In certain embodiments, training of a prediction model (e.g., recognition or other prediction model) may be facilitated via a training set based on one or more logos or other graphics. In some embodiments, graphics information associated with a logo or graphic (e.g., to be recognized via a recognition model) may be obtained. Media items (e.g., images, videos, etc.) may be generated based on the graphics information, where each of the media items includes (i) content other than the logo and (ii) a given representation of the logo integrated with the other content. In some embodiments, the media items may be processed via the recognition model to generate predictions (related to recognition of the logo or graphic for the media items). The recognition model may be updated based on (i) the generated predictions and (ii) corresponding reference indications (related to recognition of the logo for the media items).

A method, computer program product, and computing system for receiving a plurality of images of a subject. The plurality of images of the subject may be processed to generate one or more templates. At least one template of the plurality of templates may be verified against at least one other template of the plurality of templates based upon, at least in part, a template quality threshold. A verified subset of templates may be generated including the at least one template that verifies each template of the plurality of templates.

An image forming apparatus that determines whether an image having coincidence with a registered image is included in an input image and controls execution of a job that uses the input image based on a result of the determination. The image forming apparatus includes an input unit that inputs a first image as a candidate of the registered image, an evaluation unit that evaluates whether the first image is suitable for use in the determination, and a control unit registers the first image as the registered image if the evaluation unit evaluates that the first image is suitable for use in the determination, and prevents the first image from being registered as the registered image if the evaluation unit evaluates that the first image is unsuitable for use in the determination.

The novel technology described in this disclosure includes an example method comprising selecting a target of interest having an obsolete appearance model, the obsolete appearance model describing a prior appearance of the target of interest, navigating a first mobile robot to a location the first mobile robot including a mechanical component providing motive force to the first mobile robot and an image sensor, and searching for the target of interest at the location. The method may include collecting, in the location by the image sensor of the first mobile robot, appearance data of the target of interest, and updating the obsolete appearance model using the appearance data of the target of interest. In some implementations, the method may, in a subsequent meeting between the target of interest and a second mobile robot at a later point in time, recognizing the target of interest using the updated appearance model.

Systems and methods to receive one or more first images associated with a training set of images to train a machine learning model; provide the one or more first images as a first input to a first set of layers of computational units, wherein the first set of layers utilizes image filters; provide a first output of the first set of layers of computational units as a second input to a second layer of the computational units, wherein the second layer utilizes random parameter sets for computations; obtain distortion parameters from the second layer of the computational units; generate one or more second images comprising a representation of the one or more first images modified with the distortion parameters; obtain, as a third output, the one or more second images; and add the one or more second images to the training set of images to train the machine learning model.

An information processing apparatus includes a selection unit that, when a target document is recognized, selects a first mode in which a latest version of a recognition dictionary is applied, or a second mode in which a version of the recognition dictionary is applied, the version of the recognition dictionary having a highest correct answer rate among plural versions different from the latest version, the correct answer rate being obtained from a recognition result and a confirmation or correction result of each of plural documents.

In certain embodiments, training of a prediction model (e.g., recognition or other prediction model) may be facilitated via a training set generated based on one or more logos or other graphics. In some embodiments, graphics information associated with a logo or graphic (e.g., to be recognized via a recognition model) may be obtained. Training media items (e.g., images, videos, etc.) may be generated based on the graphics information, where each of the training media items includes (i) content other than the logo and (ii) a given representation of the logo integrated with the other content. The training media items may be processed via the recognition model to generate predictions (related to recognition of the logo or graphic for the training media items). The recognition model may be updated based on (i) the generated predictions and (ii) corresponding reference indications (related to recognition of the logo for the training media items).

Various embodiments describe active learning methods for training temporal action localization models used to localize actions in untrimmed videos. A trainable active learning selection function is used to select unlabeled samples that can improve the temporal action localization model the most. The select unlabeled samples are then annotated and used to retrain the temporal action localization model. In some embodiment, the trainable active learning selection function includes a trainable performance prediction model that maps a video sample and a temporal action localization model to a predicted performance improvement for the temporal action localization model.

Systems and methods to receive one or more first images associated with a training set of images to train a machine learning model; provide the one or more first images as a first input to a first set of layers of computational units, wherein the first set of layers utilizes image filters; provide a first output of the first set of layers of computational units as a second input to a second layer of the computational units, wherein the second layer utilizes random parameter sets for computations; obtain distortion parameters from the second layer of the computational units; generate one or more second images comprising a representation of the one or more first images modified with the distortion parameters; obtain, as a third output, the one or more second images; and add the one or more second images to the training set of images to train the machine learning model.

Techniques are disclosed for generating a sequence of symbols based on input data for a neuro-linguistic model. The model may be used by a behavior recognition system to analyze the input data. A mapper component of a neuro-linguistic module in the behavior recognition system receives one or more normalized vectors generated from the input data. The mapper component generates one or more clusters based on a statistical distribution of the normalized vectors. The mapper component evaluates statistics and identifies statistically relevant clusters. The mapper component assigns a distinct symbol to each of the identified clusters.