-
1.发明申请公开(公告)号：US20220148325A1
公开(公告)日：2022-05-12
申请号：US17584962
申请日：2022-01-26
Applicant: Adobe Inc.
Inventor： Zhaowen Wang , Tianlang Chen , Ning Xu , Hailin Jin
IPC: G06V30/244 , G06K9/62 , G06F16/906 , G06N3/08 , G06F16/903 , G06F40/109 , G06V10/40
Abstract: The present disclosure relates to a tag-based font recognition system that utilizes a multi-learning framework to develop and improve tag-based font recognition using deep learning neural networks. In particular, the tag-based font recognition system jointly trains a font tag recognition neural network with an implicit font classification attention model to generate font tag probability vectors that are enhanced by implicit font classification information. Indeed, the font recognition system weights the hidden layers of the font tag recognition neural network with implicit font information to improve the accuracy and predictability of the font tag recognition neural network, which results in improved retrieval of fonts in response to a font tag query. Accordingly, using the enhanced tag probability vectors, the tag-based font recognition system can accurately identify and recommend one or more fonts in response to a font tag query.
-
公开(公告)号：US11244207B2
公开(公告)日：2022-02-08
申请号：US17101778
申请日：2020-11-23
Applicant: Adobe Inc.
Inventor： Zhaowen Wang , Tianlang Chen , Ning Xu , Hailin Jin
IPC: G06K9/00 , G06K9/68 , G06K9/62 , G06K9/46 , G06F16/906 , G06N3/08 , G06F16/903 , G06F40/109
Abstract: The present disclosure relates to a tag-based font recognition system that utilizes a multi-learning framework to develop and improve tag-based font recognition using deep learning neural networks. In particular, the tag-based font recognition system jointly trains a font tag recognition neural network with an implicit font classification attention model to generate font tag probability vectors that are enhanced by implicit font classification information. Indeed, the font recognition system weights the hidden layers of the font tag recognition neural network with implicit font information to improve the accuracy and predictability of the font tag recognition neural network, which results in improved retrieval of fonts in response to a font tag query. Accordingly, using the enhanced tag probability vectors, the tag-based font recognition system can accurately identify and recommend one or more fonts in response to a font tag query.
-
Patent Agency Ranking
3.发明申请公开(公告)号：US20200285916A1
公开(公告)日：2020-09-10
申请号：US16294417
申请日：2019-03-06
Applicant: Adobe Inc.
Inventor： Zhaowen Wang , Tianlang Chen , Ning Xu , Hailin Jin
IPC: G06K9/68 , G06K9/62 , G06K9/46 , G06F17/21 , G06N3/08 , G06F16/903 , G06F16/906
Abstract: The present disclosure relates to a tag-based font recognition system that utilizes a multi-learning framework to develop and improve tag-based font recognition using deep learning neural networks. In particular, the tag-based font recognition system jointly trains a font tag recognition neural network with an implicit font classification attention model to generate font tag probability vectors that are enhanced by implicit font classification information. Indeed, the font recognition system weights the hidden layers of the font tag recognition neural network with implicit font information to improve the accuracy and predictability of the font tag recognition neural network, which results in improved retrieval of fonts in response to a font tag query. Accordingly, using the enhanced tag probability vectors, the tag-based font recognition system can accurately identify and recommend one or more fonts in response to a font tag query.
-
公开(公告)号：US20210103783A1
公开(公告)日：2021-04-08
申请号：US17101778
申请日：2020-11-23
Applicant: Adobe Inc.
Inventor： Zhaowen Wang , Tianlang Chen , Ning Xu , Hailin Jin
IPC: G06K9/68 , G06F16/906 , G06F16/903 , G06F40/109 , G06N3/08 , G06K9/62 , G06K9/46
Abstract: The present disclosure relates to a tag-based font recognition system that utilizes a multi-learning framework to develop and improve tag-based font recognition using deep learning neural networks. In particular, the tag-based font recognition system jointly trains a font tag recognition neural network with an implicit font classification attention model to generate font tag probability vectors that are enhanced by implicit font classification information. Indeed, the font recognition system weights the hidden layers of the font tag recognition neural network with implicit font information to improve the accuracy and predictability of the font tag recognition neural network, which results in improved retrieval of fonts in response to a font tag query. Accordingly, using the enhanced tag probability vectors, the tag-based font recognition system can accurately identify and recommend one or more fonts in response to a font tag query.
-
公开(公告)号：US10803231B1
公开(公告)日：2020-10-13
申请号：US16369893
申请日：2019-03-29
Applicant: Adobe Inc.
Inventor： Zhaowen Wang , Tianlang Chen , Ning Xu , Hailin Jin
Abstract: The present disclosure describes a font retrieval system that utilizes a multi-learning framework to develop and improve tag-based font recognition using deep learning neural networks. In particular, the font retrieval system jointly utilizes a combined recognition/retrieval model to generate font affinity scores corresponding to a list of font tags. Further, based on the font affinity scores, the font retrieval system identifies one or more fonts to recommend in response to the list of font tags such that the one or more provided fonts fairly reflect each of the font tags. Indeed, the font retrieval system utilizes a trained font retrieval neural network to efficiently and accurately identify and retrieve fonts in response to a text font tag query.
-
6.发明授权公开(公告)号：US11636147B2
公开(公告)日：2023-04-25
申请号：US17584962
申请日：2022-01-26
Applicant: Adobe Inc.
Inventor： Zhaowen Wang , Tianlang Chen , Ning Xu , Hailin Jin
IPC: G06F16/906 , G06F16/55 , G06N3/084 , G06F16/903 , G06F40/109 , G06V30/244 , G06F18/28 , G06F18/21 , G06F18/214 , G06F18/2415 , G06V30/19 , G06V30/226 , G06V10/82 , G06V10/44
Abstract: The present disclosure relates to a tag-based font recognition system that utilizes a multi-learning framework to develop and improve tag-based font recognition using deep learning neural networks. In particular, the tag-based font recognition system jointly trains a font tag recognition neural network with an implicit font classification attention model to generate font tag probability vectors that are enhanced by implicit font classification information. Indeed, the font recognition system weights the hidden layers of the font tag recognition neural network with implicit font information to improve the accuracy and predictability of the font tag recognition neural network, which results in improved retrieval of fonts in response to a font tag query. Accordingly, using the enhanced tag probability vectors, the tag-based font recognition system can accurately identify and recommend one or more fonts in response to a font tag query.
-
7.发明申请公开(公告)号：US20200311186A1
公开(公告)日：2020-10-01
申请号：US16369893
申请日：2019-03-29
Applicant: Adobe Inc.
Inventor： Zhaowen Wang , Tianlang Chen , Ning Xu , Hailin Jin
Abstract: The present disclosure relates to a font retrieval system that utilizes a multi-learning framework to develop and improve tag-based font recognition using deep learning neural networks. In particular, the font retrieval system jointly utilizes a combined recognition/retrieval model to generate font affinity scores corresponding to a list of font tags. Further, based on the font affinity scores, the font retrieval system identifies one or more fonts to recommend in response to the list of font tags such that the one or more provided fonts fairly reflect each of the font tags. Indeed, the font retrieval system utilizes a trained font retrieval neural network to efficiently and accurately identify and retrieve fonts in response to a text font tag query.
-
-
-
-
-
-
Search Results
7
records
(took 0.013 seconds)
