-
公开(公告)号：US11750547B2
公开(公告)日：2023-09-05
申请号：US17459161
申请日：2021-08-27
Applicant: Snap Inc.
CPC classification number: H04L51/10 , G06N3/08 , G06V10/40 , G06V10/82 , G06V30/19147 , G06V30/19173 , H04L67/10
Abstract: A caption of a multimodal message (e.g., social media post) can be identified as a named entity using an entity recognition system. The entity recognition system can use an attention-based mechanism that emphasis or de-emphasizes each data type (e.g., image, word, character) in the multimodal message based on each datatypes relevance. The output of the attention mechanism can be used to update a recurrent network to identify one or more words in the caption as being a named entity.
-
公开(公告)号：US20230013116A1
公开(公告)日：2023-01-19
申请号：US17945860
申请日：2022-09-15
Applicant: Snap Inc.
Abstract: A machine learning based system can identify an entity as the likely subject of a multimodal message (e.g., a social media post having a short text phrase overlaid on an image) by creating embeddings for an image of the multimodal message and one or more string embeddings from text of the multimodal message. The embeddings can be weighted to maximize information gain, then recombined and compared against a result embedding database to identify an entity as the subject of the multimodal message.
-
公开(公告)号：US12164603B2
公开(公告)日：2024-12-10
申请号：US17945860
申请日：2022-09-15
Applicant: Snap Inc.
Abstract: A machine learning based system can identify an entity as the likely subject of a multimodal message (e.g., a social media post having a short text phrase overlaid on an image) by creating embeddings for an image of the multimodal message and one or more string embeddings from text of the multimodal message. The embeddings can be weighted to maximize information gain, then recombined and compared against a result embedding database to identify an entity as the subject of the multimodal message.
-
Patent Agency Ranking
公开(公告)号：US11120334B1
公开(公告)日：2021-09-14
申请号：US16125615
申请日：2018-09-07
Applicant: Snap Inc.
Abstract: A caption of a multimodal message (e.g., social media post) can be identified as a named entity using an entity recognition system. The entity recognition system can use an attention-based mechanism that emphasis or de-emphasizes each data type (e.g., image, word, character) in the multimodal message based on each datatypes relevance. The output of the attention mechanism can be used to update a recurrent network to identify one or more words in the caption as being a named entity.
-
公开(公告)号：US12155612B2
公开(公告)日：2024-11-26
申请号：US18358919
申请日：2023-07-25
Applicant: Snap Inc.
Abstract: A caption of a multimodal message (e.g., social media post) can be identified as a named entity using an entity recognition system. The entity recognition system can use an attention-based mechanism that emphasis or de-emphasizes each data type (e.g., image, word, character) in the multimodal message based on each datatypes relevance. The output of the attention mechanism can be used to update a recurrent network to identify one or more words in the caption as being a named entity.
-
公开(公告)号：US20240022532A1
公开(公告)日：2024-01-18
申请号：US18358919
申请日：2023-07-25
Applicant: Snap Inc.
CPC classification number: H04L51/10 , G06N3/08 , G06V30/19147 , G06V30/19173 , G06V10/82 , G06V10/40 , H04L67/10
Abstract: A caption of a multimodal message (e.g., social media post) can be identified as a named entity using an entity recognition system. The entity recognition system can use an attention-based mechanism that emphasis or de-emphasizes each data type (e.g., image, word, character) in the multimodal message based on each datatypes relevance. The output of the attention mechanism can be used to update a recurrent network to identify one or more words in the caption as being a named entity.
-
公开(公告)号：US11475254B1
公开(公告)日：2022-10-18
申请号：US16125275
申请日：2018-09-07
Applicant: Snap Inc.
Abstract: A machine learning based system can identify an entity as the likely subject of a multimodal message (e.g., a social media post having a short text phrase overlaid on an image) by creating embeddings for an image of the multimodal message and one or more string embeddings from text of the multimodal message. The embeddings can be weighted to maximize information gain, then recombined and compared against a result embedding database to identify an entity as the subject of the multimodal message.
-
公开(公告)号：US20210390411A1
公开(公告)日：2021-12-16
申请号：US17459161
申请日：2021-08-27
Applicant: Snap Inc.
Abstract: A caption of a multimodal message (e.g., social media post) can be identified as a named entity using an entity recognition system. The entity recognition system can use an attention-based mechanism that emphasis or de-emphasizes each data type (e.g., image, word, character) in the multimodal message based on each datatypes relevance. The output of the attention mechanism can be used to update a recurrent network to identify one or more words in the caption as being a named entity.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.034 seconds)
