Abstract: A steering control device includes a processor configured to execute a reaction force control process. The reaction force control process includes a reaction force torque calculation process of calculating a reaction force torque operation amount. The reaction force torque calculation process includes a deviation compensation calculation process of calculating a deviation-compensating component. The deviation compensation calculation process includes a process of calculating a positional deviation, a process of calculating the deviation-compensating component based on the positional deviation, and a process of switching among a plurality of calculation states for calculating the deviation-compensating component. The process of switching among the calculation states is a process of permitting switching among the calculation states on the condition that a permission condition is met.

Abstract: According to one embodiment, an image processing apparatus 1 includes one or more hardware processors configured to function as an acquisition unit 20A, a pseudo label estimation unit 20B, and a learning unit 20C. The acquisition unit 20A acquires unlabeled training data including an image to which a correct label of an attribute is unassigned. The pseudo-label estimation unit 20B estimates a pseudo-label, which is an estimation result of the attribute of the image of the unlabeled training data, based on an identification target region according to a type of the attribute to be identified by a first learning model 30 to be learned in the image of the unlabeled training data. The learning unit 20C learns the first learning model 30 identifying the attribute of the image by using first labeled training data with the pseudo-label being assigned to the image of the unlabeled training data.

Abstract: According to one embodiment, an apparatus includes a first acquisition unit, a second acquisition unit, an identification unit, and an output unit. The first acquisition unit acquires a query image and a query text relating to a target object. The second acquisition unit acquires candidate images of the target object. The identification unit identifies from the candidate images a positive image containing a region demonstrating a similarity to the query image higher than or equal to a first threshold value, and identifies a position of the region in the positive image. The output unit outputs training data including the positive image, information representing the position of the region, and a correct label.

Abstract: A drug dispensing device includes: a variable cassette configured to dispense any type of drug; a mounting portion, to and from which the variable cassette is mountable and dismountable; a drive controller configured to cause the drug corresponding to the plurality of pieces of prescription data to be dispensed from the set; an allocation processor configured to allocate, based on the plurality of pieces of prescription data, drug information on the drug to be dispensed included in the plurality of pieces of prescription data to the variable cassette or the mounting portion; and a drive controller configured to drive the variable cassette in accordance with a driving condition set in advance in association with the drug information allocated to the variable cassette or the mounting portion by the allocation processor, to thereby dispense from the variable cassette the drug corresponding to the plurality of pieces of prescription data.

Abstract: According to one embodiment, a learning apparatus includes processing circuitry that generates a detection network for detecting an object from an image belonging to a target domain. The processing circuitry computes a detection task loss by supervised learning of the detection network. The processing circuitry computes a domain identification loss by adversarial learning of the detection network. The processing circuitry computes a self-learning loss by self-learning of the detection network. The processing circuitry computes a total loss based on weighted addition of the domain identification loss, the detection task loss and/or the self-learning loss. The processing circuitry updates learning parameters of the detection network by minimizing the total loss.

Abstract: According to an embodiment, a search processing device includes a memory and one or more processors coupled to the memory. The one or more processors are configured to: detect and track moving objects contained in videos by associating the moving objects with each other in a time sequence; receive setting of a search target contained in the videos; calculate a first descriptor and second descriptors, and calculate first degrees of similarity between the first descriptor and the second descriptors, the first descriptor indicating a feature of the search target and the second descriptors indicating features of the moving objects; and receive selection between a first display mode and a second display mode, and display search results corresponding to the search target on a display unit in the selected display mode.

Abstract: An information processing apparatus according to one embodiment includes one or more hardware processors coupled to a memory. The one or more hardware processors acquires pieces of target data of different types. The one or more hardware processors generates element information for each element included in the pieces of the target data. The element information indicates the corresponding element. The one or more hardware processors links, with each other, related pieces of the element information and stores the linked pieces of the element information in a storage device.

Abstract: An image recognition apparatus includes circuitry. The circuitry is configured to input an image of an object captured by a camera. The circuitry is further configured to divide, based on a predetermined positioning point, the image into a plurality of regions, set a process region that includes the respective divided region, and set a rotation of the respective process region so that a positional relationship between up and down of the object in the respective process region matches up. The circuitry is further configured to perform the rotation to the image corresponding to the respective process region and perform a recognition process to the image after rotation.

Abstract: According to one embodiment, a calculation system includes a detector, a combiner, and a duration calculator. The detector refers to a plurality of images of an object imaged from mutually-different angles, detects the object in each of the images, and calculates a provisional position of the object in a coordinate system for each of the images. The coordinate system is prescribed. The combiner calculates a combined position of the object in the coordinate system by using the calculated plurality of provisional positions. The duration calculator refers to process information and a plurality of execution regions and calculates a duration of at least a portion of a plurality of processes based on the combined position and the execution regions. The process information includes information relating to the processes. The execution regions are represented using the coordinate system. The processes are executed in the execution regions.

