Object detection and recognition apparatus based on CNN based integrated circuits
L Yang, PZ Dong, CJ Young, JZ Dong… - US Patent …, 2019 - Google Patents
A deep learning object detection and recognition system contains a number of cellular
neural networks (CNN) based integrated circuits (ICs) operatively coupling together via the …
neural networks (CNN) based integrated circuits (ICs) operatively coupling together via the …
Generating object proposals using deep-learning models
PHO Pinheiro, RS Collobert, P Dollar - US Patent 10,255,522, 2019 - Google Patents
In one embodiment, a plurality of patches of an image are processed using a first deep-
learning model to detect a plurality of features associated with the first patch of the image …
learning model to detect a plurality of features associated with the first patch of the image …
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 …
Automatically detecting user-requested objects in images
US11631234B2 - Automatically detecting user-requested objects in images - Google
Patents US11631234B2 - Automatically detecting user-requested objects in images …
Patents US11631234B2 - Automatically detecting user-requested objects in images …
Segmenting objects in digital images utilizing a multi-object segmentation model framework
The present disclosure relates to a multi-model object segmentation system that provides a
multi-model object segmentation framework for automatically segmenting objects in digital …
multi-model object segmentation framework for automatically segmenting objects in digital …
Learning method and learning device for object detector based on reconfigurable network for optimizing customers' requirements such as key performance index …
Assignee: StradVision, Inc., Gyeongbuk (KR)(*) Notice: Subject to any disclaimer, the term of
this patent is extended or adjusted under 35 USC 154 (b) by 0 days. A method for learning …
this patent is extended or adjusted under 35 USC 154 (b) by 0 days. A method for learning …
Devices and methods for identifying an object in an image
M Hillborg - US Patent 10,546,389, 2020 - Google Patents
Methods, devices, and computer-readable storage media for identifying an object in an
image, the method including using a first neural network to identify an approximate position …
image, the method including using a first neural network to identify an approximate position …
Learning method and learning device for object detector based on CNN, adaptable to customers' requirements such as key performance index, using target object …
A method for learning parameters of an object detector based on a CNN adaptable to
customers' requirements such as KPI by using a target object merging network and a target …
customers' requirements such as KPI by using a target object merging network and a target …
Systems and methods for selective enhancement of objects in images
D Sytnik - US Patent 11,651,480, 2023 - Google Patents
US11651480B2 - Systems and methods for selective enhancement of objects in images -
Google Patents US11651480B2 - Systems and methods for selective enhancement of objects …
Google Patents US11651480B2 - Systems and methods for selective enhancement of objects …
Generating object proposals using deep-learning models
PHO Pinheiro, RS Collobert, P Dollar - US Patent 10,496,896, 2019 - Google Patents
In one embodiment, a plurality of patches of an image are processed using a first-pass of a
first deep-learning model to generate object-level information for each of the patches. Each …
first deep-learning model to generate object-level information for each of the patches. Each …