Abstract: An information processing device includes one or more hardware processors configured to function as a detection unit, a collation unit, a voting unit, and a determination unit. The detection unit detects a tracking target region including a tracking target from a video frame. The collation unit collates the tracking target using a collation dictionary that stores identification information for identifying a collation target and acquires identification information for identifying a collation result in the frame of the tracking target from the collation dictionary. The voting unit obtains voting data by voting, for each of tracking targets, the identification information for identifying the collation result obtained for each of frames. The determination unit determines whether to settle collation based on the voting data and outputs identification information for identifying the settled collation result when the collation is settled.

Abstract: According to one embodiment, a learning method of causing a statistical model for outputting a distance to a subject to learn by using an image including the subject as an input is provided. The method includes acquiring an image for learning including a subject having an already known shape, acquiring a first distance to the subject included in the image for learning, from the image for learning, and causing the statistical model to learn by restraining the first distance with the shape of the subject included in the image for learning.

Abstract: According to an embodiment, an information processing apparatus includes one or more hardware processors. The one or more hardware processors update parameters of the first estimation model and the second estimation model so as to optimize a first loss function including a term indicating a difference between the correspondence information and correspondence training data that is training data concerning correspondence between the first pixel and the second pixel, a second loss function including a term concerning a depth, and a third loss function including a term indicating a difference in pixel value between the first pixel and the second pixel whose correspondence is indicated by the correspondence information, and generate the first estimation model and the second estimation model represented by the updated parameters.

Abstract: According to one embodiment, a learning method includes acquiring first multi-view images obtained by capturing a first subject and causing a statistical model to learn, based on first and second bokeh values output from the statistical model by inputting first and second images of the first multi-view images. The causing includes acquiring a first distance from the capture device to a first subject in the first image and a second distance from the capture device to a first subject in the second image, discriminating a relationship in length between the first and second distances, and causing the statistical model to learn such that a relationship in magnitude between the first and second bokeh values is equal to the discriminated relationship.

Abstract: According to one embodiment, an estimation device includes a processor. The processor is configured to acquire first and second images including a same subject continuously captured by a capture device installed in a mobile object, acquire a first distance to the subject included in the acquired first image and uncertainty of the first distance, extract a useful second distance from the acquired first distance based on the acquired uncertainty of the first distance, and estimate a position and orientation of the mobile object when the second image is captured by the capture device based on the acquired first and second images, and the extracted second distance.

Abstract: According to an embodiment, an information processing device includes a detection unit, a cut-out unit, an acquisition unit, and a visual question answering (VQA) processing unit. The detection unit is configured to detect at least one piece of object information including an object area containing an object to be detected and object identification information for identifying the object to be detected, from an image. The cut-out unit is configured to generate at least one object image, by cutting out at least one object area from the image. The acquisition unit is configured to acquire at least one question according to the object identification information. The VQA processing unit is configured to perform a VQA process with the at least one question, for each of the at least one object image.

Abstract: According to one embodiment, a case query apparatus includes a processing circuit. The processing circuit acquires a query condition represented by a query target. The processing circuit acquires a meta query condition represented by a description concerning a viewpoint to focus on when querying a case similar to the query condition. The processing circuit calculates a similarity degree between the query condition and each of a plurality of reference cases represented by a query target. The processing circuit queries a similar reference case similar to the query condition from a viewpoint of the meta query condition, among the plurality of reference cases, based on the similarity degree. The processing circuit presents a query result on the similar reference case.

Abstract: According to one embodiment, an image processing device includes storage and a processor. The storage is configured to store a statistical model generated by learning bokeh that occurs in a first image affected by aberration of an optical system and varies non-linearly in accordance with a distance to a subject in the first image. The processor is configured to acquire a second image affected by the aberration of the optical system, perform color correction on the second image to reduce a number of colors expressed in the second image, and input a third image, obtained by performing the color correction on the second image, into the statistical model and acquire first distance information indicating a distance to a subject in the third image.

Abstract: According to one embodiment, an information processing device includes a memory and one or more processors coupled to the memory. The one or more processors are configured to: receive input of a prompt including a first text and an expected value of an answer related to the first text; predict, upon input of the first text and at least one image, the answer for each of the at least one image by using an AI model that outputs the answer; compute accuracy of the answer from the expected value and the answer; and display, on a display device, display information including at least the prompt, the answer, and the accuracy.

Abstract: According to an embodiment, an information processing device is configured to: estimate, based on target image data, target position data representing an image-capturing position at which the target image data is captured; estimate, based on the target image data, target depth data representing a distance to an object from the image-capturing position; register new image-capturing information including the target image data, the target position data, and the target depth data; display, on a display device, map data representing a map of an environment in which the image data is captured; and display at least one of image data and depth data included in designated image-capturing information that is designated from among a plurality of pieces of image-capturing information, in association with a pixel position in the map data, the pixel position corresponding to position data included in the designated image-capturing information.

