Machine-learning-based detection of fake videos
AssigneeReality Defender, Inc.
InventorsGaurav BHARAJ, Trevine OORLOFF, Surya KOPPISETTI, Nicolò BONETTINI, Ben COLMAN, Ali SHAHRIYARI
Life of this patent
Estimating the term…
Loading patent…
AssigneeReality Defender, Inc.
InventorsGaurav BHARAJ, Trevine OORLOFF, Surya KOPPISETTI, Nicolò BONETTINI, Ben COLMAN, Ali SHAHRIYARI
Estimating the term…
A method for training a model for classifying videos as real or fake can include generating image tiles and audio data segments from an input video, generating a sequence of image embeddings based on the image tiles using a visual encoder and a sequence of audio embeddings based on the audio data segments using an audio encoder, transforming, using a V2A network, a first subset of the sequence of image embeddings into synthetic audio embeddings, transforming, using an A2V network, a first subset of the sequence of audio embeddings into synthetic image embeddings, updating the sequence of image embeddings by using the synthetic image embeddings, updating the sequence of audio embeddings using the synthetic audio embeddings, training the encoders and the networks using the updated sequences of image embeddings and audio embeddings, and training a classifier using the trained encoders and the trained networks.
A method for training a model comprising a visual encoder, an audio encoder, an audio-to-visual (A2V) network, a visual-to-audio (V2A) network, and a classifier for classifying videos as real or fake, the method comprising:
A system for training a model comprising a visual encoder, an audio encoder, an audio-to-visual (A2V) network, a visual-to-audio (V2A) network, and a classifier for classifying videos as real or fake, the system comprising one or more processors configured to:
A non-transitory computer readable storage medium storing instructions for training a model comprising a visual encoder, an audio encoder, an audio-to-visual (A2V) network, a visual-to-audio (V2A) network, and a classifier for classifying videos as real or fake that, when executed by one or more processors of a computer system, cause the computer system to:
Dependencies are inferred from the claim text.