An information processing apparatus includes a processor configured to, in classification of a target document according to at least one classification criterion, extract significant terms from classification-criterion terms on the basis of the degrees of significance of the classification-criterion terms relative to target-document terms, the classification-criterion terms being included in the at least one classification criterion, the target-document terms being included in the target document.

Techniques related to improved video coding based on face detection, region extraction, and tracking are discussed. Such techniques may include performing a facial search of a video frame to determine candidate face regions in the video frame, testing the candidate face regions based on skin tone information to determine valid and invalid face regions, rejecting invalid face regions, and encoding the video frame based on valid face regions to generate a coded bitstream.

Systems and methods for managing predictions for vehicle repair estimates are provided. A method includes providing one or more images of a damaged vehicle as input to a machine learning model, wherein the machine learning model has been trained with images of other damaged vehicles and corresponding vehicle operations, wherein each of the vehicle operations represents the repair or replacement of a vehicle component; receiving output of the machine learning model responsive to the input, wherein the output comprises a plurality of values each corresponding to one of a plurality of the vehicle operations; determining a confidence metric based on the values; making a comparison between the confidence metric and a confidence threshold value; and selecting the one of the plurality of the vehicle operations corresponding to the highest value as a predicted operation based on the comparison.

Techniques for auto-generation of annotated real-world training data are described. An electronic document is analyzed to determine text represented in the document and corresponding locations of the text. A representation of the electronic document is modified to include markers and printed. The printed document is photographed in real-world environments, and the markers within the digital photographs are analyzed to allow for the depiction of the document within the photographs to be rectified. The text and location data are used to annotate the rectified images.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for learning template representation libraries. In one aspect, a method includes obtaining an image depicting a physical environment, where the environment includes a given physical object. When possible, a position of the given object in the environment is inferred based on a template representation library using template matching techniques. In response to determining that the position of the given object in the environment cannot be inferred based on the template representation library using template matching techniques, the template representation library is automatically augmented with new template representations.

Described are methods, systems, and apparatus for recommending catalogue items for blacklisting. For each of a plurality of catalog items: image features are extracted; image features are associated with the catalog item; and user purchase events, user view events, a textual description, and categories are associated with the catalog item by the recommendation system. An identification of a first blacklisted catalog item is received. A catalog item is identified by the recommendation system based on i) a similarity between the image features associated with the first blacklisted catalog item and the image features associated with the catalog item, and ii) a correspondence between at least one of the user purchase events, the user view events, the textual description, or the categories associated with the blacklisted catalog item and the user purchase events, the user view events, the textual description, or the categories associated with the catalog item.

Embodiments described herein relate to methods, devices, and computer-readable media to determine a compression setting. An input image may be obtained where the input image is associated with a user account. One or more features of the input image may be determined using a feature-detection machine-learning model. A compression setting for the input image may be determined using a user-specific machine-learning model personalized to the user account based on the one or more features in the input image. The input image may be compressed based on the compression setting.

Systems and methods for data collection and processing are described, including a plurality of variable groups of industrial sensor inputs operationally coupled to an industrial environment and a multiplexer communicatively coupled to the industrial sensor inputs; and a controller configured to receive and monitor the data and adaptively schedule the data collector.

An image recognition device has a database in which pieces of feature data of a plurality of objects are registered while divided into classes for each of the plurality of objects; an identification unit that identifies an unknown object by evaluating which feature data of the class registered in the database is most similar to feature data obtained from an image of the unknown object, and a feature data registration unit that registers feature data in the database. The database is capable of setting a plurality of classes to an identical object. The feature data registration unit, in adding new feature data with respect to a first object already registered in the database, sets a new class other than an existing class with respect to the first object.

A multi-dimensional task facial beauty prediction method and system, and a storage medium are disclosed. The method includes the steps of: at a training phase, using first facial images to optimize a shared feature extraction network for extracting shared features and to train a plurality of sub-task networks for performing facial beauty classification tasks; at a testing phase, extracting shared features of second facial images; inputting the shared features to the trained plurality of sub-task networks; and obtaining a first beauty prediction result based on first output results of the plurality of sub-task networks.