A5067494585- Wireless Signal Modulation Classification
- Video Surveillance and Tracking Methods
- Fractal and DNA sequence analysis
- Image Enhancement Techniques
- Advanced Vision and Imaging
- Anomaly Detection Techniques and Applications
- Spider Taxonomy and Behavior Studies
- Impact of Light on Environment and Health
- Machine Learning in Bioinformatics
- Advanced Image Processing Techniques
- Evacuation and Crowd Dynamics
Hong Kong University of Science and Technology
2024
University of Hong Kong
2024
Heilongjiang University of Science and Technology
2022-2023
Multimodal fusion-based methods are a research hotspot for Automatic Modulation Recognition (AMR). But the existing primarily emphasize information integration and neglect balance between modalities. This paper proposes novel Contrastive Learning-based Fusion (CLMF) model, which integrates both signals key features to enhance AMR. To obtain adequate signal representations, contrastive learning architecture is proposed learn meaningful representations from multimodal fusion data, Multi-Layer...
Nighttime semantic segmentation plays a crucial role in practical applications, such as autonomous driving, where it frequently encounters difficulties caused by inadequate illumination conditions and the absence of well-annotated datasets. Moreover, models trained on daytime datasets often face generalizing effectively to nighttime conditions. Unsupervised domain adaptation (UDA) has shown potential address challenges achieved remarkable results for segmentation. However, existing methods...
Deep learning-based classification algorithms have been used for automatic modulation recognition (AMR). However, most methods only focus on end-to-end mapping and neglect the classic key features. In this paper, signals are enforced with features to propose a novel deep learning model AMR by shared latent space of aligned (LLAF); is done increase generalizability ensure physical plausibility results. To obtain adequate signal representations, an encoder-decoder architecture proposed learn...