Abstract: According to one embodiment, a state determination apparatus includes a processor. The processor acquires a targeted image. The processor acquires a question concerning the targeted image and an expected answer to the question. The processor generates an estimated answer estimated with respect to the question concerning the targeted image using a trained model trained to estimate an answer based on a question concerning an image. The processor determines a state of a target for determination in accordance with a similarity between the expected answer and the estimated answer.

Abstract: According to one embodiment, a learning method includes acquiring first and second images and causing a statistical model to learn based on a first distance output from the statistical model by inputting a first region of the first image, and a second distance output from the statistical model by inputting a second region of the second image. A relationship in size between a third distance to a subject in the first image and a fourth distance to the subject included in the second image is already known. The causing includes causing the statistical model to learn such that a relationship in size between the first and the second distances is equal to a relationship in size between the third and the fourth distances.

Abstract: According to one embodiment, an information processing method includes acquiring a first question corresponding to an input query, estimating an answer to the first question for each of pieces of content to generate a first answer estimation result including the answer to the first question for each of the pieces of content, and classifying the pieces of content into first groups by using the first answer estimation result and generating a first retrieval result indicating content belonging to each of the first groups.

Abstract: According to one embodiment, an image processing device includes first storage and a processor. The first storage is configured to store a first statistical model generated by learning bokeh which occurs in a first image. The processor is configured to acquire a second image, acquire a bokeh value which indicates bokeh occurring in the second image and an uncertainty level which indicates a level of uncertainty for the bokeh value, generate a first bokeh map based on the bokeh value and uncertainty level, and acquire a second bokeh map obtained by interpolating a bokeh value with respect to the first bokeh map. The bokeh value and the uncertainty level are output from the first statistical model by inputting the second image into the first statistical model.

Abstract: According to one embodiment, a machine learning apparatus includes a processing circuit. The processing circuit generates a training sample in a VQA format regarding a VQA task based on a sample in a non-VQA format. The training sample in the VQA format includes a combination of an object, a question text regarding the object and an answer text in response to the question text as elements, and the sample in the non-VQA format includes a combination of an object and a label related to the object as elements. The processing circuit trains a statistical model of the VQA task based on the generated training sample in the VQA format.

Abstract: According to one embodiment, a ranging device includes storage and a processor. The storage is configured to store a statistical model generated by learning a bokeh that occurs in a first image affected by aberration of an optical system of a capture unit. The processor is configured to acquire a second image captured by the capture unit, acquire focus position information when the second image was captured, acquire a bokeh value indicating a bokeh of a subject in the second image, which is output from the statistical model by inputting the acquired second image to the statistical model, and convert the acquired bokeh value into a distance to the subject based on the acquired focus position information.

Abstract: According to one embodiment, a learning method for causing a statistical model to learn is provided. The statistical model is generated by learning a bokeh caused in a first image captured in a first domain in accordance with a distance to a first subject included in the first image, the method includes acquiring a plurality of second images by capturing a second subject from multiple viewpoints in a second domain other than the first domain, and causing the statistical model to learn using the second images.

Abstract: According to one embodiment, a ranging device includes storage and a processor. The storage is configured to store a statistical model generated by learning a bokeh that occurs in a first image affected by aberration of an optical system of a capture unit. The processor is configured to acquire a second image captured by the capture unit, acquire focus position information when the second image was captured, acquire a bokeh value indicating a bokeh of a subject in the second image, which is output from the statistical model by inputting the acquired second image to the statistical model, and convert the acquired bokeh value into a distance to the subject based on the acquired focus position information.

Abstract: According to one embodiment, a case query apparatus includes a processing circuit. The processing circuit acquires a query condition represented by a query target. The processing circuit acquires a meta query condition represented by a description concerning a viewpoint to focus on when querying a case similar to the query condition. The processing circuit calculates a similarity degree between the query condition and each of a plurality of reference cases represented by a query target. The processing circuit queries a similar reference case similar to the query condition from a viewpoint of the meta query condition, among the plurality of reference cases, based on the similarity degree. The processing circuit presents a query result on the similar reference case.

Abstract: According to one embodiment, an estimation device includes a processor. The processor is configured to acquire first and second images including a same subject continuously captured by a capture device installed in a mobile object, acquire a first distance to the subject included in the acquired first image and uncertainty of the first distance, extract a useful second distance from the acquired first distance based on the acquired uncertainty of the first distance, and estimate a position and orientation of the mobile object when the second image is captured by the capture device based on the acquired first and second images, and the extracted second distance.