-
公开(公告)号：US12026463B2
公开(公告)日：2024-07-02
申请号：US18323900
申请日：2023-05-25
Applicant: Snap Inc.
Inventor： Vitor Rocha de Carvalho , Luis Carlos Dos Santos Marujo , Leonardo Ribas Machado das Neves
IPC: G06F40/263 , G06F40/284 , G06F40/295 , G06N20/00
CPC classification number: G06F40/263 , G06F40/284 , G06F40/295 , G06N20/00
Abstract: Systems, devices, media, and methods are presented for generating a language detection model of a language analysis system. The systems and methods access a set of messages including text elements and convert the set of messages into a set of training messages. The set of training messages are configured for training a language detection model. The systems and methods train a classifier based on the set of training messages. The classifier has a set of features representing word frequency, character frequency, and a character ratio. The systems and methods generate a language detection model based on the classifier and the set of features.
-
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.
-
公开(公告)号：US20210256213A1
公开(公告)日：2021-08-19
申请号：US17306010
申请日：2021-05-03
Applicant: Snap Inc.
Inventor： Di Lu , Leonardo Ribas Machado das Neves , Vitor Rocha de Carvalho , Ning Zhang
IPC: G06F40/295 , G06F40/30 , G06N3/08 , G06N20/00
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 a visual attention based mechanism to generate a visual context representation from an image and caption. The system can use the visual context representation to identify one or more terms of the caption as a named entity.
-
Patent Agency Ranking
公开(公告)号：US12056454B2
公开(公告)日：2024-08-06
申请号：US18201075
申请日：2023-05-23
Applicant: Snap Inc.
Inventor： Di Lu , Leonardo Ribas Machado das Neves , Vitor Rocha de Carvalho , Ning Zhang
IPC: G06F40/295 , G06F40/30 , G06N3/08 , G06N20/00
CPC classification number: G06F40/295 , G06F40/30 , G06N3/08 , G06N20/00
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 a visual attention based mechanism to generate a visual context representation from an image and caption. The system can use the visual context representation to identify one or more terms of the caption as a named entity.
-
公开(公告)号：US20240037141A1
公开(公告)日：2024-02-01
申请号：US18378376
申请日：2023-10-10
Applicant: Snap Inc.
Inventor： Xiaoyu Wang , Ning Xu , Ning Zhang , Vitor Rocha de Carvalho , Jia Li
IPC: G06F16/58 , G06T1/00 , G06N3/08 , G06F16/9038 , G06N3/04 , G06F18/24 , G06N3/045 , H04N23/63 , G06V10/764 , G06V10/82 , G06V10/75
CPC classification number: G06F16/5866 , G06T1/0007 , G06N3/08 , G06F16/9038 , G06N3/04 , G06F18/24 , G06N3/045 , H04N23/63 , G06V10/764 , G06V10/82 , G06V10/751 , G06N5/022
Abstract: Systems, methods, devices, media, and computer readable instructions are described for local image tagging in a resource constrained environment. One embodiment involves processing image data using a deep convolutional neural network (DCNN) comprising at least a first subgraph and a second subgraph, the first subgraph comprising at least a first layer and a second layer, processing, the image data using at least the first layer of the first subgraph to generate first intermediate output data; processing, by the mobile device, the first intermediate output data using at least the second layer of the first subgraph to generate first subgraph output data, and in response to a determination that each layer reliant on the first intermediate data have completed processing, deleting the first intermediate data from the mobile device. Additional embodiments involve convolving entire pixel resolutions of the image data against kernels in different layers if the DCNN.
-
公开(公告)号：US20230297775A1
公开(公告)日：2023-09-21
申请号：US18323900
申请日：2023-05-25
Applicant: Snap Inc.
Inventor： Vitor Rocha de Carvalho , Luis Carlos Dos Santos Marujo , Leonardo Ribas Machado das Neves
IPC: G06F40/263 , G06N20/00 , G06F40/284 , G06F40/295
CPC classification number: G06F40/263 , G06N20/00 , G06F40/284 , G06F40/295
Abstract: Systems, devices, media, and methods are presented for generating a language detection model of a language analysis system. The systems and methods access a set of messages including text elements and convert the set of messages into a set of training messages. The set of training messages are configured for training a language detection model. The systems and methods train a classifier based on the set of training messages. The classifier has a set of features representing word frequency, character frequency, and a character ratio. The systems and methods generate a language detection model based on the classifier and the set of features.
-
公开(公告)号：US11687720B2
公开(公告)日：2023-06-27
申请号：US17306010
申请日：2021-05-03
Applicant: Snap Inc.
Inventor： Di Lu , Leonardo Ribas Machado das Neves , Vitor Rocha de Carvalho , Ning Zhang
IPC: G06F40/295 , G06N20/00 , G06N3/08 , G06F40/30
CPC classification number: G06F40/295 , G06F40/30 , G06N3/08 , G06N20/00
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 a visual attention based mechanism to generate a visual context representation from an image and caption. The system can use the visual context representation to identify one or more terms of the caption as a named entity.
-
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.
-
-
-
-
-
-
-
-
-
Search Results
20
records
(took 0.021 seconds)