Abstract: An object count estimation apparatus according to an embodiment of the present disclosure includes a memory and one or more hardware processors coupled to the memory. The one or more hardware processors are configured to: obtain an image; set, based on the image, a local area size representing a unit of object count estimation in the image; and estimate an object count in the image for each local area having the set local area size.

Abstract: According to an embodiment, a calculation device includes a registerer, a first calculator, a receiver, and a second calculator. The registerer registers a plurality of patterns. The first calculator calculates a degree of closeness between the registered patterns. The receiver receives an input pattern. The second calculator calculates a first similarity value between the input pattern and a first registered pattern among the plurality of registered patterns, calculates second similarity values between the input pattern and one or more second registered patterns having a neighbor relationship with the first registered pattern among the plurality of registered patterns, and calculates a combined similarity value in which the first similarity value and the one or more second similarity values are combined.

Abstract: According to one embodiment, an information processing device includes a processor and a memory. The processor determines whether an object included in an image belongs to a first group or not. The processor calculates at least one of first statistical information of an object determined to belong to the first group or second statistical information of an object determined not to belong to the first group. The processor stores at least one of the first statistical or the second statistical information in the memory. The processor executes display processing for at least one of the first statistical information or the second statistical information stored in the memory.

Abstract: According to one embodiment, a progress determination system includes a first acquisition part and a second acquisition part. The first acquisition part acquires area data relating to area values of a plurality of colors from an image of an article, the article relating to a task. The second acquisition part acquires a classification result from a classifier by inputting the area data to the classifier. The classification result indicates a progress amount.

Abstract: According to one embodiment, an information processing device according to an embodiment includes an acquisition unit, a detection unit, and a calculation unit. The acquisition unit acquires image data in which an image of a space where a plurality of specific objects exist is captured. The detection unit detects a position and an orientation of each of the plurality of specific objects included in the image data in the space. The calculation unit calculates, for any evaluation target object of the plurality of specific objects, a close-contact evaluation value indicating a degree of close contact between the evaluation target object and one or a plurality of other specific objects other than the evaluation target object among the plurality of specific objects, based on the position and the orientation of each of the plurality of specific objects.

Abstract: An estimation device including an imager, a detection unit, and an estimation unit. The imager captures an image including a subject. The detection unit detects skeleton information including a first feature point indicating the skeleton of the subject from the image. The estimation unit estimates an action of the subject by determining a position of the first feature point in a rectangle including the subject as a first threshold value based on an installation position of the imager and an imaging range of the imager.

Abstract: According to one embodiment, an apparatus includes a first acquisition unit, a second acquisition unit, an identification unit, and an output unit. The first acquisition unit acquires a query image and a query text relating to a target object. The second acquisition unit acquires candidate images of the target object. The identification unit identifies from the candidate images a positive image containing a region demonstrating a similarity to the query image higher than or equal to a first threshold value, and identifies a position of the region in the positive image. The output unit outputs training data including the positive image, information representing the position of the region, and a correct label.

Abstract: Apparatuses and methods of sharing error correction memory on an interface chip are described. An example apparatus includes: at least one memory chip having a plurality of first memory cells and an interface chip coupled to the at least one memory chip and having a control circuit and a storage area. The control circuit detects one or more defective memory cells of the first memory cells of the at least one memory chip. The control circuit further stores first defective address information of the one or more defective memory cells of the first memory cells into the storage area. The interface chip responds to the first defective address information and an access request to access the storage area in place of the at least one memory chip when the access request has been provided with respect to the one or more defective memory cells of the first memory cells.

Abstract: According to one embodiment, a retrieval device includes one or more processors configured to retrieve a plurality of search image regions from an intended image through image search using a search query, extract a plurality of learning image regions from a learning image used in learning of the image search, through the image search using the search query, and display the search image regions and the learning image regions on a display.

Abstract: The hybrid vehicle is configured to control an engine and a motor, such that the vehicle is driven in one drive mode among a plurality of drive modes including a Charge Depleting or CD mode in which electric power in a power storage device is consumed and a Charge Sustaining or CS mode in which state of charge of the power storage device is sustained. When a sequential position is selected by a driver in an accelerator-off state, the hybrid vehicle narrows a range of a braking torque applicable to the vehicle in the CD mode as the drive mode, compared with in the CS mode as the drive mode.

Abstract: According to one embodiment, a calculation system includes a detector, a combiner, and a duration calculator. The detector refers to a plurality of images of an object imaged from mutually-different angles, detects the object in each of the images, and calculates a provisional position of the object in a coordinate system for each of the images. The coordinate system is prescribed. The combiner calculates a combined position of the object in the coordinate system by using the calculated plurality of provisional positions. The duration calculator refers to process information and a plurality of execution regions and calculates a duration of at least a portion of a plurality of processes based on the combined position and the execution regions. The process information includes information relating to the processes. The execution regions are represented using the coordinate system. The processes are executed in the execution regions.