Enhanced graph transformation-based point cloud attribute compression method

G Li, Y Shao - US Patent 11,126,887, 2021 - Google Patents
An enhanced graph transformation-based point cloud attribute compression method. For
point cloud attribute information, a point cloud is first subjected to airspace division by using …

Accelerated precomputation of reduced deformable models

Y Yang - US Patent 10,474,927, 2019 - Google Patents
Technologies are disclosed for precomputation of reduced deformable models. In such
precomputation, a Krylov subspace iteration may be used to construct a series of inertia …

Personalized beauty system

H Tran - US Patent 10,685,739, 2020 - Google Patents
In one aspect, systems methods disclosed for recommending health/beauty products for a
subject by using a genetic machine such as spectrophotometer or a DNA sequencer to …

Generating output sequences from input sequences using neural networks

O Vinyals, N Jaitly - US Patent 11,227,206, 2022 - Google Patents
US11227206B1 - Generating output sequences from input sequences using neural networks
- Google Patents US11227206B1 - Generating output sequences from input sequences using …

Language processing using a neural network

X Hu, Z Wen - US Patent 11,210,474, 2021 - Google Patents
This disclosure relates to language processing using a neural network. In one aspect, a
method includes performing, at an embedding layer of a neural network, embedding …

Finding the origin of an arrythmia

G Hayam, M Timofeyev, TH Bar-on… - US Patent 11,445,935, 2022 - Google Patents
A probe generates location signals, and has an electrode at a distal end which acquires
from heart chamber surface positions electrical signals due to a conduction wave traversing …

Method, system, and apparatus for generating and training a digital signal processor for evaluating graph data

D Fang, P Cogan - US Patent 11,568,197, 2023 - Google Patents
Example embodiments described herein includes a DSP having a self-learning/self-
trainable feature that may be optimized over time by training the DSP using known graph …