公开(公告)号：US11854116B2

公开(公告)日：2023-12-26

申请号：US17740533

申请日：2022-05-10

Applicant: Amazon Technologies, Inc.

Inventor： Vivek Yadav ,  Aayush Gupta ,  Yue Wu ,  Pradeep Natarajan ,  Ayush Jaiswal

IPC: G06T11/00 ,  G06N20/00 ,  G06N3/08 ,  G06F18/2431 ,  G06F18/214 ,  G06V10/772 ,  G06V10/20

CPC classification number: G06T11/00 ,  G06F18/214 ,  G06F18/2431 ,  G06N3/08 ,  G06N20/00 ,  G06V10/20 ,  G06V10/772

Abstract: Techniques for masking images based on a particular task are described. A system masks portions of an image that are not relevant to a particular task, thus, reducing the amount of data used by applications for image processing tasks. For example, images to be processed using a hair color classification model are masked so that only portions that show the person's hair are available for the model to analyze. The system configures different masker components to mask images for different tasks. A masker component can be implemented at a user device to mask images prior to sending to an application/task-specific model.

公开(公告)号：US11775617B1

公开(公告)日：2023-10-03

申请号：US17201358

申请日：2021-03-15

Applicant: Amazon Technologies, Inc.

Inventor： Ayush Jaiswal ,  Yue Wu ,  Pradeep Natarajan ,  Premkumar Natarajan

IPC: G06K9/00 ,  G06F18/2413 ,  G06F16/53 ,  G06F40/20 ,  G06V10/40 ,  G06F18/22 ,  G06F18/2132

CPC classification number: G06F18/2413 ,  G06F16/53 ,  G06F18/2132 ,  G06F18/22 ,  G06F40/20 ,  G06V10/40

Abstract: Devices and techniques are generally described for class-agnostic object detection. In some examples, a first frame of image data comprising a first plurality of pixels may be received. First class-agnostic feature data representing the first plurality of pixels may be generated. A first object detection component may be used to determine that the first plurality of pixels corresponds to an arbitrary object represented in the first frame of image data based at least in part on the first class-agnostic feature data. Class-agnostic data indicating that the first plurality of pixels in the first frame of image data corresponds to the arbitrary object may be generated.

公开(公告)号：US20210406589A1

公开(公告)日：2021-12-30

申请号：US16913837

申请日：2020-06-26

Applicant: Amazon Technologies, Inc.

Inventor： Vivek Yadav ,  Aayush Gupta ,  Yue Wu ,  Pradeep Natarajan ,  Ayush Jaiswal

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

Abstract: Techniques for masking images based on a particular task are described. A system masks portions of an image that are not relevant to a particular task, thus, reducing the amount of data used by applications for image processing tasks. For example, images to be processed using a hair color classification model are masked so that only portions that show the person's hair are available for the model to analyze. The system configures different masker components to mask images for different tasks. A masker component can be implemented at a user device to mask images prior to sending to an application/task-specific model.

公开(公告)号：US12254548B1

公开(公告)日：2025-03-18

申请号：US18082709

申请日：2022-12-16

Applicant: Amazon Technologies, Inc.

Inventor： Gourav Datta ,  Vivek Yadav ,  Yue Wu ,  Ayush Jaiswal ,  Rajiv M Reddy ,  Prateek Singhal ,  Karthik Ramakrishnan ,  Premkumar Natarajan

IPC: G06T7/20 ,  G06T7/70 ,  G06T13/20 ,  G06T13/40 ,  G06V40/16 ,  G10L15/22 ,  G10L25/57 ,  G10L25/60

Abstract: A system configured to perform style-aware listener animation. By representing different listening styles (e.g., facial expressions) using an embedding space, a single model can be trained to generate unique facial animations for a number of distinct listeners. Thus, individual listening styles can be associated with a listener identifier, enabling the system to (i) animate a plurality of different listeners with unique nonverbal behavior and/or (ii) select a particular listener identifier or desired type of listener style with which to animate. This enables the model to be generalized to new listeners to generate additional listener facial responses without needing training data for each new listener. The model may process a listener representation style or listener identifier, along with input data corresponding to a speaker talking, to generate unique facial animation responsive to the speech.

公开(公告)号：US20220405528A1

公开(公告)日：2022-12-22

申请号：US17740533

申请日：2022-05-10

Applicant: Amazon Technologies, Inc.

Inventor： Vivek Yadav ,  Aayush Gupta ,  Yue Wu ,  Pradeep Natarajan ,  Ayush Jaiswal

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

Abstract: Techniques for masking images based on a particular task are described. A system masks portions of an image that are not relevant to a particular task, thus, reducing the amount of data used by applications for image processing tasks. For example, images to be processed using a hair color classification model are masked so that only portions that show the person's hair are available for the model to analyze. The system configures different masker components to mask images for different tasks. A masker component can be implemented at a user device to mask images prior to sending to an application/task-specific model.

公开(公告)号：US11334773B2

公开(公告)日：2022-05-17

申请号：US16913837

申请日：2020-06-26

Applicant: Amazon Technologies, Inc.

Inventor： Vivek Yadav ,  Aayush Gupta ,  Yue Wu ,  Pradeep Natarajan ,  Ayush Jaiswal

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

Abstract: Techniques for masking images based on a particular task are described. A system masks portions of an image that are not relevant to a particular task, thus, reducing the amount of data used by applications for image processing tasks. For example, images to be processed using a hair color classification model are masked so that only portions that show the person's hair are available for the model to analyze. The system configures different masker components to mask images for different tasks. A masker component can be implemented at a user device to mask images prior to sending to an application/task-specific model.