Abstract: According to an embodiment, a learning device includes one or more hardware processors configured to function as a structure search unit. The structure search unit searches for a first learned model structure. The first learned model structure is obtained by selecting search space information in accordance with a target constraint condition of target hardware for each of a plurality of convolution processing blocks included in a base model structure in a neural network model.

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: A defect inspection device includes at least one memory storing instructions and at least one processor.

Abstract: A video encoding apparatus is a video encoding apparatus for subjecting a video image to motion compensated prediction coding, comprising an acquisition module to acquire available blocks of blocks having motion vectors from encoded blocks adjacent to a to-be-encoded block and number of the available blocks, an acquisition/selection module to select one selection block from the encoded available blocks, a selection information encoder to encode selection information specifying the selection block using a code table corresponding to the number of available blocks, and an image encoder to subject the to-be-encoded block to motion compensated prediction coding using a motion vector of the selection block.

Abstract: A learning device according to an embodiment includes one or more hardware processors configured to function as a generation unit, an inference unit, and a training unit. The generation unit generates input data with which an error between a value output from each of one or more target nodes and a preset aimed value is equal to or less than a preset value, the target nodes being in a target layer of a plurality of layers included in a first neural network. The inference unit causes the input data to propagate in a forward direction of the first neural network to generate output data. The training unit trains a second neural network differing from the first neural network by using training data including a set of the input data and the output data.

Abstract: A medical image processing device includes a first position acquirer, a first converter, a first likelihood image generator, and a learner. The first position acquirer is configured to acquire, as first positions, target positions in plural first images. The first converter is configured to convert the first positions to second positions by expanding movement in a second direction intersecting a first direction based on movement over time of the first positions. The first likelihood image generator is configured to generate a first likelihood image showing a distribution of likelihood of the second positions. The learner is configured to output a model using the plural first images and the first likelihood image as training data, and upon receiving part or all of a transparent image, derives a second likelihood image showing a distribution of likelihood indicating probability of the part or all of the transparent image corresponding to the second positions.

Abstract: A method of dividing an input image signal into pixel blocks, and performing inter-prediction on the divided pixel blocks. This method includes selecting predicted motion information from a motion information buffer storing motion information in an encoded region, and predicting motion information of an encoding target block by using the predicted motion information. The method further includes acquiring representative motion information from a plurality of items of motion information in an encoded region in accordance with first information indicating a method of selecting the predicted motion information, thereby obtaining only the representative motion information.

Abstract: A method of dividing an input image signal into pixel blocks, and performing inter-prediction on the divided pixel blocks. This method includes selecting predicted motion information from a motion information buffer storing motion information in an encoded region, and predicting motion information of an encoding target block by using the predicted motion information. The method further includes acquiring representative motion information from a plurality of items of motion information in an encoded region in accordance with first information indicating a method of selecting the predicted motion information, thereby obtaining only the representative motion information.

Abstract: An inference apparatus according to an embodiment of the present disclosure includes a memory and a hardware processor coupled to the memory. The hardware processor is configured to: acquire at least one control parameter of second machine learning model, the second machine learning model having a size smaller than a size of a first machine learning model input to the inference apparatus; change the first machine learning model to the second machine learning model based on the at least one control parameter; and perform inference in response to input data by using the second machine learning model.

Abstract: A method of dividing an input image signal into pixel blocks, and performing inter-prediction on the divided pixel blocks. This method includes selecting predicted motion information from a motion information buffer storing motion information in an encoded region, and predicting motion information of an encoding target block by using the predicted motion information. The method further includes acquiring representative motion information from a plurality of items of motion information in an encoded region in accordance with first information indicating a method of selecting the predicted motion information, thereby obtaining only the representative motion information.

Abstract: A method of dividing an input image signal into pixel blocks, and performing inter-prediction on the divided pixel blocks. This method includes selecting predicted motion information from a motion information buffer storing motion information in an encoded region, and predicting motion information of an encoding target block by using the predicted motion information. The method further includes acquiring representative motion information from a plurality of items of motion information in an encoded region in accordance with first information indicating a method of selecting the predicted motion information, thereby obtaining only the representative motion information.

