Large-scale distance metric learning for k-nearest neighbors regression

B Nguyen, C Morell, B De Baets - Neurocomputing, 2016 - Elsevier
This paper presents a distance metric learning method for k-nearest neighbors regression.
We define the constraints based on triplets, which are built from the neighborhood of each …

[HTML][HTML] Acoustic inspection of concrete structures using active weak supervision and visual information

JY Louhi Kasahara, A Yamashita, H Asama - Sensors, 2020 - mdpi.com
Concrete structures are featured heavily in most modern societies. In recent years, the need
to inspect those structures has been a growing concern and the automation of inspection …

Bag of feature with discriminative module for non-rigid shape retrieval

L Yang, L Wang, Z Zhang, J Zhuang - Digital Signal Processing, 2022 - Elsevier
Non-grid shape retrieval has been an important and challenging task that usually requires
high-level and discriminative shape features. However, most of the existing descriptors are …

A local-global shape characterization scheme using quadratic Bezier triangle aiding retrieval

M Kanimozhi, MS Sudhakar - Digital Signal Processing, 2023 - Elsevier
Shape characterization plays a highly prominent role in retrieval and relies extremely upon
descriptors inbuilt with lightweight operations and compaction qualities. However, realizing …

Co-weighting semantic convolutional features for object retrieval

J Zhu, J Wang, S Pang, W Guan, Z Li, Y Li… - Journal of Visual …, 2019 - Elsevier
Deep feature aggregation, which refers to aggregating a set of local convolutional features
into a global image-level vector, has attracted increasing attention in object instance …

Parsing 3D motion trajectory for gesture recognition

J Yang, J Yuan, Y Li - Journal of Visual Communication and Image …, 2016 - Elsevier
Motion trajectories have been widely used for gesture recognition. An effective
representation of 3D motion trajectory is important for capturing and recognizing complex …

Bayesian distance metric learning for discriminative fuzzy c-means clustering

N Heidari, Z Moslehi, A Mirzaei, M Safayani - Neurocomputing, 2018 - Elsevier
A great number of machine learning algorithms strongly depend on the underlying distance
metric for representing the important correlations of input data. Distance metric learning is …

Learning dynamic relationship between joints for 3D hand pose estimation from single depth map

H Xing, J Yang, Y Xiao - Journal of Visual Communication and Image …, 2023 - Elsevier
Abstract 3D hand pose estimation from a single depth map is an essential topic in computer
vision. Most existing methods are devoted to designing a model to capture more spatial …

Improved biharmonic kernel signature for 3D non-rigid shape matching and retrieval

Y Yan, M Zhou, D Zhang, S Geng - The Visual Computer, 2024 - Springer
Object retrieval, in particular 3D shape retrieval, recently has many applications such as
molecular biology, medical research and computer-aided manufacturing. As the internet and …

Weakly supervised acoustic defect detection in concrete structures using clustering-based augmentation

JYL Kasahara, H Fujii, A Yamashita… - … /ASME transactions on …, 2021 - ieeexplore.ieee.org
The automation of inspection methods for concrete structures is a pressing issue worldwide.
Weakly supervised approaches, ie, approaches based on supervision in other forms than …