Nippon Telegraph and Telephone Corporation

Go Irie

Kunio Kashino

Kaoru Hiramatsu

Takahito Kawanishi

Xiaomeng Wu

Takashi Satou

Kota Hidaka

Yukinobu Taniguchi

Shinya Nakajima

Kiyoharu Aizawa

Hidehisa Nagano

Masataka Yamaguchi

Kazuhiko Sumi

Seiya Ito

Yu Mizutsumi

Krishna Onkar

A search apparatus for searching media data for a target region that matches query data includes a first feature extraction unit configured to extract a first feature vector from the query data using a first trained neural network; a second feature extraction unit configured to obtain a first region from the media data and extract a second feature vector from the first region using a second trained neural network; a localization unit configured to determine a candidate for the target region using a third trained neural network, based on the first feature vector, the second feature vector, and the first region or a location of the first region; and a control unit configured to repeat the operations of the second feature extraction unit and the localization unit until a predetermined condition is satisfied, by using the determined candidate for the target region as the first region to be used by the second feature extraction unit.

Search apparatus, training apparatus, search method, training method, and program

An acquiring unit of a depth estimation apparatus acquires an input image. In addition, a depth map generating unit inputs the input image acquired by the acquiring unit into a depth estimator for generating, from an image, a depth map in which a depth of a space that appears on the image is imparted to each pixel of the image, and generates an estimated depth map that represents a depth map corresponding to the input image. The depth estimator is a model having been learned in advance so as to reduce, with respect to each error between a depth of the estimated depth map and a depth of a correct-answer depth map that presents the depth map of a correct answer, a value of a loss function set such that a degree of increase of a loss value with respect to a pixel at which the error is larger than a threshold is smaller than a degree of increase of a loss value with respect to a pixel at which the error is equal to or smaller than the threshold.

Depth estimation device, depth estimation model learning device, depth estimation method, depth estimation model learning method, and depth estimation program

An image identification device can be trained to identify classes with high accuracy even in cases with a small number of learning images. Using a first loss function for outputting a value that is smaller the greater a similarity is between the belongingness probability of each class for the image output by the image identification device and a given teacher belongingness probability of the image, and a second loss function for, in a case in which the image input into the image identification device is an actual image, outputting a value that is smaller the smaller the estimated authenticity probability, which expresses how artificial the input image is, output by the image identification device is and for, in a case in which the image input into the image identification device is an artificial image, outputting a value that is smaller the greater the estimated authenticity probability output by the image identification device is, iterative learning of a parameter of the image identification device is executed to reduce the value of the first loss function and the value of the second loss function.

Image recognition learning device, image recognition device, method and program

The purpose of the present invention is to enable learning of a neural network for extracting features of images having high robustness from an undiscriminating image region while minimizing the number of parameters of a pooling layer. A parameter learning unitlearns parameters of each layer in a convolutional neural network configured by including a fully convolutional layer for performing convolution of an input image to output a feature tensor of the input image, a weighting matrix estimation layer for estimating a weighting matrix indicating a weighting of each element of the feature tensor, and a pooling layer for extracting a feature vector of the input image based on the feature tensor and the weighting matrix. The parameter learning unitlearns the parameters such that a loss function value obtained by calculating a loss function expressed by using a distance between a first feature vector of a first image and a second feature vector of a second image, which are relevant images and are obtained by applying the convolutional neural network, becomes smaller.

Image feature learning device, image feature learning method, image feature extraction device, image feature extraction method, and program

It is possible to receive a point cloud as input and perform shape completion with high accuracy. A shape completion unit inputs an input point cloud and a class identification feature output by a class identification unit to a generator that is learned in advance and generates a shape completion point cloud that is to complete a point cloud and is a set of three-dimensional points by receiving, as input, the point cloud and the class identification feature, gaining an integration result obtained by integrating a global feature that is a global feature based on local features extracted from respective points of the point cloud with the class identification feature, and convoluting the integration result, and outputs the shape completion point cloud that is to complete the input point cloud.

Shape supplementation device, shape supplementation learning device, method, and program

Low-dimensional feature values with which semantic factors of content are ascertained are generated from relevance between sets of two types of content. Based on a relation indicator indicating a pair of groups indicating which groups are related to first types of content groups among second types of content groups, an initial feature value extracting unitextracts initial feature values of the first type of content and the second type of content. A content pair selecting unitselects a content pair by selecting one first type of content and one second type of content from each pair of groups indicated by the relation indicator. A feature value conversion function generating unitgenerates feature conversion functionsof converting the initial feature values into low-dimensional feature values based on the content pair selected from each pair of groups.

Feature amount generation method, feature amount generation device, and feature amount generation program

Clustering can be performed using a self-expression matrix in which noise is suppressed. A self-expression matrix is calculated that minimizes an objective function that is for obtaining, from among matrices included in a predetermined matrix set, a self-expression matrix whose elements are linear weights when data points in a data set are expressed by linear combinations of points, the objective function being represented by a term for obtaining the residual between data points in the data set and data points expressed by linear combinations of points using the self-expression matrix, a first regularization term that is multiplied by a predetermined weight and is for reducing linear weights of the data points that have a large Euclidean norm in the self-expression matrix, and a second regularization term for the self-expression matrix. A similarity matrix defined by the calculated self-expression matrix is then calculated. Then a clustering result is obtained by clustering the data set based on the similarity matrix.

Clustering device, method and program

An audio feature is extracted from audio signal data for each analysis frame and stored in a storage part. Then, the audio feature is read from the storage part, and an emotional state probability of the audio feature corresponding to an emotional state is calculated using one or more statistical models constructed based on previously input learning audio signal data. Then, based on the calculated emotional state probability, the emotional state of a section including the analysis frame is determined.

Emotion detecting method, emotion detecting apparatus, emotion detecting program that implements the same method, and storage medium that stores the same program

Growing community of inventors

Tokyo, Japan

Go Irie