Abstract: An information processing apparatus includes a processor including hardware. The processor extracts neighboring nodes in two or more different extraction ranges for each node constituting input data of a graph structure. The processor calculates an anomaly score representing a degree of anomaly of the node for each extraction range based on a representation of a combination of the node and the neighboring nodes. The processor records each calculated anomaly score in a storage. The processor selects a maximum anomaly score among the anomaly scores recorded in the storage. The processor determines an anomaly node in the input data of the graph structure based on the selected maximum anomaly score. The processor outputs information of the anomaly node.

Abstract: According to an embodiment, an information processing apparatus includes one or more processors. The one or more processors display a relation display screen including text box images each indicating one of a plurality of text ranges included in a document and a relation image indicating a relation between the plurality of text ranges.

Abstract: In general, according to one embodiment, an information processing apparatus includes a processor. The processor includes hardware configured to extract a sub-graph that is a graph structure operating independently from data of an input graph structure including a plurality of nodes and an edge connecting the nodes, extract a path from the extracted sub-graph, and perform learning of an embedding model using the extracted path. The embedding model performs embedding on data of a graph structure.

Abstract: In general, according to one embodiment, an information processing apparatus includes a processor. The processor includes hardware configured to extract a sub-graph that is a graph structure operating independently from data of an input graph structure including a plurality of nodes and an edge connecting the nodes, extract a path from the extracted sub-graph, and perform learning of an embedding model using the extracted path. The embedding model performs embedding on data of a graph structure.

Abstract: An information processing apparatus includes a processor. The processor receives an input of a graph structure. The graph structure has nodes including text and edge. The processor assigns the nodes to one or more clusters. The processor partitions the text into words. The processor classifies the words into 1) a word representing a subject or target of an operation, 2) a word representing a content or state of the operation, and 3) other words. The processor extracts a frequent word by counting a frequency of occurrence of one or more words classified as the words representing the subject or target of the operation and extracts a frequent word by counting a frequency of occurrence of one or more words classified as the words representing the content or state of the operation, for the respective clusters.

Abstract: A robot system according to an embodiment includes one or more processors. The processors acquire first input data predetermined as data affecting an operation of a robot. The processors calculate a calculation cost of inference processing using a machine learning model for inferring control data used for controlling the robot, on the basis of the first input data. The processors infer the control data by the machine learning model set according to the calculation cost. The processors control the robot using the inferred control data.

Abstract: According to one embodiment, a discrimination apparatus includes a processor. The processor acquires an event indicative of a case that is a processing object, and a document including a plurality of sentences. The processor generates a plurality of subsets in each of which part of the sentences are grouped. The processor discriminates, in regard to each of the subsets, a causal relationship between a sentence included in the subset and the event.

Abstract: An information processing apparatus includes a processor. The processor receives an input of a graph structure. The graph structure has nodes including text and edge. The processor assigns the nodes to one or more clusters. The processor partitions the text into words. The processor classifies the words into 1) a word representing a subject or target of an operation, 2) a word representing a content or state of the operation, and 3) other words. The processor extracts a frequent word by counting a frequency of occurrence of one or more words classified as the words representing the subject or target of the operation and extracts a frequent word by counting a frequency of occurrence of one or more words classified as the words representing the content or state of the operation, for the respective clusters.

Abstract: According to an embodiment, an information processing apparatus includes one or more processors. The one or more processors display a relation display screen including text box images each indicating one of a plurality of text ranges included in a document and a relation image indicating a relation between the plurality of text ranges.

Abstract: A robot system according to an embodiment includes one or more processors. The processors acquire first input data predetermined as data affecting an operation of a robot. The processors calculate a calculation cost of inference processing using a machine learning model for inferring control data used for controlling the robot, on the basis of the first input data. The processors infer the control data by the machine learning model set according to the calculation cost. The processors control the robot using the inferred control data.

Abstract: According to one embodiment, an image processor includes a processor. The processor implements acquiring a first image and first information. The first information indicates a condition of a first projection surface. The first information includes a first color gamut of the first projection surface. The processor implements deriving a second color gamut according to the first color gamut derived by using the first information. The processor implements converting a chromaticity of the first image to obtain a second image. Each pixel of the second image has a color included in the second color gamut. The processor implements generating a first converted image by correcting the second image based on the first color gamut.

Abstract: According to one embodiment, a motion vector detection apparatus includes following units. The layering unit generates layers with different resolutions for each of first and second images. The first extraction unit extracts a space candidate vector. The second extraction unit extracts a time candidate vector. The third extraction unit extracts a layer candidate vector. The determination unit determines a motion vector to be assigned to the target block, based on correlations between the target block and blocks, the blocks being located in a layer which corresponds to the second image and being specified by assigning, to the target block, the space, time, and layer candidate vectors.

