Faster Mean-shift: GPU-accelerated clustering for cosine embedding-based cell segmentation and tracking

M Zhao, A Jha, Q Liu, BA Millis… - Medical Image …, 2021 - Elsevier
Recently, single-stage embedding based deep learning algorithms gain increasing attention
in cell segmentation and tracking. Compared with the traditional “segment-then-associate” …

GPU-accelerated Faster Mean Shift with euclidean distance metrics

L You, H Jiang, J Hu, CH Chang, L Chen… - 2022 IEEE 46th …, 2022 - ieeexplore.ieee.org
Handling clustering problems are important in data statistics, pattern recognition and image
processing. The mean-shift algorithm, a common unsupervised algorithms, is widely used to …

Fast image dehazing using guided joint bilateral filter

C **ao, J Gan - The Visual Computer, 2012 - Springer
In this paper, we propose a new fast dehazing method from single image based on filtering.
The basic idea is to compute an accurate atmosphere veil that is not only smoother, but also …

Adaptive core fusion-based density peak clustering for complex data with arbitrary shapes and densities

F Fang, L Qiu, S Yuan - Pattern Recognition, 2020 - Elsevier
A challenging issue of clustering in real-word application is to detect clusters with arbitrary
shapes and densities in complex data. Many conventional clustering algorithms are capable …

Tigris: Architecture and algorithms for 3d perception in point clouds

T Xu, B Tian, Y Zhu - Proceedings of the 52nd Annual IEEE/ACM …, 2019 - dl.acm.org
Machine perception applications are increasingly moving toward manipulating and
processing 3D point cloud. This paper focuses on point cloud registration, a key primitive of …

Fast shadow removal using adaptive multi‐scale illumination transfer

C **ao, R She, D **ao, KL Ma - Computer Graphics Forum, 2013 - Wiley Online Library
In this paper, we present a new method for removing shadows from images. First, shadows
are detected by interactive brushing assisted with a Gaussian Mixture Model. Secondly, the …

MeanShift++: Extremely fast mode-seeking with applications to segmentation and object tracking

J Jang, H Jiang - Proceedings of the IEEE/CVF Conference …, 2021 - openaccess.thecvf.com
MeanShift is a popular mode-seeking clustering algorithm used in a wide range of
applications in machine learning. However, it is known to be prohibitively slow, with …

QuickFPS: Architecture and algorithm co-design for farthest point sampling in large-scale point clouds

M Han, L Wang, L **ao, H Zhang… - … on Computer-Aided …, 2023 - ieeexplore.ieee.org
Point clouds have been employed extensively in machine perception applications. Farthest
point sampling (FPS) is a critical kernel for point cloud processing. With the rapid growth of …

Segmentation for high-resolution optical remote sensing imagery using improved quadtree and region adjacency graph technique

G Fu, H Zhao, C Li, L Shi - Remote sensing, 2013 - mdpi.com
An approach based on the improved quadtree structure and region adjacency graph for the
segmentation of a high-resolution remote sensing image is proposed in this paper. In order …

Entropy-weighted medoid shift: An automated clustering algorithm for high-dimensional data

A Kumar, OS Ajani, S Das, R Mallipeddi - Applied Soft Computing, 2025 - Elsevier
Unveiling the intrinsic structure within high-dimensional data presents a significant
challenge, particularly when clusters manifest themselves in lower-dimensional subspaces …