Výsledky vyhledávání - "Masked autoencoder"

  1. 1

    Topology-Guided Graph Masked Autoencoder Learning for Population-Based Neurodevelopmental Disorder Diagnosis Autor Li, Yueying, Zhang, Xiaotong, Guan, Shihan, Ma, Guolin, Kong, Youyong

    ISSN: 1534-4320, 1558-0210, 1558-0210
    Vydáno: United States IEEE 01.01.2025
    “…-individual associations in population. To solve these problems, this work proposes a novel approach for detecting abnormal neural circuits associated with brain diseases, named Topology-guided Graph Masked autoencoder Learning method (TGML…”
    Získat plný text
    Journal Article
  2. 2

    MAE-EEG-Transformer: A transformer-based approach combining masked autoencoder and cross-individual data augmentation pre-training for EEG classification Autor Cai, Miao, Zeng, Yu

    ISSN: 1746-8094
    Vydáno: Elsevier Ltd 01.08.2024
    “…Convolutional neural networks (CNN) may not be ideal for extracting global temporal features from non-stationary Electroencephalogram (EEG) signals. The…”
    Získat plný text
    Journal Article
  3. 3
  4. 4

    Fine-Tuned Visual Transformer Masked Autoencoder Applied for Anomaly Detection in Satellite Images Autor Gajda, Jakub, Kwiecień, Joanna

    ISSN: 2076-3417, 2076-3417
    Vydáno: Basel MDPI AG 01.06.2025
    Vydáno v Applied sciences (01.06.2025)
    “… A Transformer Masked Autoencoder was fine-tuned for a custom satellite image dataset after being pre-trained on the ImageNet subset…”
    Získat plný text
    Journal Article
  5. 5

    WAVELET2VEC: A Filter Bank Masked Autoencoder for EEG-Based Seizure Subtype Classification Autor Peng, Ruimin, Zhao, Changming, Xu, Yifan, Jiang, Jun, Kuang, Guangtao, Shao, Jianbo, Wu, Dongrui

    ISSN: 2379-190X
    Vydáno: IEEE 04.06.2023
    “…Electroencephalogram (EEG) based seizure subtype classification plays an important role in clinical diagnostics. However, existing deep learning approaches…”
    Získat plný text
    Konferenční příspěvek
  6. 6

    EEG generalizable representations learning via masked fractional fourier domain modeling Autor Zhang, Shubin, An, Dong, Liu, Jincun, Wei, Yaoguang

    ISSN: 1568-4946
    Vydáno: Elsevier B.V 01.02.2025
    Vydáno v Applied soft computing (01.02.2025)
    “… To improve the generalization ability of pre-trained models, we propose a novel masked autoencoder based on fractional Fourier…”
    Získat plný text
    Journal Article
  7. 7

    DMAE-EEG: A Pretraining Framework for EEG Spatiotemporal Representation Learning Autor Zhang, Yifan, Yu, Yang, Li, Hao, Wu, Anqi, Chen, Xin, Liu, Jinfang, Zeng, Ling-Li, Hu, Dewen

    ISSN: 2162-237X, 2162-2388, 2162-2388
    Vydáno: United States IEEE 01.10.2025
    “… To address these challenges, we develop a pretraining framework named DMAE-EEG, a denoising masked autoencoder for mining generalizable spatiotemporal representation from massive unlabeled EEG…”
    Získat plný text
    Journal Article
  8. 8
  9. 9

    Masked Autoencoder with Swin Transformer Network for Mitigating Electrode Shift in HD-EMG-based Gesture Recognition Autor Laamerad, Kasra, Shabanpour, Mehran, Islam, Md Rabiul, Mohammadi, Arash

    ISSN: 2331-8422
    Vydáno: Ithaca Cornell University Library, arXiv.org 07.10.2024
    Vydáno v arXiv.org (07.10.2024)
    “… In this context, the paper proposes the Masked Autoencoder with Swin Transformer (MAST) framework, where training is performed on a masked subset of HDsEMG channels…”
    Získat plný text
    Paper
  10. 10

    Uncovering cognitive taskonomy through transfer learning in masked autoencoder-based fMRI reconstruction Autor Qu, Youzhi, Xia, Junfeng, Xinyao Jian, Li, Wendu, Peng, Kaining, Liang, Zhichao, Wu, Haiyan, Liu, Quanying

    ISSN: 2331-8422
    Vydáno: Ithaca Cornell University Library, arXiv.org 24.05.2024
    Vydáno v arXiv.org (24.05.2024)
    “… Here, we employ the masked autoencoder (MAE) model to reconstruct functional magnetic resonance imaging (fMRI…”
    Získat plný text
    Paper
  11. 11

    Multi-Scale Masked Autoencoders for Cross-Session Emotion Recognition Autor Pang, Miaoqi, Wang, Hongtao, Huang, Jiayang, Vong, Chi-Man, Zeng, Zhiqiang, Chen, Chuangquan