Abstract: A video encoding apparatus is a video encoding apparatus for subjecting a video image to motion compensated prediction coding, comprising an acquisition module to acquire available blocks of blocks having motion vectors from encoded blocks adjacent to a to-be-encoded block and number of the available blocks, an acquisition/selection module to select one selection block from the encoded available blocks, a selection information encoder to encode selection information specifying the selection block using a code table corresponding to the number of available blocks, and an image encoder to subject the to-be-encoded block to motion compensated prediction coding using a motion vector of the selection block.

Abstract: According to one embodiment, an electronic device includes one or more processors. The one or more processors are configured to acquire a first image and an optical parameter of a camera that captures the first image, the first image including an object, and calculate an area of a partial region of the object by using the first image and the parameter.

Abstract: A method of dividing an input image signal into pixel blocks, and performing inter-prediction on the divided pixel blocks. This method includes selecting predicted motion information from a motion information buffer storing motion information in an encoded region, and predicting motion information of an encoding target block by using the predicted motion information. The method further includes acquiring representative motion information from a plurality of items of motion information in an encoded region in accordance with first information indicating a method of selecting the predicted motion information, thereby obtaining only the representative motion information.

Abstract: According to one embodiment, an image encoding method includes selecting a motion reference block from an encoded pixel block to which an inter prediction is applied. The method includes selecting one or more available blocks from the motion reference block. The method includes selecting a selection block from the available blocks. The method includes generating a predicted image of the encoding target block using motion information of the selection block. The method includes encoding a prediction error between the predicted image and an original image. The method includes encoding selection information specifying the selection block by referring to a code table decided according to a number of the available blocks.

Abstract: According to one embodiment, an image encoding method includes selecting a motion reference block from an already-encoded pixel block. The method includes selecting an available block including different motion information from the motion reference block, and selecting a selection block from the available block. The method includes generating a predicted image of the encoding target block using motion information of the selection block. The method includes encoding a prediction error between the predicted image and an original image. The method includes encoding selection information identifying the selection block by referring to a code table decided according to a number of the available block.

Abstract: According to one embodiment, an image encoding method includes selecting a motion reference block from an encoded pixel block to which an inter prediction is applied. The method includes selecting one or more available blocks from the motion reference block. The method includes selecting a selection block from the available blocks. The method includes generating a predicted image of the encoding target block using motion information of the selection block. The method includes encoding a prediction error between the predicted image and an original image. The method includes encoding selection information specifying the selection block by referring to a code table decided according to a number of the available blocks.

Abstract: According to an embodiment, an encoding device includes an index setting unit and an encoding unit. The index setting unit generates a common index in which reference indices of one or more reference images included in a first index and a second index are sorted in a combination so as not to include a same reference image in accordance with a predetermined scanning order. The first index representing a combination of the one or more reference images referred to by a first reference image. The second index representing a combination of the one or more reference images referred to by a second reference image. The encoding unit encodes the common index.

Abstract: According to an embodiment, an encoding device includes an index setting unit and an encoding unit. The index setting unit generates a common index in which reference indices of one or more reference images included in a first index and a second index are sorted in a combination so as not to include a same reference image in accordance with a predetermined scanning order. The first index representing a combination of the one or more reference images referred to by a first reference image. The second index representing a combination of the one or more reference images referred to by a second reference image. The encoding unit encodes the common index.

Abstract: According to an embodiment, an encoding device includes an index setting unit and an encoding unit. The index setting unit generates a common index in which reference indices of one or more reference images included in a first index and a second index are sorted in a combination so as not to include a same reference image in accordance with a predetermined scanning order. The first index representing a combination of the one or more reference images referred to by a first reference image. The second index representing a combination of the one or more reference images referred to by a second reference image. The encoding unit encodes the common index.