A hierarchical dual-path architecture that decouples macro-structural consensus modeling from fine-grained local saliency excitation is proposed, and a differential multi-head attention mechanism is introduced to capture long-range global consensus with near-linear complexity.
A fully-supervised 3D point cloud classification framework integrating an edge-aware sampling strategy with a multi-scale attention mechanism enhances feature discriminability and robustness for point cloud classification, providing a robust algorithmic foundation for intelligent optical sensing systems in practical 3D...
Chen-Meng Wang, Su-Yuan Li, Hao-Rui Zhou et al.· Global Intelligent Industry...· 0 citations
This work reformulate point cloud prediction as a unified spatio-temporal correlation learning problem and proposes a novel framework, the Motion-guided Spatio-Temporal Point Cloud Prediction Network (MoCNet), which achieves higher prediction accuracy and better generalization ability.
Kai Gao, Yu-Xiang Zhou, Ping-Ping Dong et al.· Journal of Intelligent and C...· 0 citations
Car logo detection is a challenging fine-grained perception task characterized by small object scales and high inter-class similarity. In such scenarios, discriminative cues mainly reside in subtle local textures rather than global structures. Although State Space Model (SSM)-based detectors, such as Mamba-YOLO with it...
Jing-Wen Gong, Jun-Xing Zhang, Chun-Juan Bo· Italian National Conference...· 0 citations
Panoramic Semantic Segmentation (PASS) aims to achieve comprehensive 360° scene understanding from panoramic images. However, due to the geometric distortions introduced by equirectangular projection (ERP) and the complex semantic relationships in wide field-of-view scenes, effectively modeling both global contextual i...
Guo-Xu Li, Cheng Han, Chao Zhang et al.· Journal of King Saud Univers...· 0 citations
Domain adaptive object detection (DAOD) aims to reduce performance degradation due to distribution shifts between training (source) and testing (target) datasets. However, owing to insufficient modeling of fine-grained features and limited instance-level alignment, existing approaches become less effective under comple...
Zhen-Hua Yu, Jia-Hao Zhang, Wen-Chao Zhang et al.· 0 citations
Visible-thermal (RGB-T) imaging systems provide crucial complementary information for robust visual sensing and measurement in complex illumination conditions. However, effectively fusing multi-modal sensory data to achieve accurate semantic segmentation remains a key challenge. Most existing methods rely on heuristic...
Hong-Wei Liu, Yi-Sha Liu, Wei-Min Xue et al.· Measurement science and tech...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.