Showing 1-25 of 3,116 resultsfor "Index Terms":Self-attention Module
"Index Terms":Self-attention Module
- Sort
Get notified when new research is published matching your search criteria.
Sort By
Results
GS-Net: Global Self-Attention Guided CNN for Multi-Stage Glaucoma Classification
2023 IEEE International Conference on Image Processing (ICIP)
Year: 2023 | Conference Paper |
Cited by: Papers (2)
Glaucoma is a common eye disease that leads to irreversible blindness unless timely detected. Hence, glaucoma detection at an early stage is of utmost importance for a better treatment plan and ultimately saving the vision. The recent literature has shown the prominence of CNN-based methods to detect glaucoma from retinal fundus images. However, such methods mainly focus on solving binary classifi...Show More
Self-Attention Relation Network for Few-Shot Learning
2019 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)
Year: 2019 | Conference Paper |
Cited by: Papers (34)
The success of deep learning greatly attributes to massive data with accurate labels. However, for few shot learning, especially zero shot learning, deep models cannot be well trained in that there are few available labeled samples. Inspired by human visual system, attention models have been widely used in action recognition, instance segmentation, and other vision tasks by introducing spatial, te...Show More
Spectral–Spatial Self-Attention Networks for Hyperspectral Image Classification
Xuming Zhang;Genyun Sun;Xiuping Jia;Lixin Wu;Aizhu Zhang;Jinchang Ren;Hang Fu;Yanjuan Yao
This study presents a spectral–spatial self-attention network (SSSAN) for classification of hyperspectral images (HSIs), which can adaptively integrate local features with long-range dependencies related to the pixel to be classified. Specifically, it has two subnetworks. The spatial subnetwork introduces the proposed spatial self-attention module to exploit rich patch-based contextual information...Show More
Linkage Transformer: an Attention Based Neural Network for Multi-Cell Traffic Prediction
Zhenqian Wang;Meixia Fu;Qu Wang;Yifan Lu;Jiansheng Wu;Le Chen;Wanqing Guan;Wei Li;Jianquan Wang
2023 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)
Year: 2023 | Conference Paper |
Cited by: Papers (1)
With the growing complexity of base station network, the research of traffic prediction has attracted increasingly attention in the world. Especially, artificial intelligence technology is applied to traffic prediction, which plays important role in communication system. In this article, we propose a Linkage Transformer model for multi-cell traffic prediction, which contains three main procedures....Show More
UGAN-GSAM-IT: Unsupervised Generative Adversarial Network with Generative Self-Attention Method for Image Translation
2023 4th International Conference on Computer Vision, Image and Deep Learning (CVIDL)
Year: 2023 | Conference Paper |
The unsupervised image translation is the core task of computer image processing, spanning a variety of real-world application scenarios, and constitutes an important branch of computer vision research orientations. In image translation tasks with significant geometric variations, conventional image translation algorithms have led to the generation of low-quality images due to unstable training. T...Show More
HSAN: A Hierarchical Self-Attention Network for Multi-Turn Dialogue Generation
ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2021 | Conference Paper |
Cited by: Papers (10)
In the multi-turn dialogue system, response generation is not only related to the sentences in context but also relies on the words in each utterance. Although there are lots of methods that pay attention to model words and utterances, there still exist problems such as tending to generate common responses. In this paper, we propose a hierarchical self-attention network, named HSAN, which attends ...Show More
Research on Lightweight High-resolution Network Human Pose Estimation Based on Self-attention
2023 IEEE 8th International Conference on Big Data Analytics (ICBDA)
Year: 2023 | Conference Paper |
At present, when deep learning networks in the field of human pose estimation improve prediction accuracy, often accompany the improvement of network structure complexity, which brings about the improvement of network model parameters and computational complexity, making it difficult to deploy on devices with small computing power for practical application. On the basis of HRNet, this paper devise...Show More
End-to-End Deblending of Simultaneous Source Data Using Transformer
Shaohuan Zu;Chaofan Ke;Chengzhi Hou;Junxing Cao;Hongjing Zhang
Simultaneous source acquisition is becoming more promising than the traditional seismic acquisition by firing multiple sources with a short interval time, which improves acquisition efficiency and enhances data quality. However, the blended interference severely obscures the coherent signal, challenging the conventional seismic data processing methods. Recently, convolution neural network (CNN) ha...Show More
Eddy Current Array for Defects Detection based on Spatiotemporal Self-attention Network
