A5011749112- Neural Networks and Applications
- Advanced Graph Neural Networks
- Face and Expression Recognition
- Advanced Image and Video Retrieval Techniques
- Advanced Algorithms and Applications
- Energy, Environment, and Transportation Policies
- Electric Vehicles and Infrastructure
- Graph Theory and Algorithms
- Advanced Battery Technologies Research
Fujian Agriculture and Forestry University
2024
Tongji University
2011-2024
Feature matching is an essential computer vision task that requires the establishment of high-quality correspondences between two images. Constructing sparse dynamic graphs and extracting contextual information by searching for neighbors in feature space a prevalent strategy numerous previous works. Nonetheless, these works often neglect potential connections from different layers, leading to underutilization available information. To tackle this issue, we introduce Sparse Dynamic Graph...
In this article, we propose a novel pyramid transformer network (PT-Net) for feature matching problems. Recent studies have used the dense motion field to transform unordered correspondences into ordered vectors and convolutional neural networks (CNNs) extract deep features. However, limited receptive of CNNs restricts ability capture global information within field. To tackle limitation, devise (PT) block enhance models both local from field, which fuses multiscale by constructing...
This paper used Advisor to define structures and power trains of parallel plug-in hybrid electric vehicles (PHEVs), made two PHEV models that have different battery ranges 20 km 60 km, established consumer total ownership cost based on purchase, compared with a conventional vehicle (CV) vehicles. Then three scenarios were defined – government subsidy (US$2571 for PHEV20 US$7143 PHEV60 according Chinese policy, where in this 1 US$ = 7.00 RMB), high oil price (10 per cent annual growth rate),...