder; generating a spatial feature and a modification feature from the input text instruction using the instruction attention network; generating an edited image feature from the input image feature, the spatial feature and the modification feature; and generating the output image from the edited image feature using the image decoder.