-
公开(公告)号：US20200097766A1
公开(公告)日：2020-03-26
申请号：US16577337
申请日：2019-09-20
Applicant: NEC Laboratories America, Inc.
Inventor： Renqiang Min , Bing Bai , Yogesh Balaji
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.
-
公开(公告)号：US20170039183A1
公开(公告)日：2017-02-09
申请号：US15208558
申请日：2016-07-12
Applicant: NEC Laboratories America, Inc.
Inventor： Bing Bai , Yusuf Osmanlioglu
IPC: G06F17/27
CPC classification number: G06F17/2785 , G06F16/313 , G06F17/2775
Abstract: Systems and methods are disclosed for Natural Language Processing (NLP) by applying metric labeling to sentence matching problem by preprocessing a dataset of sentences into objects graphs and label graphs; given an object graph and a label graph, assigning nodes of the object graph to the nodes of the label graph by minimizing an objective function including an assignment cost and a separation cost; and applying the metric labeling to matching two sentences where the objective function value is used as a similarity score between sentences for classification, clustering, or ranking.
Abstract translation: 通过将语法数据集预处理成对象图形和标签图，通过对句子匹配问题应用度量标注，公开了自然语言处理（NLP）的系统和方法; 给定对象图和标签图，通过最小化包括分配成本和分离成本的目标函数，将对象图的节点分配给标签图的节点; 并且将度量标签应用于匹配两个句子，其中目标函数值被用作用于分类，聚类或排名的句子之间的相似性得分。
-
公开(公告)号：US20140236578A1
公开(公告)日：2014-08-21
申请号：US14166273
申请日：2014-01-28
Applicant: NEC Laboratories America, Inc.
Inventor： Christopher Malon , Bing Bai
CPC classification number: G06F17/28 , G06F17/2785 , G06N3/02
Abstract: Systems and methods are disclosed to answer free form questions using recursive neural network (RNN) by defining feature representations at every node of a parse trees of questions and supporting sentences, when applied recursively, starting with token vectors from a neural probabilistic language model; and extracting answers to arbitrary natural language questions from supporting sentences.
Abstract translation: 公开了系统和方法，通过在从神经概率语言模型的令牌向量开始递归应用时，通过定义问题和支持句子的解析树的每个节点上的特征表示，使用递归神经网络（RNN）来回答自由形式问题; 并从支持句子中提取任意自然语言问题的答案。
-
公开(公告)号：US11087174B2
公开(公告)日：2021-08-10
申请号：US16580497
申请日：2019-09-24
Applicant: NEC Laboratories America, Inc.
Inventor： Renqiang Min , Kai Li , Bing Bai , Hans Peter Graf
Abstract: A method is provided for visual inspection. The method includes learning, by a processor, group disentangled visual feature embedding vectors of input images. The input images include defective objects and defect-free objects. The method further includes generating, by the processor using a weight generation network, classification weights from visual features and semantic descriptions. Both the visual features and the semantic descriptions are for predicting defective and defect-free labels. The method also includes calculating, by the processor, a cosine similarity score between the classification weights and the group disentangled visual feature embedding vectors. The method additionally includes episodically training, by the processor, the weight generation network on the input images to update parameters of the weight generation network. The method further includes generating, by the processor using the trained weight generation network, a prediction of a test image as including any of defective objects and defect-free objects.
-
15.发明申请公开(公告)号：US20200097771A1
公开(公告)日：2020-03-26
申请号：US16580497
申请日：2019-09-24
Applicant: NEC Laboratories America, Inc.
Inventor： Renqiang Min , Kai Li , Bing Bai , Hans Peter Graf
Abstract: A method is provided for visual inspection. The method includes learning, by a processor, group disentangled visual feature embedding vectors of input images. The input images include defective objects and defect-free objects. The method further includes generating, by the processor using a weight generation network, classification weights from visual features and semantic descriptions. Both the visual features and the semantic descriptions are for predicting defective and defect-free labels. The method also includes calculating, by the processor, a cosine similarity score between the classification weights and the group disentangled visual feature embedding vectors. The method additionally includes episodically training, by the processor, the weight generation network on the input images to update parameters of the weight generation network. The method further includes generating, by the processor using the trained weight generation network, a prediction of a test image as including any of defective objects and defect-free objects.