2022 International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD)
Year: 2022 | Conference Paper |
Cited by: Papers (1)
Unlike single eddy current coil, eddy current array (ECA) which arranges multiple eddy current coils in a certain way, has the property of higher accuracy and efficiency to detect defects. The process of eddy current array collecting data own naturally spatial and temporal characteristics. In this paper, we introduce spatiotemporal self-attention mechanism to ECA Testing, and propose a spatiotempo...Show More
Saladnet: Self-Attentive Multisource Localization in the Ambisonics Domain
Pierre-Amaury Grumiaux;Srđan Kitić;Prerak Srivastava;Laurent Girin;Alexandre Guérin
2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)
Year: 2021 | Conference Paper |
Cited by: Papers (5)
In this work, we propose a novel self-attention based neural network for robust multi-speaker localization from Ambisonics recordings. Starting from a state-of-the-art convolutional recurrent neural network, we investigate the benefit of replacing the recurrent layers by self-attention encoders, inherited from the Transformer architecture. We evaluate these models on synthetic and real-world data,...Show More
Software Defect Prediction Method Based on Transformer Model
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)
Year: 2021 | Conference Paper |
Cited by: Papers (2)
Aiming at the problem of grammar and semantic information understanding of the network structure of software system, this paper proposes a method of software defect prediction, which is based on Transformer model, which is completely dependent on self-attention mechanism, it can embed key information in the code semantics of the end-to-end learning software modules. Firstly, the software module is...Show More
Periodicity Estimation Method for RCS Sequence based on Convolution Self-Attention Network
2021 CIE International Conference on Radar (Radar)
Year: 2021 | Conference Paper |
The RCS (Radar cross section) sequence usually contains the periodicity of the motion of the space target because of their stable or rolling attitude. However, the measured data are inevitably disturbed by various reasons. Most traditional period estimation methods require high data quality. In this paper, we propose a periodicity estimation method for RCS sequence using convolution self-attention...Show More
Super-Resolution and Self-Attention with Generative Adversarial Network for Improving Malignancy Characterization of Hepatocellular Carcinoma
Yunling Li;Hui Huang;Lijuan Zhang;Guangyi Wang;Honglai Zhang;Wu Zhou
2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI)
Year: 2020 | Conference Paper |
Cited by: Papers (8)
The slice thickness of MR imaging may remarkably degrade the clarity of 3D lesion images within through-plane slices (coronal or sagittal views) so as to influence the performance of lesion characterization. To alleviate the problem, we propose an end-to-end super-resolution and self-attention framework based on Generative adversarial networks (GAN) for improving the malignancy characterization of...Show More
Global-Local Awareness Network for Image Super-Resolution
2023 IEEE International Conference on Image Processing (ICIP)
Year: 2023 | Conference Paper |
Deep-net models based on self-attention, such as Swin Transformer, have achieved great success for single image super-resolution (SISR). While self-attention excels at modeling global information, it is less effective at capturing high frequencies (e.g., edges etc.) that deliver local information primarily, which is crucial for SISR. To tackle this, we propose a global-local awareness network (GLA...Show More
Hybrid Attention Module and Transformer Based Fuze DRFM Jamming Signal Recognition
Jikai Yang;Zhiquan Bai;Zhaoxia Xian;Hongwu Xiang;Jingxin Li;Huili Hu;Jian Dai;Xinhong Hao
The fuze system is usually affected by jamming signals, especially the digital radio frequency memory (DRFM) based jamming signals. In this letter, we propose a recognition method for the fuze DRFM jamming signals based on hybrid attention module (HAM) and Transformer. Specifically, we first build a backbone network with the combination of the convolutional neural network (CNN) and the Transformer...Show More
Spatio-Temporal Slowfast Self-Attention Network For Action Recognition
2020 IEEE International Conference on Image Processing (ICIP)
Year: 2020 | Conference Paper |
Cited by: Papers (17)
We propose Spatio-Temporal SlowFast Self-Attention network for action recognition. Conventional Convolutional Neural Networks have the advantage of capturing the local area of the data. However, to understand a human action, it is appropriate to consider both human and the overall context of given scene. Therefore, we repurpose a self-attention mechanism from Self-Attention GAN (SAGAN) to our mode...Show More
Video Description Model Based on Feature Reinforcement and Knowledge Supplement
2024 IEEE 7th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)
Year: 2024 | Conference Paper |
