Facebook, Inc.

Meta Platforms, Inc.

Ahmad Abdulmageed Mohammed Abdulkader

Stephane Taine

Ewa Dominowska

Giridhar Rajaram

Vladislav Belous

Seyed Mohsen Amiri

Tianshi Gao

Sofus Attila Macskassy

Liang Xiong

Ou Jin

Benjamin Ray

Yifei Huang

To select the content to be presented to the user, a first latent vector is determined for a content item based on a first object associated with the content item. A second latent vector is determined for the content item based on a second object associated with the content item. A content item vector is then determined based on the first and second latent vectors. Furthermore, a user vector is determined based on interactions of the user with the first set of content objects and the second set of content objects. A score indicative of the likelihood of the user interacting with the content item is determined based on the content item vector and the user vector.

Deep semantic content selection

An online system using attributes of users to select content for presentation to the users predicts one or more attributes of users whose attributes are unavailable to the online system. For a user with one or more attributes unavailable to the online system, the online system applies a model to attributes of additional users to predict one or more attributes of the user. Attributes of the additional user use in the prediction may include demographic information and interactions with content by the additional users. The online system may determine an accuracy of the model by using the model to predict attributes for users whose attributes are known to the online system and comparing the predicted attributes to the known attributes. If the model's accuracy is less than a threshold value, the online system discontinues using the model to predict attributes of users.

Predicting demographic information of an online system user based on online system login status

Systems, methods, and non-transitory computer-readable media can acquire an image that depicts at least one character. A set of pixels, within the image, through which the at least one character is depicted can be identified. At least one linear portion, within the image, can be identified based on the set of pixels. For each sub-portion within the at least one linear portion, a respective first confidence score representing a respective first likelihood that a respective sub-portion depicts the at least one character can be determined.

Systems and methods for incremental character recognition to recognize characters in images

A arbitrated image classifier can be trained to identify whether an image contains specified features, such as sexual, violent, or other potentially objectionable content. An arbitrated image classifier can include a configuration of classifiers and an arbitrator that determines a final image classification based on classification results from the classifiers. An arbitrated image classifier can be trained to identify image features by dividing images labeled as including or not including a specified feature into portions, which are provided to the classifiers of the arbitrated image classifier. The arbitrator of the arbitrated image classifier can determine a result for whether or not the image includes the specified feature. If the final result does not match the image label, parameter values for various of the classifiers or the arbitrator combining procedure can be adjusted. A trained arbitrated image classifier can then be used to determine whether new images include the particular feature.

Objectionable content detector

Growing community of inventors

Palo Alto, CA, United States of America

Ahmad Abdulmageed Mohammed Abdulkader