Digital watermarking of machine-learning models
P Zatloukal - US Patent 11,042,611, 2021 - Google Patents
In one embodiment, a method includes by a computing device, detecting a sensory input,
identifying, using a machine-learning model, one or more attributes associated with the …
identifying, using a machine-learning model, one or more attributes associated with the …
Deep neural network based identification of realistic synthetic images generated using a generative adversarial network
Techniques are provided for deep neural network (DNN) identification of realistic synthetic
images generated using a generative adversarial network (GAN). According to an …
images generated using a generative adversarial network (GAN). According to an …
Classifying audio scene using synthetic image features
ECW Sommerlade, Y Liu, A Neofytou… - US Patent …, 2021 - Google Patents
A computing system includes an encoder that receives an input image and encodes the
input image into real image features, a decoder that decodes the real image features into a …
input image into real image features, a decoder that decodes the real image features into a …
Audio source identification
JC Huang, GQ Hu, P Ji, J Zhu - US Patent 10,748,554, 2020 - Google Patents
Embodiments facilitating audio source identification are provided. A computer-implemented
method comprises: receiving, by a device operatively coupled to one or more processors, an …
method comprises: receiving, by a device operatively coupled to one or more processors, an …
Electronic apparatus for providing information based on existence of a user account and method thereof
HJ Oh, YJ Yang, SI Kim, HY Lee, HH Ahn… - US Patent …, 2023 - Google Patents
2021-12-29 Assigned to COUPANG CORP. reassignment COUPANG CORP. ASSIGNMENT
OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: GAO, YUN, AHN …
OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: GAO, YUN, AHN …
End-to-end multi-speaker audio-visual automatic speech recognition
O Braga - US Patent 11,900,919, 2024 - Google Patents
An audio-visual automated speech recognition model for transcribing speech from audio-
visual data includes an encoder frontend and a decoder. The encoder includes an attention …
visual data includes an encoder frontend and a decoder. The encoder includes an attention …
Digital watermarking of machine-learning models
P Zatloukal - US Patent 11,893,486, 2024 - Google Patents
In one embodiment, a method includes by a computing device, detecting a sensory input,
identifying, using a machine-learning model, one or more attributes associated with the …
identifying, using a machine-learning model, one or more attributes associated with the …
Generating video information representative of audio clips
SM Hallgren, AB Smith - US Patent 11,238,886, 2022 - Google Patents
A service for automatically generating video representations of audio content is provided. A
video representation gen eration component receives a request with search criteria related …
video representation gen eration component receives a request with search criteria related …
Deep neural network based identification of realistic synthetic images generated using a generative adversarial network
Techniques are provided for deep neural network (DNN) identification of realistic synthetic
images generated using a generative adversarial network (GAN). According to an …
images generated using a generative adversarial network (GAN). According to an …
Network operational decision engine
JB Castinado, JH Jain - US Patent 10,965,548, 2021 - Google Patents
Due to communication and design constraints of existing resource distribution networks,
users have little control over 15 operational decisions to multiple user accounts simultane …
users have little control over 15 operational decisions to multiple user accounts simultane …