An automatic scale-adaptive approach with attention mechanism-based crowd spatial information for crowd counting

W Kong, H Li, G Xing, F Zhao - IEEE Access, 2019 - ieeexplore.ieee.org
This paper proposes an automatic scale-adaptive approach with attention mechanism-
based crowd spatial information addressing the crowd counting task, ie a novel cascaded …

Efficient triple output network for vertebral segmentation and identification

CH Chuang, CY Lin, YY Tsai, ZY Lian, HX Xie… - IEEE …, 2019 - ieeexplore.ieee.org
Precise vertebral segmentation provides the basis for spinal image analyses and
interventions, such as vertebral compression fracture detection and other abnormalities …

MSPPNet: A lightweight network for real-time semantic image segmentation

Y Liang, T Hang, J Chen, L Liu - Journal of Physics: Conference …, 2021 - iopscience.iop.org
Real-time semantic segmentation is widely applied in many fields. However, current state-of-
the-art methods ignore the inference speed, while some other models that have short run …

[PDF][PDF] Efficient Triple Output Network for Vertebral Segmentation and Identification

CC HSU, CLIN HUANG - scholar.archive.org
Precise vertebral segmentation provides the basis for spinal image analyses and
interventions, such as vertebral compression fracture detection and other abnormalities …

[PDF][PDF] Estimation of Optical Flow using Semantic Segmentation and AES Deep Neural Network

H Zamanian, H Farsi, S Mohamadzadeh - Journal of Advanced …, 2020 - adst.ihu.ac.ir
The importance and demand of visual scene understanding have been increasing because
of autonomous systems development. Optical flow is known as an important tool for scene …

Method, system, and computer-readable medium for improving quality of low-light images

Z Meng, C Ho - US Patent 11,741,578, 2023 - Google Patents
In an embodiment, a method includes receiving a digital image; generating, by at least one
processor, a resulting digital image by processing the digital image with an encoder …

Method, system, and computer-readable medium for improving quality of low-light images

Z Meng - US Patent 11,887,280, 2024 - Google Patents
In an embodiment, a method includes receiving a low-light digital image; generating, by at
least one processor, a resulting digital image by processing the low-light digital image with …

تخمین جریان نوری با استفاده از تقسیم‌بندی معنایی و شبکه عصبی عمیق AES

زمانیان, فرسی, محمدزاده - علوم و فناوریهای پدافند نوین, 2020‎ - adst.ihu.ac.ir
اهمیت و نیاز به درک صحنههای بصری به علت پیشرفت سامانه‌های خودکار به‌طور پیوسته افزایش
یافته است. جریان نوری یکی از ابزارهای درک صحنه‌های بصری است. روشهای جریان نوری موجود …

Interpretable Verification of Visually Similar Vehicle Images Using Convolutional Networks

L Hong, W Wang, Y Pang, H Hu, J Tang - … , Big Data 2018, Xi'an, China …, 2018 - Springer
This paper presents a simple and effective method to verify similar vehicle images. In order
to provide a meaningful interpretation of the verification, we propose to detect the local …