Abstract: An information processing apparatus of the present invention correctly determines in advance whether interference occurs between an object around a target workpiece to be grasped, and a hand. The information processing apparatus includes an obtaining unit configured to obtain a range image of a space including a plurality of workpieces, an identification unit configured to identify, from the obtained range image, an area of the target workpiece to be grasped among the plurality of workpieces, an interference determination unit configured to determine whether interference occurs between an area included in the range image and a grasping unit configured to grasp the target workpiece, and an output unit configured to output, based on a result of the interference determination by the interference determination unit, a result of determination as to whether interference occurs between an area excluding the area of the target workpiece and the grasping unit.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for classifying an input image utilizing a classification model conditioned by a generative model and/or self-supervision. For example, the disclosed systems can utilize a generative model to generate a reconstructed image from an input image to be classified. In turn, the disclosed systems can combine the reconstructed image with the input image itself. Using the combination of the input image and the reconstructed image, the disclosed systems utilize a classification model to determine a classification for the input image. Furthermore, the disclosed systems can employ self-supervised learning to cause the classification model to learn discriminative features for better classifying images of both known classes and open-set categories.

Abstract: A method for processing a plurality of radiation protective garments includes receiving a plurality of radiation protective garments from a customer, scanning an identification tag of each received radiation protective garment to identify electronic identification data of each radiation protective garment, and automatically identifying a subset of the radiation protective garments that require performance testing by using the identification data to access a file history of each scanned radiation protective garment, the file history including a performance testing schedule. The method further includes using an x-ray scanning system to scan the subset of the radiation protective garments and to generate x-ray image data, automatically updating the file histories of the subset of the radiation protective garments to include the corresponding x-ray image data, and identifying defects in the corresponding radiation protective garment based on the x-ray image data.

Abstract: Provided is a neural-network-based classification method, including: generating, by a neural network, one or more score vectors corresponding to one or more samples respectively; determining a first subset of the one or more samples according to the one or more score vectors and a first decision threshold, wherein the first subset is associated with a first class; and selecting samples to be re-examined from the one or more samples according to the first subset.

Abstract: A processor system comprises a memory organizer unit and a matrix computing unit. The memory organizer unit is configured to receive a request for a three-dimensional data of a convolutional neural network layer. The requested three-dimensional data is obtained from a memory. The obtained three-dimensional data is rearranged in an optimized linear order and the rearranged data in the optimized linear order is provided to the matrix computing unit. The matrix computing unit is configured to perform at least a portion of a three-dimensional convolution using at least a portion of the provided rearranged data in the optimized linear order.

Abstract: A processing unit recognizes an object based on image data. An object recognition unit identifies the object based on the image data. A conversion unit is configured as a neural network provided as an upstream stage of the object recognition unit. The conversion unit converts a first image IMG acquired by the camera into a second image, and inputs the second image to the object recognition unit.

Abstract: Systems and methods are provided herein for processing digital content. A registry includes a set of common registry identifiers used to classify metadata. Further, an interchange layer and registry classification service: receives metadata derived from digital content in a content file; and classifies the metadata, by associating the metadata with one of the common registry identifiers, based upon a classification from a set of classification rules that is associated with a metadata type of the metadata.

Abstract: An information processing device that executes calculation of a neural network, includes a memory; and a processor coupled to the memory and the processor configured to: set a division position for quantization of a variable to be used for the calculation so that a quantization error based on a difference between the variable before the quantization and the variable after the quantization is reduced; and quantize the variable based on the division position set.

Abstract: An apparatus and a method image classification based positioning are provided. For image-based positioning to predict a camera pose from image data, a positioning apparatus obtains a prediction result indicating which cell the image data belongs to among cells constituting a space for positioning from a classification network that processes the image data based on a pre-learned weight. The positioning apparatus obtains map information on the space for positioning by using a cell index selected based on the prediction result, and the map information includes minimum and maximum values of coordinates constituting a cell for each cell index, and a cell size. A position of the image data based on the map information is calculated to output a corresponding camera pose.

Abstract: Methods, computer program products and/or systems are provided that perform the following operations: obtaining a first graph comprising first nodes representing first entities and first edges representing relationships between first entities, the first nodes being associated with first entity attributes descriptive of the first entities represented by the first nodes, the first edges being associated with first edge attributes descriptive of the relationships represented by the first edges; determining a first subgraph for a certain node of the first nodes of the first graph, the first subgraph including the certain node and at least one neighboring node of the certain node; and determining a data quality issue regarding the certain node based, at least in part, on applying one or more applicable rules of a set of data quality rules to first entity attribute values and first edge attribute values of the first subgraph.

