Abstract: According to the present disclosure, a weight parameter of a neural network is divided into a plurality of portions having a certain size and approximation is individually performed on the portions using a weighted sum of the codebook vectors.

Abstract: A minute bubble generator includes a flow path member including a flow path allowing a liquid to pass therethrough; and a colliding part provided in the flow path and generating minute bubbles in the liquid passing through the flow path by locally reducing a cross sectional area of the flow path. The colliding part is formed integrally with the flow path member and is provided closer to an upstream end or a downstream end relative to a lengthwise center of the flow path.

Abstract: A result of recognition processing of a convolutional neural network is acquired using recognition object data including information of a recognition object, as an input. A region of interest for the recognition object data and/or an intermediate layer output of the convolutional neural network is set. Detail recognition processing is performed for the recognition object data and/or the intermediate layer output in the region of interest. Integration processing of a result of the detail recognition processing and the intermediate layer output is performed. A result of the integration processing is input as the intermediate layer output to the convolutional neural network. A result of the recognition processing is output.

Abstract: It is an object of the present invention to provide a user interface which facilitates confirmation of an area in an image and associated data corresponding to the area without requiring user's complicated operations. To achieve the object, an information processing apparatus comprises: an obtaining unit configured to obtain a first image including a plurality of objects, and information related to respective positions of the plurality of objects in the first image; and a determining unit configured to determine a position in case of shifting and displaying a second image indicating the plurality of objects with respect to the first image, based on the obtained positions of the plurality of objects.

Abstract: A result of recognition processing of a convolutional neural network is acquired using recognition object data including information of a recognition object, as an input. A region of interest for the recognition object data and/or an intermediate layer output of the convolutional neural network is set. Detail recognition processing is performed for the recognition object data and/or the intermediate layer output in the region of interest. Integration processing of a result of the detail recognition processing and the intermediate layer output is performed. A result of the integration processing is input as the intermediate layer output to the convolutional neural network. A result of the recognition processing is output.

Abstract: It is an object of the present invention to provide a user interface which facilitates confirmation of an area in an image and associated data corresponding to the area without requiring user's complicated operations. To achieve the object, an information processing apparatus comprises: an obtaining unit configured to obtain a first image including a plurality of objects, and information related to respective positions of the plurality of objects in the first image; and a determining unit configured to determine a position in case of shifting and displaying a second image indicating the plurality of objects with respect to the first image, based on the obtained positions of the plurality of objects.

Abstract: An image processing apparatus comprising: a learning unit configured to perform learning of a discriminator based on an image feature amount in a first image and a class of the first image defined by a first granularity; an evaluation unit configured to evaluate an image feature amount in a second image whose class is known by the discriminator after the learning; and a control unit configured to control the learning unit to, in a case in which the evaluation by the evaluation unit is that a predetermined criterion is not satisfied, perform the learning of the discriminator based on the image feature amount in the first image and a class of the first image defined by a second granularity coarser than the first granularity.

Abstract: An information processing apparatus includes a learning unit configured to learn a plurality of multi-layer neural networks configured to carry out a plurality of tasks, a generation unit configured to generate a shared layer candidate at a predetermined layer between or among the plurality of multi-layer neural networks, a first relearning unit configured to relearn the plurality of multi-layer neural networks in a structure using the shared layer candidate, and a determination unit configured to determine whether to share the shared layer candidate at the predetermined layer with respect to each of the plurality of tasks based on an evaluation of the relearning.

Abstract: An information processing apparatus includes a first detection unit configured to detect an event from a captured image through first detection processing, a resource management unit configured to allocate a resource allocated to predetermined processing to second detection processing different from the first detection processing in a case where the event is detected through the first detection processing, and a second detection unit configured to detect an event from the captured image through the second detection processing using the resource allocated by the resource management unit.

Abstract: An image processing apparatus includes: an acquisition unit configured to acquire a plurality of images each capturing an identical target and having a different attribute; a derivation unit configured to derive features from the plurality of images, using a first neural network; an integration unit configured to integrate the features derived from the plurality of images; and a generation unit configured to generate a higher quality image than the plurality of images from the feature integrated by the integration unit, using a second neural network.

Abstract: In the present disclosure, an image parameter of an input image is changed, features is extracted from each of a plurality of generated images, a category of each region is determined based on the features in each image, and the results are integrated.

Abstract: A minute bubble generator includes a flow path member including a flow path allowing a liquid to pass therethrough; and a colliding part provided in the flow path and generating minute bubbles in the liquid passing through the flow path by locally reducing a cross sectional area of the flow path. The colliding part is formed integrally with the flow path member and is provided closer to an upstream end or a downstream end relative to a lengthwise center of the flow path.

Abstract: A result of recognition processing of a convolutional neural network is acquired using recognition object data including information of a recognition object, as an input. A region of interest for the recognition object data and/or an intermediate layer output of the convolutional neural network is set. Detail recognition processing is performed for the recognition object data and/or the intermediate layer output in the region of interest. Integration processing of a result of the detail recognition processing and the intermediate layer output is performed. A result of the integration processing is input as the intermediate layer output to the convolutional neural network. A result of the recognition processing is output.

Abstract: It is an object of the present invention to provide a user interface which facilitates confirmation of an area in an image and associated data corresponding to the area without requiring user's complicated operations. To achieve the object, an information processing apparatus comprises: an obtaining unit configured to obtain a first image including a plurality of objects, and information related to respective positions of the plurality of objects in the first image; and a determining unit configured to determine a position in case of shifting and displaying a second image indicating the plurality of objects with respect to the first image, based on the obtained positions of the plurality of objects.

Abstract: An image processing apparatus comprising: a learning unit configured to perform learning of a discriminator based on an image feature amount in a first image and a class of the first image defined by a first granularity; an evaluation unit configured to evaluate an image feature amount in a second image whose class is known by the discriminator after the learning; and a control unit configured to control the learning unit to, in a case in which the evaluation by the evaluation unit is that a predetermined criterion is not satisfied, perform the learning of the discriminator based on the image feature amount in the first image and a class of the first image defined by a second granularity coarser than the first granularity.

Abstract: To appropriately superimpose and display a virtual object on an image of a real space, an information processing apparatus according to exemplary embodiment of the present invention determines the display position of the virtual object based on information indicating an allowable degree of superimposition of a virtual object on each real object in the image of the real space, and a distance from a real object for which a virtual object is to be displayed in association with the real object.

Abstract: In the present disclosure, an image parameter of an input image is changed, features is extracted from each of a plurality of generated images, a category of each region is determined based on the features in each image, and the results are integrated.

Abstract: An image processing apparatus includes: an acquisition unit configured to acquire a plurality of images each capturing an identical target and having a different attribute; a derivation unit configured to derive features from the plurality of images, using a first neural network; an integration unit configured to integrate the features derived from the plurality of images; and a generation unit configured to generate a higher quality image than the plurality of images from the feature integrated by the integration unit, using a second neural network.

Abstract: According to the present disclosure, a weight parameter of a neural network is divided into a plurality of portions having a certain size and approximation is individually performed on the portions using a weighted sum of the codebook vectors.

Abstract: An information processing apparatus includes a learning unit configured to learn a plurality of multi-layer neural networks configured to carry out a plurality of tasks, a generation unit configured to generate a shared layer candidate at a predetermined layer between or among the plurality of multi-layer neural networks, a first relearning unit configured to relearn the plurality of multi-layer neural networks in a structure using the shared layer candidate, and a determination unit configured to determine whether to share the shared layer candidate at the predetermined layer with respect to each of the plurality of tasks based on an evaluation of the relearning.