TOSD: A Hierarchical Object-Centric Descriptor Integrating Shape, Color, and Topology
This paper introduces a hierarchical object-centric descriptor framework called TOSD (Triplet Object-Centric Semantic Descriptor). The goal of this method is to overcome the limitations of existing pixel-based and global feature embedding approaches. To this end, the framework adopts a hierarchical...
Saved in:
| Main Authors: | Jun-Hyeon Choi, Jeong-Won Pyo, Ye-Chan An, Tae-Yong Kuc |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/15/4614 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
A Pure First Order Representation for Undamped Second Order Descriptor Systems
by: A. Aasaraai
Published: (2011-12-01) -
Enabling High-Level Worker-Centric Semantic Understanding of Onsite Images Using Visual Language Models with Attention Mechanism and Beam Search Strategy
by: Hui Deng, et al.
Published: (2025-03-01) -
Abnormal events detection using spatio-temporal saliency descriptor and fuzzy representation analysis
by: R. Tino Merlin, et al.
Published: (2024-11-01) -
Gaussian-UDSR: Real-Time Unbounded Dynamic Scene Reconstruction with 3D Gaussian Splatting
by: Yang Sun, et al.
Published: (2025-06-01) -
Local-Descriptors-Based Rectification Network for Few-Shot Remote Sensing Scene Classification
by: Anyong Qin, et al.
Published: (2025-01-01)