Abstract: An adaptive processing method for new scenes in autonomous driving, comprising: obtaining scene data corresponding to new scene of vehicle driving, wherein the scene data describes vehicles state and driving operations in the new scene; obtaining a test set of the new scene based on processing the scene data by a preset distribution; updating parameters of a pre-training model by inputting the test set, and obtaining a scene model adapted to the new scene based on gradient iteration of general model parameters of the pre-training model, wherein the scene model is configured to output an autonomous driving strategy for the vehicle in the new scene. Therefore, the autonomous driving vehicle transforms a new scene to a known scene, and no longer be troubled by unpredictable new scenes, and greatly enhance the reliability and stability of autonomous driving.

Abstract: Systems and methods of improved network analytics are disclosed. A system may determine feature propagation in a network of nodes of a graph database. The system may compute, at scale, datasets having complex relationships using graph analysis to determine network effects of entities in a network of entities stored in a graph database. The system may identify entities of interest, which may be associated with a quantitative feature value. The system may compute paths from an entity to the entities of interest, centrality metrics for entities in each of the paths, and path lengths to determine network effects of the entity of interests on the entity. The system may use the computed network effects, taking into account types of relationships between entities in the paths, to determine scaled quantitative feature values for the entity that is subject to the network effects of the entities of interest.

Abstract: Registered, first unregistered, and second unregistered encodings are generated for registered images of content, first unregistered images of the content, and second unregistered images of different content, respectively. First and second distance matrices having rows respectively corresponding to the first and second unregistered encodings are generated based on the registered encodings and the first and second unregistered encodings, respectively. A statistic is selected having a greatest difference between first and second distance vectors having values corresponding to the rows of the first and second distance matrices, respectively. Whether content of a new unregistered image corresponds to the content of the registered images is assessed by using the selected statistic.

Abstract: A monitor is installed in an eye of a robot, and an eye image is displayed on the monitor. The robot extracts a feature quantity of an eye of a user from a filmed image of the user. The feature quantity of the eye of the user is reflected in the eye image. For example, a feature quantity is a size of a pupillary region and a pupil image, and a form of an eyelid image. Also, a blinking frequency or the like may also be reflected as a feature quantity. Familiarity with respect to each user is set, and which user's feature quantity is to be reflected may be determined in accordance with the familiarity.

Abstract: Mechanisms are provided to implement an ensemble of unsupervised machine learning (ML) models. The ensemble of unsupervised ML models processes a portion of input data to generate an ensemble output and the ensemble output is output to an authorized user computing device to obtain user feedback from the authorized user via the user computing device. The user feedback indicates a correctness of the ensemble output. The mechanisms modify at least one feature of the ensemble of unsupervised ML models based on the obtained user feedback to thereby generate a modified ensemble of unsupervised ML models. Subsequent portions of input data are then processed using the modified ensemble of unsupervised ML models.

Abstract: Methods and systems for crowd level estimation are provided. The system for crowd level estimation includes an input module and a crowd level estimation module. The input module receives an input image of a crowd and the crowd level estimation module estimates a crowd level of the crowd in the input image in response to a crowd density level.

Abstract: A cross-domain image comparison method and a cross-domain image comparison system are provided. The cross-domain image comparison method includes the following steps. Two videos in cross-domain are obtained. The videos are generated by different types of devices. A plurality of semantic segmentation areas are obtained from one frame of each of the videos. A region of interest pair (ROI pair) is obtained according to moving paths of the semantic segmentation areas in the videos. Two bounding boxes and two central points of the ROI pair are obtained. A similarity between the frames is obtained according to the bounding boxes and the central points.

Abstract: Using detection of low variance regions for improving detection is described. In an example, sensor data can be received from a sensor associated with a vehicle. The sensor data can represent an environment. An indication of a low variance region associated with the sensor data can be determined and an indication of a high variance region associated with the sensor data can be determined based at least in part on the indication of the low variance region. The vehicle can be controlled based on at least one of the sensor data or the indication of the high variance region.

Abstract: Low variance detection training is described herein. In an example, annotated data can be determined based on sensor data received from a sensor associated with a vehicle. The annotated data can comprise an annotated low variance region and/or an annotated high variance region. The sensor data can be input into a model, and the model can determine an output comprising a high variance output and a low variance output. In an example, a difference between the annotated data and the output can be determined and one or more parameters associated with the model can be altered based at least in part on the difference. The model can be transmitted to a vehicle configured to be controlled by another output of the model.

Abstract: The present disclosure relates to a method and an apparatus for classifying data points using convex hulls based on centroids of clusters, and a method for classifying data points according to one embodiment of the present disclosure comprises clustering data points into a plurality of clusters; constructing a hyperplane by using a set of centroids of singular clusters having a single class label from the plurality of clusters and removing singular clusters whose centroids are not used to construct the hyperplane; generating a convex hull for a singular cluster used to construct the hyperplane; removing internal data points except for the vertices of the generated convex hull from the singular cluster whose centroid is used to construct the hyperplane; and classifying a set of remaining data points except for the removed internal data points among the plurality of clusters.