Ancestry.com Operations Inc.

Azadeh Moghtaderi

Yen-Yun Yu

Jack Reese

Jiayun Li

Mohammad K Ebrahimpour

Peng Jiang

Ruhan Wang

Tyler Folkman

Tsung-Nan Liu

Gann Alexander Bierner

Yingrui Yang

Gopalkrishna Balkrishna Veni

Christopher Miller

Randon Morford

Michael Benjamin Brodie

Methods, systems, and computer-program products for image enhancement include receiving an image and optionally a user request, classify the image, crop image components of the image, restore cropped image components of the image, colorized restored image components, and reconstruct the image from the colorized, restored image components and other components. The other components may include text components that are restored in a separate treatment pipeline.

Image enhancement in a genealogy system

Described herein are systems, methods, and other techniques for evaluating a classifier model. The classifier model may be provided with a set of elements to be classified into N classes. Classification results may be obtained from the classifier model. N class-specific precisions and N class-specific recalls for the N classes may be computed based on the classification results. N class-specific precision weights and N class-specific recall weights corresponding to the N classes may be obtained. A weighted f-measure may be computed by weighting the N class-specific precisions with the N class-specific precision weights and weighting the N class-specific recalls with the N class-specific recall weights.

Multiclass classification with diversified precision and recall weightings

Techniques for training a machine-learning (ML) model for captioning images are disclosed. A plurality of feature vectors and a plurality of visual attention maps are generated by a visual model of the ML model based on an input image. Each of the plurality of feature vectors correspond to different regions of the input image. A plurality of caption attention maps are generated by an attention model of the ML model based on the plurality of feature vectors. An attention penalty is calculated based on a comparison between the caption attention maps and the visual attention maps. A loss function is calculated based on the attention penalty. One or both of the visual model and the attention model are trained using the loss function.

Image captioning with weakly-supervised attention penalty

Systems and methods for training a machine learning (ML) ranking model to rank genealogy hints are described herein. One method includes retrieving a plurality of genealogy hints for a target person, where each of the plurality of genealogy hints corresponds to a genealogy item and has a hint type of a plurality of hint types. The method includes generating, for each of the plurality of genealogy hints, a feature vector having a plurality of feature values, the feature vector being included in a plurality of feature vectors. The method includes extending each of the plurality of feature vectors by at least one additional feature value based on the number of features of one or more other hint types of the plurality of hint types. The method includes training the ML ranking model using the extended plurality of feature vectors and user-provided labels.

Genealogy item ranking and recommendation

Embodiments described herein relate generally to a methodology of efficient object classification within a visual medium. The methodology utilizes a first neural network to perform an attention based object localization within a visual medium to generate a visual mask. The visual mask is applied to the visual medium to generate a masked visual medium. The masked visual medium may be then fed into a second neural network to detect and classify objects within the visual medium.

Ventral-dorsal neural networks: object detection via selective attention

An information entropy-based metric is used to represent a degree of diversity of a search result of genealogical records. In response to a query, a data query server locates a set of multiple records that match the query. The records are classified into different record types based on the records' attributes. One or more distributions of numbers of records classified into each record type are determined. Each distribution corresponds to one of the subsets the records. For each distribution, an entropy value is determined. A cumulative entropy that corresponds to a sum of the entropy values of those distributions is then determined. The cumulative entropy may serve as the entropy-based metric of the search result. The cumulative entropy may also be normalized by an ideal cumulative entropy. The normalized metric allows the diversity of different search results to be compared across different queries that may generate different numbers of records.

Growing community of inventors

San Francisco, CA, United States of America

Azadeh Moghtaderi