Výsledky vyhledávání - "vector-quantized variational autoencoder"

Robust Semantic Communications with Masked VQ-VAE Enabled Codebook Autor Hu, Qiyu, Zhang, Guangyi, Qin, Zhijin, Cai, Yunlong, Yu, Guanding, Li, Geoffrey Ye

“…Although semantic communications have exhibited satisfactory performance on a large number of tasks, the impact of semantic noise and the robustness of the…”
Získat plný text

Attention-based vector quantized variational autoencoder for anomaly detection by using orthogonal subspace constraints Autor Yu, Qien, Dai, Shengxin, Dong, Ran, Ikuno, Soichiro

“…This paper introduces a new framework that uses a vector quantized variational autoencoder (VQVAE) enhanced by orthogonal subspace constraints (OSC) and…”
Získat plný text

Unsupervised brain imaging 3D anomaly detection and segmentation with transformers Autor Pinaya, Walter H.L., Tudosiu, Petru-Daniel, Gray, Robert, Rees, Geraint, Nachev, Parashkev, Ourselin, Sebastien, Cardoso, M. Jorge

“…•We develop transformers for unsupervised brain imaging anomaly detection.•Our approach combines a VQ-VAE with an ensemble of autoregressive…”
Získat plný text

Frequency enhanced vector quantized variational autoencoder for structural vibration response compression Autor Xue, Zhilin, An, Yonghui, Ou, Jinping

“…•The frequency enhanced vector quantized variational autoencoder (FEVQVAE) is proposed for structural vibration response compression.•The proposed dual-branch…”
Získat plný text

Stochastic human motion prediction using a quantized conditional diffusion model Autor Huang, Biaozhang, Li, Xinde, Hu, Chuanfei, Li, Heqing

“…Human motion prediction is a fundamental task in computer vision, aiming to forecast future human poses based on observed motion sequences. Existing…”
Získat plný text

Unsupervised fabric defect detection algorithm based on vector quantization and feature distance Autor Wei, Qiyu, Zhang, Lei, Zhan, Zhu, Li, Liqing, Wang, Jun

“…Fabric defect detection is an indispensable step in textile fabric production, and many deep-learning-based methods have been proposed. However, existing…”
Získat plný text

SVQ-VAE: Federated-Learning-Based Semantic-Aware Communication for Vehicular Networks Autor Jin, Zhu, Li, Yundi, Song, Tiecheng, Jia, Wen-Kang, Song, Xiaoqin

“…The integration of semantic communication technology into intelligent vehicular networks represents a promising research direction, as it significantly reduces…”
Získat plný text

Microstructure Estimation by Combining Deep Learning and Phase Transformation Model Autor Aihara, Syuji, Inoue, Junya, Noguchi, Satoshi

“…In material design, the establishment of process–structure–property relationship is crucial for analyzing and controlling material microstructures. For the…”
Získat plný text

Microstructure estimation by combining deep learning and phase transformation model Autor Inoue, Junya, Noguchi, Satoshi, Aihara, Syuji

“…In material design, the establishment of process–structure–property relationship is crucial for analyzing and controlling material microstructures. For the…”
Získat plný text

Free Space Optical Semantic Communication for Satellite Remote Sensing Image Transmission Autor Chen, Wenbin, Ju, Cheng, Yuan, Tianxing, Zhan, Yueying, Zhang, Min, Wang, Danshi

“…To further improve the transmission efficiency and link stability for free space optical (FSO)-based satellite communication (SatCom) systems when transmitting…”
Získat plný text

Entropy-Constrained VQ-VAE for Deep-Learning-Based CSI Feedback Autor Shin, Junyong, Park, Jinsung, Jeon, Yo-Seb

“…Deep-learning (DL)-based channel state information (CSI) feedback has attracted a great deal of attention due to its effectiveness in compressing CSI in…”
Získat plný text

Quaternion Vector Quantized Variational Autoencoder Autor Luo, Hui, Liu, Xin, Sun, Jian, Zhang, Yang

“…Vector quantized variational autoencoders, as variants of variational autoencoders, effectively capture discrete representations by quantizing continuous…”
Získat plný text

Remembering without (representational) memory: a neuro-computational study on regaining categoricity and compositionality from minimal traces Autor Fayyaz, Zahra, Righetti, Francesca, Wiskott, Laurenz, Werning, Markus

Získat plný text

PCGen: A Fully Parallelizable Point Cloud Generative Model Autor Vercheval, Nicolas, Royen, Remco, Munteanu, Adrian, Pižurica, Aleksandra

“…Generative models have the potential to revolutionize 3D extended reality. A primary obstacle is that augmented and virtual reality need real-time computing…”
Získat plný text

Erratum: Latent space improved masked reconstruction model for human skeleton-based action recognition

“…[This corrects the article DOI: 10.3389/fnbot.2025.1482281.]…”
Získat plný text

Robust and adaptive semantic noise for complex secure communication networks Autor Cai, Yao

“…Privacy protection and robust transmission play critical roles in secure semantic communication, especially in open wireless environments with the presence of…”
Získat plný text

Latent space improved masked reconstruction model for human skeleton-based action recognition Autor Enqing Chen, Xueting Wang, Xin Guo, Ying Zhu, Dong Li

“…Human skeleton-based action recognition is an important task in the field of computer vision. In recent years, masked autoencoder (MAE) has been used in…”
Získat plný text

深層学習と相変態モデルの融合による微細組織推定 Autor 粟飯原, 周二, 野口, 聖史, 井上, 純哉

Získat plný text

Compression-enhanced Three-Pass Protocol for secure and bandwidth-efficient image transmission Autor Abdelfattah, Mohamed G., Elnakib, Ahmed, Hegazy, Salem F.

“…Key-based cryptography faces persistent challenges in secure key distribution and newly rising vulnerabilities. Three-Pass Protocols (3PPs) tackle these issues…”
Získat plný text

Reviving Legacy Seismic Data via Machine Learning Technique-Part 2: Estimating 3-D Seismic Volumes From 2-D Seismic Lines With VQ-VAE Autor Lee, Jun-Woo, Je Lee, Min, Min, Dong-Joo, Cho, Yongchae

“…We propose a machine learning-based method that estimates a 3-D seismic volume from irregularly placed 2-D seismic lines, addressing the challenges regarding…”
Získat plný text