-
公开(公告)号：US11170256B2
公开(公告)日：2021-11-09
申请号：US16577337
申请日：2019-09-20
Applicant: NEC Laboratories America, Inc.
Inventor： Renqiang Min , Bing Bai , Yogesh Balaji
IPC: G06K9/00 , G06K9/62 , G06N3/08 , G06N3/04 , G06F40/279
Abstract: Systems and methods for processing video are provided. The method includes receiving a text-based description of active scenes and representing the text-based description as a word embedding matrix. The method includes using a text encoder implemented by neural network to output frame level textual representation and video level representation of the word embedding matrix. The method also includes generating, by a shared generator, frame by frame video based on the frame level textual representation, the video level representation and noise vectors. A frame level and a video level convolutional filter of a video discriminator are generated to classify frames and video of the frame by frame video as true or false. The method also includes training a conditional video generator that includes the text encoder, the video discriminator, and the shared generator in a generative adversarial network to convergence.
-
2.发明授权公开(公告)号：US10706310B2
公开(公告)日：2020-07-07
申请号：US15420518
申请日：2017-01-31
Applicant: NEC Laboratories America, Inc.
Inventor： Bing Bai
Abstract: A camera device and camera system for video-based workplace safety is provided. The camera device includes at least one imaging sensor configured to capture one or more video sequences in a workplace environment having a plurality of machines therein. The video camera further includes a processor. The processor is configured to generate a plurality of embedding vectors based on a plurality of observations. The observations include (i) a subject, (ii) an action taken by the subject, and (iii) an object on which the subject is taking the action on. The subject and object are constant. The processor is further configured to generate predictions of one or more future events based on one or more comparisons of at least some of the plurality of embedding vectors. The processor is configured to generate a signal for initiating an action to the at least one of the plurality of machines to mitigate harm.
-
公开(公告)号：US20200097757A1
公开(公告)日：2020-03-26
申请号：US16580199
申请日：2019-09-24
Applicant: NEC Laboratories America, Inc.
Inventor： Renqiang Min , Kai Li , Bing Bai , Hans Peter Graf
Abstract: A computer-implemented method and system are provided for training a model for New Class Categorization (NCC) of a test image. The method includes decoupling, by a hardware processor, a feature extraction part from a classifier part of a deep classification model by reparametrizing learnable weight variables of the classifier part as a combination of learnable variables of the feature extraction part and of a classification weight generator of the classifier part. The method further includes training, by the hardware processor, the deep classification model to obtain a trained deep classification model by (i) learning the feature extraction part as a multiclass classification task, and (ii) episodically training the classifier part by learning a classification weight generator which outputs classification weights given a training image.
-
4.发明申请QUERY GENERATION AND TIME DIFFERENCE FEATURES FOR SUPERVISED SEMANTIC INDEXING 有权查询产生和时间差异特征用于监督语义索引公开(公告)号：US20140122388A1
公开(公告)日：2014-05-01
申请号：US14064949
申请日：2013-10-28
Applicant: NEC Laboratories America, Inc.
Inventor： Bing Bai , Christopher Malon , lain Melvin
IPC: G06N99/00
CPC classification number: G06N99/005 , G06F17/30864
Abstract: Semantic indexing methods and systems are disclosed. One such method is directed to training a semantic indexing model by employing an expanded query. The query can be expanded by merging the query with documents that are relevant to the query for purposes of compensating for a lack of training data. In accordance with another exemplary aspect, time difference features can be incorporated into a semantic indexing model to account for changes in query distributions over time.
Abstract translation: 公开了语义索引方法和系统。 一种这样的方法旨在通过使用扩展查询来训练语义索引模型。 通过将查询与与查询相关的文档合并，可以扩展查询，以补偿缺乏培训数据。 根据另一示例性方面，可以将时差特征并入到语义索引模型中以考虑随时间的查询分布的变化。
-
公开(公告)号：US10706309B2
公开(公告)日：2020-07-07
申请号：US15420476
申请日：2017-01-31
Applicant: NEC Laboratories America, Inc.
Inventor： Bing Bai
Abstract: Systems and methods for training a recursive neural network (RNN) is provided. The method includes generating, by the processor using the RNN, a plurality of embedding vectors based on a plurality of observations, wherein the observations include (i) a subject, (ii) an action taken by the subject, and (iii) an object on which the subject is taking the action on, wherein the subject and object are constant. The method further includes generating, by the processor, predictions of one or more future events based on one or more comparisons of at least some of the plurality of embedding vectors. The method also includes initiating, by the processor, based on the predictions, an action to a hardware device to mitigate expected harm to at least one item selected from the group consisting of the hardware device, another hardware device related to the hardware device, and a person related to the hardware device.
