公开(公告)号：US20240403362A1

公开(公告)日：2024-12-05

申请号：US18326496

申请日：2023-05-31

Applicant: Google LLC

Inventor： Harshit Kharbanda ,  Belinda Luna Zeng ,  Viviana Caso Corella ,  Aashi Jain ,  David William Hendon ,  Christopher James Kelley ,  Jessica Lee ,  Dounia Berrada ,  Kai Yu ,  Louis Wang ,  Thomas J. Duerig ,  Radu Soricut ,  Robin Dua

IPC: G06F16/735 ,  G06F16/732 ,  G06F16/783 ,  G06T7/70 ,  G06V10/62 ,  G06V10/774 ,  G06V20/40

Abstract: A multimodal search system using a video query is described. The system can receive video data captured by a camera of a user device. The video data can have a sequence of image frames. Additionally, the system can receive audio data associated with the video data captured by the user device. Moreover, the system can process, using one or more machine-learned models, the sequence of image frames to generate video embeddings related to the sequence of the image frames. The video embeddings can have a plurality of image embeddings associated with the sequence of image frames. Furthermore, the system can determine one or more video results based on the video embeddings and the audio data. Subsequently, the system can transmit, to the user device, the one or more video results.

公开(公告)号：US12271417B2

公开(公告)日：2025-04-08

申请号：US18305660

申请日：2023-04-24

Applicant: Google LLC

Inventor： Belinda Luna Zeng ,  Harshit Kharbanda ,  Christopher James Kelley ,  Erica Bjornsson ,  David William Hendon

IPC: G06F16/532 ,  G06F16/538 ,  G06F16/55 ,  G06F16/583 ,  G06V10/22 ,  G06V10/26 ,  G06V10/75 ,  G06V10/764

Abstract: Systems and methods for multi-image search can include obtaining two or more images and determining one or more search results that are based on the two or more images. The one or more search results can be determined based on determined shared attributes of the two or more images. The one or more search results may be based on feature embeddings associated with the two or more images. The two or more images may be obtained based on one or more user interactions with one or more databases.

公开(公告)号：US20240354332A1

公开(公告)日：2024-10-24

申请号：US18305660

申请日：2023-04-24

Applicant: Google LLC

Inventor： Belinda Luna Zeng ,  Harshit Kharbanda ,  Christopher James Kelley ,  Erica Bjornsson ,  David William Hendon

IPC: G06F16/532 ,  G06F16/538 ,  G06F16/55 ,  G06F16/583 ,  G06V10/22 ,  G06V10/26 ,  G06V10/75 ,  G06V10/764

CPC classification number: G06F16/532 ,  G06F16/538 ,  G06F16/55 ,  G06F16/5846 ,  G06V10/235 ,  G06V10/267 ,  G06V10/751 ,  G06V10/764

Abstract: Systems and methods for multi-image search can include obtaining two or more images and determining one or more search results that are based on the two or more images. The one or more search results can be determined based on determined shared attributes of the two or more images. The one or more search results may be based on feature embeddings associated with the two or more images. The two or more images may be obtained based on one or more user interactions with one or more databases.