Fcanet: Frequency channel attention networks

Z Qin, P Zhang, F Wu, X Li - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
… Namely, we evaluate the results of each frequency component in channel attention individually.
Finally, we choose the Top-k highest performance frequency components based on the …

Image super-resolution using very deep residual channel attention networks

Y Zhang, K Li, K Li, L Wang… - Proceedings of the …, 2018 - openaccess.thecvf.com
… main network focus on learning high-frequency information. Furthermore, we propose a channel
attention mechanism to adaptively rescale channel… interdependencies among channels. …

Multi-frequency information enhanced channel attention module for speaker representation learning

M Sang, JHL Hansen - arXiv preprint arXiv:2207.04540, 2022 - arxiv.org
network parameters. Therefore, we propose the single-frequency single-channel (SFSC)
attention module which can be painlessly added to the existing speaker embedding networks. …

A high-capacity steganography algorithm based on adaptive frequency channel attention networks

S Zhang, H Li, L Li, J Lu, Z Zuo - Sensors, 2022 - mdpi.com
frequency-domain perspective. We propose a module called the … frequency-domain channel
attention network (AFcaNet), which makes full use of the frequency features in each channel

CFCANet: A complete frequency channel attention network for SAR image scene classification

B Su, J Liu, X Su, B Luo, Q Wang - IEEE Journal of Selected …, 2021 - ieeexplore.ieee.org
… complete frequency channel attention network (CFCANet) that can handle noisy RS images
directly without any filtering operation. CFCANet selects part of the low-frequencyfrequency

A time-frequency network with channel attention and non-local modules for artificial bandwidth extension

Y Dong, Y Li, X Li, S Xu, D Wang… - ICASSP 2020-2020 …, 2020 - ieeexplore.ieee.org
… fusing both channel-wise … -Frequency Network (TFNet) with channel attention (CA) and
non-local (NL) modules for ABE. The TFNet exploits the information from both time and frequency

Multi-level attention network: Mixed time–frequency channel attention and multi-scale self-attentive standard deviation pooling for speaker recognition

L Deng, F Deng, K Zhou, P Jiang, G Zhang… - … Applications of Artificial …, 2024 - Elsevier
… Therefore, we propose mixed time–frequency channel (MTFC) attention to capture global …
level attention (mixed time–frequency channel attention and multi-scale self-attention standard …

Orthonets: Orthogonal channel attention networks

H Salman, C Parks, M Swan… - 2023 IEEE International …, 2023 - ieeexplore.ieee.org
… We hypothesize that the choice of frequency plays only a supporting role and the primary …
of quality channel attention is filter diversity. • We propose to relocate the channel attention

Duality temporal-channel-frequency attention enhanced speaker representation learning

L Zhang, Q Wang, L Xie - 2021 IEEE Automatic Speech …, 2021 - ieeexplore.ieee.org
… Duality Temporal-Channel-Frequency (DTCF) attention mechanism after each … frequency
information into the channel-wise attention masks. Compared with other channel-wise attention

Deep learning based OFDM channel estimation using frequency-time division and attention mechanism

A Yang, P Sun, T Rakesh, B Sun… - 2021 IEEE Globecom …, 2021 - ieeexplore.ieee.org
… Abstract—In this paper, we propose a frequency-time division network (FreqTimeNet) to
improve the performance of deep learning (DL) based OFDM channel estimation. This Freq