Abstract: According to an embodiment, an image processing apparatus includes a corresponding point calculator, a parameter calculator, a corrector, and a detector. The corresponding point calculator calculates corresponding points between an input image and a captured image including a projection surface onto which a projection image is projected. The projection image is generated from the input image. The parameter calculator calculates a correction parameter based on the input image, the captured image, and the corresponding points. The corrector corrects pixel values of the input image using the correction parameter with respect to each color component. The detector detects a change in the projection surface. When the detector detects the change in the projection surface, the corresponding point calculator updates the corresponding points for the change, and the parameter calculator calculates the correction parameter based on the updated corresponding points.

Abstract: According to one embodiment, an image processor includes a processor. The processor implements acquiring a first image and first information. The first information indicates a condition of a first projection surface. The first information includes a first color gamut of the first projection surface. The processor implements deriving a second color gamut according to the first color gamut derived by using the first information. The processor implements converting a chromaticity of the first image to obtain a second image. Each pixel of the second image has a color included in the second color gamut. The processor implements generating a first converted image by correcting the second image based on the first color gamut.

Abstract: According to one embodiment, a controller includes: an analyzer; a determiner; a projection image generator. The analyzer analyzes an environment of a projection surface on which an image is projected, based on a capture image obtained by capturing a region including at least part of the projection surface. The determiner determines a parameter for controlling illumination light illuminating the region based on information regarding the analyzed environment. The projection image generator generates a projection image projected on the region based on the information regarding the environment and acquired image data.

Abstract: According to an embodiment, an image processing device includes a detector, a determiner, and a generator. The detector is configured to detect a real-space position of a viewer. The determiner is configured to determine a first relative position in a virtual space between the viewer and a display surface displaying a stereoscopic image based on the real-space position of the viewer, so that a particular site of the object to be displayed on the display surface faces the viewer in the virtual space. The generator is configured to generate a stereoscopic image by rendering a three-dimensional data of the object based on the first relative position.

Abstract: According to one embodiment, a first extraction unit extracts a first group of pixels having a specific hue from an input image. A second extraction unit extracts a second group of pixels having large distance from a reference axis on a plane defined by a chroma axis and a luminance axis from the first group. A first transform unit executes a plurality of color-transform processing to the second group and obtains a plurality of third groups of pixels as the second group transformed by each color-transform processing. A reliability calculation unit calculates a reliability of each third group. The reliability is larger when pixels of the third group are more located in shape of a straight line on the plane. A selection unit selects a color-transform processing by which the third group has the largest reliability from the plurality of color-transform processing. A second transform unit executes the color-transform processing to the input image to obtain an output image.

Abstract: According to one embodiment, an image processing apparatus includes a scale down unit, a calculation unit, a scale up unit, and a subtraction unit. The scale down unit generates a scaled down image by scaling down a target image. The scaled down image has a size smaller than the target image. The calculation unit calculates a pixel value of a diffuse reflection component of each pixel in the scaled down image, and generates a first diffuse reflection image having the pixel value and the same size as the scaled down image. The scale up unit generates a second diffuse reflection image by scaling up the first diffuse reflection image. The second diffuse reflection image has the same size as the target image. The subtraction unit generates a specular reflection image by subtracting the second diffuse reflection image from the target image.

Abstract: An image processing device includes a hue calculation unit configured to calculate a hue of a pixel included in a target image; an extraction unit configured to extract a first group including a pixel, a hue of which is close to a hue of the target pixel; a chromaticity calculation unit configured to calculate a chromaticity of the pixel included in the first group and that of the target pixel; a diffuse reflection factor calculation unit configured to calculate an estimated diffuse reflection factor by using the chromaticity of the pixel included in the first group and that of the target pixel; and a separation unit configured to separate a diffuse reflection component from a pixel value of the target pixel by using the diffuse reflection factor, the diffuse reflection component representing a component in the pixel value that varies as the diffuse reflection factor varies.

Abstract: An image processing device includes a hue calculation unit configured to calculate a hue of a pixel included in a target image; an extraction unit configured to extract a first group including a pixel, a hue of which is close to a hue of the target pixel; a chromaticity calculation unit configured to calculate a chromaticity of the pixel included in the first group and that of the target pixel; a diffuse reflection factor calculation unit configured to calculate an estimated diffuse reflection factor by using the chromaticity of the pixel included in the first group and that of the target pixel; and a separation unit configured to separate a diffuse reflection component from a pixel value of the target pixel by using the diffuse reflection factor, the diffuse reflection component representing a component in the pixel value that varies as the diffuse reflection factor varies.