Results 291 to 300 of about 7,815,504 (353)
Some of the next articles are maybe not open access.
Sparse-to-Dense Matching Network for Large-Scale LiDAR Point Cloud Registration
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023Point cloud registration is a fundamental problem in 3D computer vision. Previous learning-based methods for LiDAR point cloud registration can be categorized into two schemes: dense-to-dense matching methods and sparse-to-sparse matching methods ...
Fan Lu +6 more
semanticscholar +1 more source
Proxy Graph Matching with Proximal Matching Networks
Proceedings of the AAAI Conference on Artificial Intelligence, 2021Estimating feature point correspondence is a common technique in computer vision. A line of recent data-driven approaches utilizing the graph neural networks improved the matching accuracy by a large margin. However, these learning-based methods require a lot of labeled training data, which are expensive to collect.
Haoru Tan +5 more
openaire +1 more source
Cross-modal Graph Matching Network for Image-text Retrieval
ACM Trans. Multim. Comput. Commun. Appl., 2022Image-text retrieval is a fundamental cross-modal task whose main idea is to learn image-text matching. Generally, according to whether there exist interactions during the retrieval process, existing image-text retrieval methods can be classified into ...
Yuhao Cheng +4 more
semanticscholar +1 more source
A Compact and Broadband Doherty Power Amplifier Without Post-Matching Network
IEEE Transactions on Circuits and Systems - II - Express Briefs, 2023Post-matching network (PMN) dominates broadband Doherty power amplifier (DPA) design, but at the cost of large footprint. This brief presents a PMN-free, compact and broadband DPA based on dual-mode impedance transformer (IT) which can simultaneously ...
Liheng Zhou, X. Zhou, W. Chan
semanticscholar +1 more source
Highly Efficient Power Amplifier Based on Harmonic-Controlled Matching Network
IEEE Microwave and Wireless Technology Letters, 2023This study presents a highly efficient power amplifier (PA) based on a compact harmonic-controlled matching network (HCMN). The proposed HCMN with three-stage band-stop matching network (BMN) can simultaneously match to the optimum power matching ...
Jisu Kim, Sun K. Hong, Juntaek Oh
semanticscholar +1 more source
IEEE transactions on industrial electronics (1982. Print), 2023
Since the power supply is limited in ships, the impedance matching network is essential for a high-power underwater electroacoustic transduction system. However, the existing impedance matching networks can barely achieve full impedance matching under a ...
Jiawen Yu +5 more
semanticscholar +1 more source
Since the power supply is limited in ships, the impedance matching network is essential for a high-power underwater electroacoustic transduction system. However, the existing impedance matching networks can barely achieve full impedance matching under a ...
Jiawen Yu +5 more
semanticscholar +1 more source
A Hybrid Impedance Matching Network for Underwater Acoustic Transducers
IEEE transactions on power electronics, 2023The underwater acoustic transducer (UAT) is an electro-acoustic conversion device, which is a nonlinear reactive load. An impedance matching network is usually added between the power amplifier and the UAT.
W. Tian +6 more
semanticscholar +1 more source
A Novel Impedance Matching Network Suitable for Designing High-Efficiency Power Amplifiers
IEEE Transactions on Circuits and Systems - II - Express Briefs, 2023In this brief, a novel impedance matching network (IMN) for designing high-efficiency power amplifiers (PAs) is presented. With this method, the fundamental matching network (FMN) and the harmonic control network (HCN) are incorporated into a single ...
Chang Liu, Wen-hua Chen, F. Ghannouchi
semanticscholar +1 more source
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018
Generative Adversarial Nets (GANs) and Conditonal GANs (CGANs) show that using a trained network as loss function (discriminator) enables to synthesize highly structured outputs (e.g. natural images). However, applying a discriminator network as a universal loss function for common supervised tasks (e.g.
Gellért Máttyus, Raquel Urtasun
openaire +1 more source
Generative Adversarial Nets (GANs) and Conditonal GANs (CGANs) show that using a trained network as loss function (discriminator) enables to synthesize highly structured outputs (e.g. natural images). However, applying a discriminator network as a universal loss function for common supervised tasks (e.g.
Gellért Máttyus, Raquel Urtasun
openaire +1 more source
Efficient Tri-Band Rectifier Using Multistub Matching Network for WPT Applications
IEEE Microwave and Wireless Technology Letters, 2023This letter presents an efficient tri-band rectifier using a multistub matching network. Theoretical analysis of the tri-band impedance matching network consisting of the multistub is carried out, which shows that good input impedance matching can be ...
Chunlai Du, Fei Cheng, Chao Gu
semanticscholar +1 more source