    ISSN: 1534-4320, 1558-0210, 1558-0210
    Vydáno: United States IEEE 2024
    “… challenges in developing subject-specific cross-session emotion recognition models. To simultaneously address these challenges, we propose a unified pre-training framework based on multi-scale masked autoencoders (MSMAE…”
    Získat plný text
    Journal Article
  12. 12

    Visual prediction method based on time series-driven LSTM model Autor Jumahong, Huxidan, Wang, Yongjie, Aili, Abuduwaili, Wang, Weina

    ISSN: 2045-2322, 2045-2322
    Vydáno: London Nature Publishing Group UK 30.10.2025
    Vydáno v Scientific reports (30.10.2025)
    “…Significant progress has been made in time series prediction and image processing problems. However, most of the studies have focused on either the field of…”
    Získat plný text
    Journal Article
  13. 13

    Self Pre-Training with Adaptive Mask Autoencoders for Variable-Contrast 3D Medical Imaging Autor Das, Badhan Kumar, Zhao, Gengyan, Liu, Han, Re, Thomas J., Comaniciu, Dorin, Gibson, Eli, Maier, Andreas

    ISSN: 1945-8452
    Vydáno: IEEE 14.04.2025
    “… To address this limitation, we propose a 3D Adaptive Masked Autoencoders (AMAE) architecture that accommodates a variable number of 3D input contrasts per subject…”
    Získat plný text
    Konferenční příspěvek
  14. 14

    Exploring Long-Sequence Masked Autoencoders Autor Hu, Ronghang, Debnath, Shoubhik, Xie, Saining, Chen, Xinlei

    ISSN: 2331-8422
    Vydáno: Ithaca Cornell University Library, arXiv.org 13.10.2022
    Vydáno v arXiv.org (13.10.2022)
    “… In contrast to discrete tokens in natural languages, the input for image MAE is continuous and subject to additional specifications…”
    Získat plný text
    Paper
  15. 15

    Spotting Suspicious Academic Citations Using Self-Learning Graph Transformers Autor Avros, Renata, Haim, Mor Ben, Madar, Almog, Ravve, Elena, Volkovich, Zeev

    ISSN: 2227-7390, 2227-7390
    Vydáno: Basel MDPI AG 01.03.2024
    Vydáno v Mathematics (Basel) (01.03.2024)
    “… This method utilizes perturbations of a deep embedding model, integrating Graph-Masked Autoencoders to merge textual information with evidence of graph connectivity…”
    Získat plný text
    Journal Article
  16. 16

    Privacy Protection in MRI Scans Using 3D Masked Autoencoders Autor Lennart Alexander Van der Goten, Smith, Kevin

    ISSN: 2331-8422
    Vydáno: Ithaca Cornell University Library, arXiv.org 18.03.2024
    Vydáno v arXiv.org (18.03.2024)
    “… to possibly identify the subject by cross-referencing a database. Data anonymization and de-identification is concerned with ensuring the privacy and confidentiality of individuals' personal information…”
    Získat plný text
    Paper
  17. 17

    Fluid Antenna System Liberating Multiuser MIMO for ISAC via Deep Reinforcement Learning Autor Wang, Chao, Li, Guo, Zhang, Haibin, Wong, Kai-Kit, Li, Zan, Ng, Derrick Wing Kwan, Chae, Chan-Byoung

    ISSN: 1536-1276, 1558-2248
    Vydáno: New York IEEE 01.09.2024
    “…) to maximize the sum-rate of the downlink users subject to a sensing constraint. The unique feature of this setup is that the locations of the antenna ports at the FAS can be optimized jointly with the precoding design to achieve a higher sum-rate…”
    Získat plný text
    Journal Article
  18. 18
  19. 19

    Multi-View Self-Supervised Domain Adaptation for EEG-Based Emotion Recognition Autor Zhang, Lu, Shi, Hanwen, Li, Ziyi, Zheng, Wei-Long, Lu, Bao-Liang

    ISSN: 1949-3045, 1949-3045
    Vydáno: Piscataway IEEE 2025
    “… the last two problems mentioned above. Specifically, we add a multi-class domain discriminator to construct the adversarial relationship between the sub-networks so that distribution discrepancy of different subjects can be reduced effectively…”
    Získat plný text
    Journal Article
  20. 20

    Gram: A Large-Scale General EEG Model for Raw Data Classification and Restoration Tasks Autor Li, Ziyi, Zheng, Wei-Long, Lu, Bao-Liang

    ISSN: 2379-190X
    Vydáno: IEEE 06.04.2025
    “…) The second stage features a multi-view layer-fusion masked autoencoder that exploits EEG's complex Temporal and Spectral views through dual training objectives…”
    Získat plný text
    Konferenční příspěvek