-
Patent Agency Ranking
16.发明申请公开(公告)号：US20190122111A1
公开(公告)日：2019-04-25
申请号：US16168244
申请日：2018-10-23
Applicant: NEC Laboratories America, Inc.
Inventor： Renqiang Min , Bing Bai , Alexandru Niculescu-Mizil , Igor Durdanovic , Hans Peter Graf
Abstract: Systems and methods for predicting new relationships in the knowledge graph, including embedding a partial triplet including a head entity description and a relationship or a tail entity description to produce a separate vector for each of the head, relationship, and tail. The vectors for the head entity, relationship, and tail entity can be combined into a first matrix, and adaptive kernels generated from the entity descriptions can be applied to the matrix through convolutions to produce a second matrix having a different dimension from the first matrix. An activation function can be applied to the second matrix to obtain non-negative feature maps, and max-pooling can be used over the feature maps to get subsamples. A fixed length vector, Z, flattens the subsampling feature maps into a feature vector, and a linear mapping method is used to map the feature vectors into a prediction score.
-
公开(公告)号：US20170300632A1
公开(公告)日：2017-10-19
申请号：US15489023
申请日：2017-04-17
Applicant: NEC Laboratories America, Inc.
Inventor： Bing Bai
CPC classification number: G06N20/00 , G06F17/2765 , G16H10/60
Abstract: Systems and methods for document analysis include identifying candidates in a corpus matching a requested expression. String kernel features are extracted for each candidate. Each candidate is classified according to the string kernel features using a machine learning model. A report is generated that identifies instances of the requested expression in the corpus that match a requested class.
-
18.发明申请公开(公告)号：US20170249515A1
公开(公告)日：2017-08-31
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.
-
19.发明申请High-Order Semi-RBMs and Deep Gated Neural Networks for Feature Interaction Identification and Non-Linear Semantic Indexing 审中-公开高阶半RBM和深度门控神经网络，用于特征交互识别和非线性语义索引公开(公告)号：US20140310218A1
公开(公告)日：2014-10-16
申请号：US14243311
申请日：2014-04-02
Applicant: NEC LABORATORIES AMERICA, INC.
Inventor： Renqiang Min , Bing Bai
IPC: G06N3/08
CPC classification number: G06N3/08
Abstract: Systems and method are disclosed for determining complex interactions among system inputs by using semi-Restricted Boltzmann Machines (RBMs) with factorized gated interactions of different orders to model complex interactions among system inputs; applying semi-RBMs to train a deep neural network with high-order within-layer interactions for learning a distance metric and a feature mapping; and tuning the deep neural network by minimizing margin violations between positive query document pairs and corresponding negative pairs.
Abstract translation: 公开了系统和方法，用于通过使用半限制玻尔兹曼机器（RBM）与系统输入之间的复杂相互作用的分解门控交互来确定系统输入之间的复杂相互作用; 应用半RBM来训练具有高阶层内交互的深层神经网络，用于学习距离度量和特征映射; 并通过最小化正查询文档对和对应的负对之间的边缘违规来调整深层神经网络。
-
20.发明申请Semantic Representations of Rare Words in a Neural Probabilistic Language Model 审中-公开神话概率语言模型中罕见词的语义表示公开(公告)号：US20140236577A1
公开(公告)日：2014-08-21
申请号：US14166228
申请日：2014-01-28
Applicant: NEC Laboratories America, Inc.
Inventor： Christopher Malon , Bing Bai
CPC classification number: G06F17/28 , G06F17/2785 , G06N3/02
Abstract: Systems and methods are disclosed for representing a word by extracting n-dimensions for the word from an original language model; if the word has been previously processed, use values previously chosen to define an (n+m) dimensional vector and otherwise randomly selecting m values to define the (n+m) dimensional vector; and applying the (n+m) dimensional vector to represent words that are not well-represented in the language model.
Abstract translation: 公开了通过从原始语言模型中提取单词的n维来表示单词的系统和方法; 如果字已经被处理过，则使用先前选择的值来定义（n + m）维向量，否则随机选择m个值来定义（n + m）维向量; 以及应用（n + m）维向量来表示在语言模型中未被很好表示的单词。
-
-
-
-
-
-
-
-
-
Search Results
20
records
(took 0.019 seconds)
