公开(公告)号：US20210034657A1

公开(公告)日：2021-02-04

申请号：US16525366

申请日：2019-07-29

Applicant: Adobe Inc.

Inventor： Ajinkya Kale ,  Baldo Faieta ,  Benjamin Leviant ,  Fengbin Chen ,  Francois Guerin ,  Kate Sousa ,  Trung Bui ,  Venkat Barakam ,  Zhe Lin

IPC: G06F16/48 ,  G06K9/62 ,  G06F16/43 ,  G06F16/2457

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for determining multi-term contextual tags for digital content and propagating the multi-term contextual tags to additional digital content. For instance, the disclosed systems can utilize search query supervision to determine and associate multi-term contextual tags (e.g., tags that represent a specific concept based on the order of the terms in the tag) with digital content. Furthermore, the disclosed systems can propagate the multi-term contextual tags determined for the digital content to additional digital content based on similarities between the digital content and additional digital content (e.g., utilizing clustering techniques). Additionally, the disclosed systems can provide digital content as search results based on the associated multi-term contextual tags.

公开(公告)号：US11232147B2

公开(公告)日：2022-01-25

申请号：US16525366

申请日：2019-07-29

Applicant: Adobe Inc.

Inventor： Ajinkya Kale ,  Baldo Faieta ,  Benjamin Leviant ,  Fengbin Chen ,  Francois Guerin ,  Kate Sousa ,  Trung Bui ,  Venkat Barakam ,  Zhe Lin

IPC: G06F16/20 ,  G06F16/48 ,  G06K9/62 ,  G06F16/2457 ,  G06F16/43

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for determining multi-term contextual tags for digital content and propagating the multi-term contextual tags to additional digital content. For instance, the disclosed systems can utilize search query supervision to determine and associate multi-term contextual tags (e.g., tags that represent a specific concept based on the order of the terms in the tag) with digital content. Furthermore, the disclosed systems can propagate the multi-term contextual tags determined for the digital content to additional digital content based on similarities between the digital content and additional digital content (e.g., utilizing clustering techniques). Additionally, the disclosed systems can provide digital content as search results based on the associated multi-term contextual tags.

公开(公告)号：US11971885B2

公开(公告)日：2024-04-30

申请号：US17172986

申请日：2021-02-10

Applicant: ADOBE INC.

Inventor： Fengbin Chen ,  Venkat Barakam ,  Benjamin Leviant ,  Amine Ben Khalifa ,  Kerem Turgutlu ,  Jayant Kumar ,  Sumeet Zaverilal Gala ,  Gaurav Kukal ,  Vipul Dalal

IPC: G06F16/00 ,  G06F16/245 ,  G06N3/04 ,  G06N3/08

CPC classification number: G06F16/245 ,  G06N3/04 ,  G06N3/08

Abstract: Systems and methods for information retrieval are described. Embodiments generate a dense embedding for each of a plurality of media objects to be searched, generate a sparse embedding for each of the media objects using an encoder that takes the dense embedding as an input, wherein the sparse embedding satisfies a sparsity constraint that is applied to at least one layer of the encoder during training, and perform a search on the plurality of media objects based at least in part on the sparse embedding.

公开(公告)号：US20220100791A1

公开(公告)日：2022-03-31

申请号：US17544689

申请日：2021-12-07

Applicant: Adobe Inc.

Inventor： Ajinkya Kale ,  Baldo Faieta ,  Benjamin Leviant ,  Fengbin Chen ,  Francois Guerin ,  Kate Sousa ,  Trung Bui ,  Venkat Barakam ,  Zhe Lin

IPC: G06F16/48 ,  G06K9/62 ,  G06F16/2457 ,  G06F16/43

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for determining multi-term contextual tags for digital content and propagating the multi-term contextual tags to additional digital content. For instance, the disclosed systems can utilize search query supervision to determine and associate multi-term contextual tags (e.g., tags that represent a specific concept based on the order of the terms in the tag) with digital content. Furthermore, the disclosed systems can propagate the multi-term contextual tags determined for the digital content to additional digital content based on similarities between the digital content and additional digital content (e.g., utilizing clustering techniques). Additionally, the disclosed systems can provide digital content as search results based on the associated multi-term contextual tags.

公开(公告)号：US11741157B2

公开(公告)日：2023-08-29

申请号：US17544689

申请日：2021-12-07

Applicant: Adobe Inc.

Inventor： Ajinkya Kale ,  Baldo Faieta ,  Benjamin Leviant ,  Fengbin Chen ,  Francois Guerin ,  Kate Sousa ,  Trung Bui ,  Venkat Barakam ,  Zhe Lin

IPC: G06F16/40 ,  G06F16/58 ,  G06F16/48 ,  G06F16/2457 ,  G06F16/43 ,  G06V20/00 ,  G06F18/23213

CPC classification number: G06F16/5866 ,  G06F16/24578 ,  G06F16/43 ,  G06F16/48 ,  G06F18/23213 ,  G06V20/35 ,  G06V2201/10

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for determining multi-term contextual tags for digital content and propagating the multi-term contextual tags to additional digital content. For instance, the disclosed systems can utilize search query supervision to determine and associate multi-term contextual tags (e.g., tags that represent a specific concept based on the order of the terms in the tag) with digital content. Furthermore, the disclosed systems can propagate the multi-term contextual tags determined for the digital content to additional digital content based on similarities between the digital content and additional digital content (e.g., utilizing clustering techniques). Additionally, the disclosed systems can provide digital content as search results based on the associated multi-term contextual tags.

公开(公告)号：US20220253435A1

公开(公告)日：2022-08-11

申请号：US17172986

申请日：2021-02-10

Applicant: ADOBE INC.

Inventor： Fengbin Chen ,  Venkat Barakam ,  Benjamin Leviant ,  Amine Ben Khalifa ,  Kerem Turgutlu ,  Jayant Kumar ,  Sumeet Zaverilal Gala ,  Gaurav Kukal ,  Vipul Dalal

IPC: G06F16/245 ,  G06N3/04 ,  G06N3/08

Abstract: Systems and methods for information retrieval are described. Embodiments generate a dense embedding for each of a plurality of media objects to be searched, generate a sparse embedding for each of the media objects using an encoder that takes the dense embedding as an input, wherein the sparse embedding satisfies a sparsity constraint that is applied to at least one layer of the encoder during training, and perform a search on the plurality of media objects based at least in part on the sparse embedding.