Large-scale distance metric learning for k-nearest neighbors regression
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 …
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
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 …
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 …
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 …
descriptors inbuilt with lightweight operations and compaction qualities. However, realizing …
Co-weighting semantic convolutional features for object retrieval
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 …
into a global image-level vector, has attracted increasing attention in object instance …
Parsing 3D motion trajectory for gesture recognition
Motion trajectories have been widely used for gesture recognition. An effective
representation of 3D motion trajectory is important for capturing and recognizing complex …
representation of 3D motion trajectory is important for capturing and recognizing complex …
Bayesian distance metric learning for discriminative fuzzy c-means clustering
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 …
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 …
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 …
molecular biology, medical research and computer-aided manufacturing. As the internet and …
Weakly supervised acoustic defect detection in concrete structures using clustering-based augmentation
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 …
Weakly supervised approaches, ie, approaches based on supervision in other forms than …