Nec Laboratories America, Inc.

Nec Corporation

Nec Laboratories Amercia, Inc.

Bing Bai

Yanjun Qi

Jason Edward Weston

Renqiang Min

Ronan Collobert

Xi Chen

Hans Peter Graf

Iain Melvin

Kai Li

David Grangier

Christopher Malon

Xia Ning

Koray Kavukcuoglu

Akshat Aranya

Yogesh Balaji

Pavel Kuksa

Ronan Collorbert

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.

Multi-scale text filter conditioned generative adversarial networks

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.

Deep group disentangled embedding and network weight generation for visual inspection

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.

Network reparameterization for new class categorization

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.

Recursive neural networks on future event prediction

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.

Video camera device and system using recursive neural networks for future event prediction

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.

Query generation and time difference features for supervised semantic indexing

Methods and systems for document classification include embedding n-grams from an input text in a latent space, embedding the input text in the latent space based on the embedded n-grams and weighting said n-grams according to spatial evidence of the respective n-grams in the input text, classifying the document along one or more axes, and adjusting weights used to weight the n-grams based on the output of the classifying step.

Document classification with weighted supervised n-gram embedding

The method and apparatus for discriminative natural language parsing, uses a deep convolutional neural network adapted for text and a structured tag inference in a graph. In the method and apparatus, a trained recursive convolutional graph transformer network, formed by the deep convolutional neural network and the graph, predicts 'levels' of a parse tree based on predictions of previous levels.

Method and apparatus for full natural language parsing

Systems and methods are disclosed to perform relation extraction in text by applying a convolution strategy to determine a kernel between sentences; applying one or more semi-supervised strategies to the kernel to encode syntactic and semantic information to recover a relational pattern of interest; and applying a classifier to the kernel to identify the relational pattern of interest in the text in response to a query.

Systems and methods for semi-supervised relationship extraction

Systems and methods are disclosed to perform preference learning on a set of documents includes receiving raw input features from the set of documents stored on a data storage device; generating polynomial combinations from the raw input features; generating one or more parameters; applying the parameters to one or more classifiers to generate outputs; determining a loss function and parameter gradients and updating parameters determining one or more sparse regularizing terms and updating the parameters; and expressing that one document is preferred over another in a search query and retrieving one or more documents responsive to the search query.

System and methods for finding hidden topics of documents and preference ranking documents

A cell phone having distributed artificial intelligence services is provided. The cell phone includes a neural network for performing a first pass of object recognition on an image to identify objects of interest therein based on one or more criterion. The cell phone also includes a patch generator for deriving patches from the objects of interest. Each of the patches includes a portion of a respective one of the objects of interest. The cell phone additionally includes a transmitter for transmitting the patches to a server for further processing in place of an entirety of the image to reduce network traffic.

Distributed artificial intelligence services on a cell phone

A method and system for searching for information contained in a database of documents each includes an offline part and an online part. The offline part includes predicting, in a first computer process, semantic data for sentences of the documents contained in the database and storing this data in a database. The online part includes querying the database for information with a semantically-sensitive query, predicting, in a real time computer process, semantic data for the query, and determining, in a second computer process, a matching score against all the documents in the database, which incorporates the semantic data for the sentences and the query.

Semantic search via role labeling

A system and method for determining a similarity between a document and a query includes providing a frequently used dictionary and an infrequently used dictionary in storage memory. For each word or gram in the infrequently used dictionary, n words or grams are correlated from the frequently used dictionary based on a first score. Features for a vector of the infrequently used words or grams are replaced with features from a vector of the correlated words or grams from the frequently used dictionary when the features from a vector of the correlated words or grams meet a threshold value. A similarity score is determined between weight vectors of a query and one or more documents in a corpus by employing the features from the vector of the correlated words or grams that met the threshold value.

Growing community of inventors

Princeton Junction, NJ, United States of America

Bing Bai