-
Patent Agency Ranking
公开(公告)号：US20170249549A1
公开(公告)日：2017-08-31
申请号：US15420476
申请日：2017-01-31
Applicant: NEC Laboratories America, Inc.
Inventor： Bing Bai
Abstract: Systems and methods for training a recursive neural network (RNN) is provided. The method includes generating, by the processor using the RNN, a plurality of embedding vectors based on a plurality of observations, wherein the observations include (i) a subject, (ii) an action taken by the subject, and (iii) an object on which the subject is taking the action on, wherein the subject and object are constant. The method further includes generating, by the processor, predictions of one or more future events based on one or more comparisons of at least some of the plurality of embedding vectors. The method also includes initiating, by the processor, based on the predictions, an action to a hardware device to mitigate expected harm to at least one item selected from the group consisting of the hardware device, another hardware device related to the hardware device, and a person related to the hardware device.
-
公开(公告)号：US20210173837A1
公开(公告)日：2021-06-10
申请号：US17109781
申请日：2020-12-02
Applicant: NEC Laboratories America, Inc.
Inventor： Christopher Malon , Bing Bai
IPC: G06F16/2452 , G06N3/08 , G06N3/04
Abstract: A computer-implemented method is provided for generating following up questions for multi-hop bridge-type question answering. The method includes retrieving a premise for an input multi-hop bridge-type question. The method further includes assigning, by a three-way neural network based controller, a classification of the premise against the input multi-hop bridge-type question as being any of irrelevant, including a final answer, or including intermediate information. The method also includes outputting the final answer in relation to a first hop of the multi-hop bridge-type question responsive to the classification being including the final answer. The method additionally includes generating a followup question by a neural network and repeating said retrieving, assigning, outputting and generating steps for the followup question, responsive to the classification being including the intermediate information.
-
公开(公告)号：US20180150755A1
公开(公告)日：2018-05-31
申请号：US15811074
申请日：2017-11-13
Applicant: NEC Laboratories America, Inc. , NEC Corporation
Inventor： Bing Bai , Daniel Andrade
CPC classification number: G06N5/04 , G06F9/3838 , G06F9/542 , G06K9/6217 , G06N3/084 , G06N5/022
Abstract: A method is provided that includes accessing a training set of positive and negative event pairs. The method includes calculating (i) positive similarity scores between an input pair of events and the positive event pairs, and (ii) negative similarity scores between the input pair of events and the negative event pairs. The method includes applying a Softmax process to (i) the positive similarity scores to produce an overall positive similarity score for the input pair of events, and (ii) the negative similarity scores to produce an overall negative similarity score for the input pair of events. The method includes calculating the difference between the overall positive and negative similarity scores to obtain a future event prediction score indicating a future occurrence likelihood of at least one of two events forming the input pair of events. The method includes performing an action responsive to the future event prediction score.
-
9.发明授权公开(公告)号：US09336495B2
公开(公告)日：2016-05-10
申请号：US14064949
申请日：2013-10-28
Applicant: NEC Laboratories America, Inc.
Inventor： Bing Bai , Christopher Malon , Iain Melvin
CPC classification number: G06N99/005 , G06F17/30864
Abstract: Semantic indexing methods and systems are disclosed. One such method is directed to training a semantic indexing model by employing an expanded query. The query can be expanded by merging the query with documents that are relevant to the query for purposes of compensating for a lack of training data. In accordance with another exemplary aspect, time difference features can be incorporated into a semantic indexing model to account for changes in query distributions over time.
Abstract translation: 公开了语义索引方法和系统。 一种这样的方法旨在通过使用扩展查询来训练语义索引模型。 通过将查询与与查询相关的文档合并，可以扩展查询，以补偿缺乏培训数据。 根据另一示例性方面，可以将时差特征并入到语义索引模型中以考虑随时间的查询分布的变化。
-
公开(公告)号：US11087184B2
公开(公告)日：2021-08-10
申请号：US16580199
申请日：2019-09-24
Applicant: NEC Laboratories America, Inc.
Inventor： Renqiang Min , Kai Li , Bing Bai , Hans Peter Graf
Abstract: A computer-implemented method and system are provided for training a model for New Class Categorization (NCC) of a test image. The method includes decoupling, by a hardware processor, a feature extraction part from a classifier part of a deep classification model by reparametrizing learnable weight variables of the classifier part as a combination of learnable variables of the feature extraction part and of a classification weight generator of the classifier part. The method further includes training, by the hardware processor, the deep classification model to obtain a trained deep classification model by (i) learning the feature extraction part as a multiclass classification task, and (ii) episodically training the classifier part by learning a classification weight generator which outputs classification weights given a training image.
-
-
-
-
-
-
-
-
-
Search Results
20
records
(took 0.016 seconds)
