Adaptive local landscape feature vector for problem classification and algorithm selection

Y Li, J Liang, K Yu, K Chen, Y Guo, C Yue… - Applied Soft Computing, 2022 - Elsevier
Fitness landscape analysis is a data-driven technique to study the relationship between
problem characteristics and algorithm performance by characterizing the landscape features …

IPD-Net: SO (3) Invariant Primitive Decompositional Network for 3D Point Clouds

RA Tabib, N Upasi, T Anvekar… - Proceedings of the …, 2023 - openaccess.thecvf.com
In this paper, we propose IPD-Net: Invariant Primitive Decompositional Network, a SO (3)
invariant framework for decomposition of a point cloud. The human cognitive system is able …

Snowvision: Segmenting, identifying, and discovering stamped curve patterns from fragments of pottery

Y Lu, J Zhou, ST McDorman, C Zhang, D Scott… - International Journal of …, 2022 - Springer
Abstract In southeastern North America, Indigenous potters and woodworkers carved
complex, primarily abstract, designs into wooden pottery paddles, which were subsequently …

3D surface matching by a voxel-based buffer-weighted binary descriptor

R Zhou, X Li, W Jiang - IEEE Access, 2019 - ieeexplore.ieee.org
3D surface matching by local feature descriptors is a fundamental task in 3D object
registration, recognition, and retrieval. In view of 2D projected descriptors' information …

3D Feature detector-descriptor pair evaluation on point clouds

P Stancelova, E Sikudova… - 2020 28th European …, 2021 - ieeexplore.ieee.org
In recent years, computer vision research has focused on extracting features from 3D data.
In this work, we reviewed methods of extracting local features from objects represented in …

Track-Oriented Self-Supervised Learning for Micro-Doppler Target Classification

S Rolfsjord, D Gusland, J Ahlberg - 2024 IEEE Radar …, 2024 - ieeexplore.ieee.org
Deep learning's shift from supervised to unsupervised methods has revolutionized many
applications, exemplified by innovations such as DALL-E-2 and Chat-GPT. This paper …

3D object recognition through a size function resulting from an invariant topological feature

MAA Mhamdi, D Ziou - Pattern Recognition, 2021 - Elsevier
In this paper, a critical points based descriptor for 3 D objects recognition is presented. It is
based on the topological invariant provided by the critical points of the 3 D object. The …

Deep learned compact binary descriptor with a lightweight network-in-network architecture for visual description

R Bandara, L Ranathunga, NA Abdullah - The Visual Computer, 2021 - Springer
Binary descriptors have been widely used for real-time image retrieval and correspondence
matching. However, most of the learned descriptors are obtained using a large deep neural …

Keypoint Description Using Statistical Descriptor with Similarity-Invariant Regions.

S Alsharif - Computer Systems Science & Engineering, 2022 - search.ebscohost.com
This article presents a method for the description of key points using simple statistics for
regions controlled by neighboring key points to remedy the gap in existing descriptors …

Performance evaluation of selected 3D keypoint detector–descriptor combinations

P Stancelova, E Sikudova, Z Cernekova - International Conference on …, 2020 - Springer
Nowadays, with easily accessible 3D point cloud acquisition tools, the field of point cloud
processing gained a lot of attention. Extracting features from 3D data became main …