The video captured in low illumination environment often has low contrast, much noise, unclear details and other problems, which seriously affects the subsequent target detection, segmentation and other computer vision tasks. Most of the existing low-light video enhancement methods are built based on convolutional neural networks. Because convolutional can not make full use of the long-term depend...Show More
Self-attention Mechanism and Pyramid Feature Fusion for Point Cloud Segmentation
2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan)
Year: 2023 | Conference Paper |
This study introduces RandLASAMP-Net as an advanced version of RandLA-Net, designed to facilitate efficient per-point semantics inference for large-scale 3D point clouds. Existing algorithms encounter difficulties in processing large point clouds due to costly sampling or pre/post-processing necessities. To enhance the feature aggregation module of RandLA-Net, which relies on a rudimentary attenti...Show More
Cleaning Up Mislabeled Data via Image Plotting Method and Self-Attention Module
2022 22nd International Conference on Control, Automation and Systems (ICCAS)
Year: 2022 | Conference Paper |
This paper proposes the method for cleaning up label noise in multivariate time-series outlier data. An image plotting method is proposed to reflect the tendency of original time-series data. The image data generated from the plotting method shows effectiveness, since the data can be smoothly utilized in label noise cleaning process and easy to analyze. To verify the availability of plotted data, ...Show More
ISANet: An Interactive Self-attention Network for Cropland Image Change Detection
2024 IEEE 18th International Conference on Control & Automation (ICCA)
Year: 2024 | Conference Paper |
The change detection task is a vital research topic in the remote sensing area, particularly significant in the context of agricultural land monitoring. Currently, many researchers perform change detection tasks based on the self-attention mechanism. A common method involves applying a self-attention mechanism within single-temporal images, then fusing the feature maps of bitemporal images to deco...Show More
Dual-stream Self-attention Network for Image Captioning
2022 IEEE International Conference on Visual Communications and Image Processing (VCIP)
Year: 2022 | Conference Paper |
Cited by: Papers (2)
Self-attention based encoder-decoder models achieve dominant performance in image captioning. However, most existing image captioning models (ICMs) only focus on modeling the relation between spatial tokens, while channel-wise attention is neglected for getting visual representation. Considering that different channels of visual representation usually denote different visual objects, it may lead t...Show More
A Self-Attention based Network for Low Resolution Multi-View Stereo
2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)
Year: 2023 | Conference Paper |
Cited by: Papers (1)
We present SA-MVSNet, a novel two-stage multi-view stereo network equipped with self-attention mechanism, which can improve the quality of low-resolution image 3D reconstruction. SA-MVSNet consists of two stages, and the lower resolution depth maps predicted in the first stage provide a priori information for the second stage. To increase the utilization of image information, a pyramid scheme was ...Show More
Improving Fastspeech TTS with Efficient Self-Attention and Compact Feed-Forward Network
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2022 | Conference Paper |
FastSpeech, as a feed-forward transformer based TTS, can avoid the slow serial, autoregressive inference to generate the target mel-spectrogram in a parallel way. As a non-autoregressive TTS, the latency and computation load in inference is shifted from vocoder to transformer where the efficiency is limited by the quadratic time and memory complexity in the self-attention mechanism, particularly f...Show More
Multi-Field De-Interlacing Using Deformable Convolution Residual Blocks and Self-Attention
2022 IEEE International Conference on Image Processing (ICIP)
Year: 2022 | Conference Paper |
Cited by: Papers (1)
Although deep learning has made significant impact on image/video restoration and super-resolution, learned deinterlacing has so far received less attention in academia or industry. This is despite deinterlacing is well-suited for supervised learning from synthetic data since the degradation model is known and fixed. In this paper, we propose a novel multi-field full frame-rate deinterlacing netwo...Show More
The post-equalizer in the Underwater Visible Light Communication (UVLC) system can overcome the nonlinear distortion existing in the system. The existing nonlinear post-equalizer based on deep learning still has problems such as the number of data nodes has a great influence on the effect, the equalization effect decreases significantly when the data rate becomes higher and too complex a model lea...Show More
IEEE Account
Purchase Details
Profile Information
Need Help?
- US & Canada: +1 800 678 4333
- Worldwide: +1 732 981 0060
- Contact & Support
- About IEEE Xplore
- Contact Us
- Help
- Accessibility
- Terms of Use
- Nondiscrimination Policy
- Sitemap
- Privacy & Opting Out of Cookies
A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.