Facebook, Inc.

Facebook Technologies, LLC

Meta Platforms Technologies, LLC

Yaniv Taigman

Gil Hirsch

Dan Barak

Dirk John Stoop

Jorn Martinus Johannes Van Dijk

Eden Shochat

Moti Shniberg

Lubomir Dimitrov Bourdev

Lior Wolf

Balamanohar Paluri

Robert D Fergus

Cory West

Ning Zhang

Ming Yang

Michael James Matas

Oran Gafni

Hyunbin Park

Tali Zvi

Michael Waldman Reckhow

Marc′Aurelio Ranzato

David Vazquez

Adam Polyak

Marc'Aurelio Ranzato

Disclosed herein a system, a method and a device for generating a voice model for a user. A device can include an encoder and a decoder to generate a voice model for converting text to an audio output that resembles a voice of the person sending respective text. The encoder can includes a neural network and can receive a plurality of audio samples from a user. The encoder can generate a sequence of values and provide the sequence of values to the decoder. The decoder can establish, using the sequence of values and one or more speaker embeddings of the user, a voice model corresponding to the plurality of audio samples of the user.

Generating a voice model for a user

Systems, methods, and non-transitory computer readable media can align face images, classify face images, and verify face images by employing a deep neural network (DNN). A 3D-aligned face image can be generated from a 2D face image. An identity of the 2D face image can be classified based on provision of the 3D-aligned face image to the DNN. The identity of the 2D face image can comprise a feature vector.

Systems and methods for facial representation

A video generation system is described that extracts one or more characters or other objects from a video, re-animates the character, and generates a new video in which the extracted characters. The system enables the extracted character(s) to be positioned and controlled within a new background scene different from the original background scene of the source video. In one example, the video generation system comprises a pose prediction neural network having a pose model trained with (i) a set of character pose training images extracted from an input video of the character and (ii) a simulated motion control signal generated from the input video. In operation, the pose prediction neural network generates, in response to a motion control input from a user, a sequence of images representing poses of a character. A frame generation neural network generates output video frames that render the character within a scene.

Controllable video characters with natural motions extracted from real-world videos

A system and method for mapping interpersonal relationships, the method including sending a first composite image that includes an image of at least one unknown person from the client machine to an image analysis system of the online social network, receiving a list of candidate persons, each candidate person corresponding to a particular person identifier and having a predetermined relationship with the first user at the client machine, and sending information indicating a selection of one of the candidate persons for tagging the image of the unknown person with the particular person identifier corresponding to the selected candidate person from the client machine.

Relationship mapping employing multi-dimensional context including facial recognition

Techniques to allow a social networking system to provide hints when a user tags an image. In one embodiment, a comment associated with an image to be tagged by a user of a social networking system is received. A hint based on the comment that is suggestive of at least one aspect relating to the image is identified. A set of candidate tags associated with the user is determined. At least one suggested tag from the set of candidate tags is selected based on the hint. The at least one suggested tag is provided for the user to potentially tag the image.

Methods and systems for using hints in media content tagging

In one embodiment, a method includes sending, from a client system of a first user to a server of an online social network, an image portraying at least a first person and determining, for each user in a first set of users, a facial-recognition score with respect to the first person portrayed in the image. The facial-recognition score is based at least in part on a facial-representation associated with the user being compared with the image. The method further includes presenting, at the client system, one or more tag suggestions for the first person portrayed in the image based on the facial-recognition scores and a social-graph affinity associated with one or more users of the first set of users and receiving a selection of a particular tag suggestion by the first user. Each tag suggestion corresponds to a particular user of the first set of users.

Tag suggestions for images on online social networks

Systems, methods, and non-transitory computer-readable media can acquire real-time image data depicting at least a portion of a face of a user of a computing system (or device). The real-time image data can be analyzed to determine a state associated with at least the portion of the face. An emoji can be provided based on the state associated with at least the portion of the face. The emoji can be inputted in a communication to be made by the user.

Systems and methods for dynamically generating emojis based on image analysis of facial features

A system and method for mapping interpersonal relationships, the method including processing a multiplicity of images and contextual information relating thereto including creating and prioritizing a list of a plurality of candidate persons having at least a predetermined relationship with at least one person connected to at least one image, using multi-dimensional information including visually sensible information in the multiplicity of images and contextual information relating thereto and searching the list of a plurality of candidate persons based at least in part on the prioritizing to select at least one of the candidate persons as having at least a predetermined relationship with the at least one person.

Systems, methods, and non-transitory computer-readable media can receive a first image including a representation of a first user. A second image including a representation of a second user can be received. A first set of poselets associated with the first user can be detected in the first image. A second set of poselets associated with the second user can be detected in the second image. The first image including the first set of poselets can be inputted into a first instance of a neural network to generate a first multi-dimensional vector. The second image including the second set of poselets can be inputted into a second instance of the neural network to generate a second multi-dimensional vector. A first distance metric between the first multi-dimensional vector and the second multi-dimensional vector can be determined.

Systems and methods for identifying users in media content based on poselets and neural networks

In one embodiment, a method includes accessing an image portraying at least a first person, accessing a social graph, determining a social-graph affinity for a first set of users, determining a facial-recognition scores for the first set of users based on the social-graph affinity for each user and a facial-representation associated with each user, where the facial-representation for each user is compared with the image, and generating one or more tag suggestions for the first person portrayed in the image based on the facial-recognition scores.

Growing community of inventors

Los Altos, CA, United States of America

Yaniv Taigman