Self-learning in distributed architecture for enhancing artificial neural network

A Mondello, A Troia - US Patent 11,328,210, 2022 - Google Patents
(57) ABSTRACT A vehicle having the first ANN model initially installed therein to generate
outputs from inputs generated by one or more sensors of the vehicle. The vehicle selects an …

Inter-prediction method and apparatus using reference frame generated based on deep learning

SH Cho, K Je-Won, NY Kim, JK Lee, J Lee… - US Patent …, 2021 - Google Patents
An inter-prediction method and apparatus uses a reference frame generated based on deep
learning. In the inter-predic tion method and apparatus, a reference frame is selected, and a …

Autonomous vehicle data recorders

G Golov - US Patent 11,410,475, 2022 - Google Patents
Systems, methods and apparatus to collect sensor data generated in an autonomous
vehicle. Sensors in the vehicle generate a sensor data stream during operations of the …

Data recorders of autonomous vehicles

G Golov - US Patent 11,373,466, 2022 - Google Patents
Systems, methods and apparatus to collect sensor data generated in an autonomous
vehicle. Sensors of the vehicle generate a sensor data stream that is buffered, in parallel …

Machine learning models for implementing animation actions

CD de Castro - US Patent 10,765,944, 2020 - Google Patents
An animation system and method generates predictive mod els that are deployed in
animations, such as an animation associated with a video game, to predict outcomes …

Systems and methods for multi-frame video frame interpolation

Z Chi, RM Nasiri, Z Liu, J Tang, J Lu - US Patent 11,430,138, 2022 - Google Patents
Systems and methods for multi-frame video frame interpo lation. Higher-order motion
modeling, such as cubic motion modeling, achieves predictions of intermediate optical flow …

Syntax signaling for optical-flow based inter coding

K Zhang, L Zhang, H Liu, Y Wang - US Patent 11,496,733, 2022 - Google Patents
10,819,891 B2 10,904,565 B2 2016/0100189 Al 2017/0006302 A1 2018/0192072 A1
2018/0310017 A1 2019/0082191 A1 2019/0104319 Al 2019/0138889 Al 2019/0273937 A1 …

Syntax signaling in sub-block merge mode

K Zhang, L Zhang, H Liu, Y Wang - US Patent 11,627,313, 2023 - Google Patents
....(57) ABSTRACT (63) Continuation of application No. PCT/CN2020/A method of visual
media processing includes determining 091539, filed on May 21, 2020. whether to use an …

Adaptive motion vector difference resolution for affine mode

K Zhang, L Zhang, H Liu, Y Wang - US Patent 11,470,309, 2022 - Google Patents
A method of visual media processing includes determining whether to use an affine adaptive
motion vector resolution (AMVR) technique on visual media data relying on a control …

Interplay between subpictures and in-loop filtering

K Zhang, Z Deng, H Liu, L Zhang, J Xu - US Patent 11,909,967, 2024 - Google Patents
An example method of video processing includes determining, for a conversion between a
block of a first sub-picture of a video and a bitstream representation of the video, whether to …