Adversarial attacks on black box video classifiers: Leveraging the power of geometric transformations

S Li, A Aich, S Zhu, S Asif, C Song… - Advances in …, 2021 - proceedings.neurips.cc
When compared to the image classification models, black-box adversarial attacks against
video classification models have been largely understudied. This could be possible …

FetusMapV2: Enhanced fetal pose estimation in 3D ultrasound

C Chen, X Yang, Y Huang, W Shi, Y Cao, M Luo… - Medical Image …, 2024 - Elsevier
Fetal pose estimation in 3D ultrasound (US) involves identifying a set of associated fetal
anatomical landmarks. Its primary objective is to provide comprehensive information about …

Neuromorphic system for real-time visual activity recognition

D Khosla, RM Uhlenbrock, Y Chen - US Patent 10,997,421, 2021 - Google Patents
Described is a system for visual activity recognition that includes one or more processors
and a memory, the memory being a non-transitory computer-readable medium having …

Three dimensional bounding box estimation from two dimensional images

A Mousavian, JP Flynn, DD Anguelov - US Patent 10,304,191, 2019 - Google Patents
A three dimensional bounding box is determined from a two dimensional image. A two
dimensional bounding box is calculated based on a detected object within the image. A …

Method and system for detection and classification of cells using convolutional neural networks

M Mesmakhosroshahi, S Agarwal, Y Zhang - US Patent 10,282,589, 2019 - Google Patents
BACKGROUND OF THE INVENTION unclear boundaries and occlusion. Cell classification
classi fies each of the segmented cells to one of a number of Field of the Invention …

Image quality score using a deep generative machine-learning model

BL Odry, B Mailhe, HE Cetingul, X Chen… - US Patent …, 2018 - Google Patents
For image quality scoring of an image from a medical scanner, a generative model of an
expected good quality image may be created using deep machine-learning. The deviation of …

System and method for automatically detecting a target object from a 3D image

Q Song, S Sun, H Chen, J Bai, F Gao… - US Patent …, 2020 - Google Patents
(57) ABSTRACT A computer-implemented method for automatically detect ing a target
object from a 3D image is disclosed. The method may include receiving the 3D image …

Image processing apparatus, image processing method, and non-transitory computer-readable storage medium

S Tate - US Patent 11,256,955, 2022 - Google Patents
(57) ABSTRACT A connected layer feature is generated by connecting outputs of a plurality
of layers of a hierarchical neural network obtained by processing an input image using the …

Learning method and learning device for adjusting parameters of CNN by using multi-scale feature maps and testing method and testing device using the same

Y Kim, W Nam, S Boo, M Sung, D Yeo… - US Patent …, 2018 - Google Patents
A learning method for acquiring a bounding box corresponding to an object in a training
image from multi-scaled feature maps by using a CNN is provided. The learning method …

Implementation of MobileNet in a CNN based digital integrated circuit

L Yang, PZ Dong, JZ Dong, B Sun - US Patent 10,360,470, 2019 - Google Patents
Method and systems of replacing operations of depthwise separable filters with first and
second replacement convolutional layers are disclosed. Depthwise separable filters …