Výsledky vyhledávání - vector-quantized variational autoencoder~

Leveraging Vector Quantized Variational Autoencoder for Accurate Synthetic Data Generation in Multivariate Time Series

Autoři: Mohammad Diqi Ema Utami Kusrini Kusrini a další

Zdroj: MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer. 24:423-438

Rapid Object Modeling Initialization for Vector Quantized-Variational AutoEncoder

Autoři: Michael Karnes Alper Yilmaz

Zdroj: 2025 IEEE International Conference on Image Processing (ICIP). :2402-2407

CrowdSurfer: Sampling Optimization Augmented with Vector-Quantized Variational AutoEncoder for Dense Crowd Navigation

Autoři: Kumar, Naman Singha, Antareep Nanwani, Laksh a další

Zdroj: 2025 IEEE International Conference on Robotics and Automation (ICRA). :16854-16860

Témata: FOS: Computer and information sciences, Computer Science - Robotics, Optimization and Control (math.OC), FOS: Mathematics, Mathematics - Optimization and Control, Robotics (cs.RO)

Přístupová URL adresa: http://arxiv.org/abs/2409.16011

S-HR-VQVAE: Sequential Hierarchical Residual Learning Vector Quantized Variational Autoencoder for Video Prediction

Autoři: Mohammad Adiban Kalin Stefanov Sabato Marco Siniscalchi a další

Zdroj: IEEE Transactions on Multimedia. 27:4321-4332

Témata: FOS: Computer and information sciences, Computer Science - Machine Learning, I.2.10, I.4.2, Computer Science - Artificial Intelligence, I.2.6, I.4.5, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, I.4.10, Machine Learning (cs.LG), Hierarchical Modeling, Video Prediction, Artificial Intelligence (cs.AI), Autoregressive Modeling, Settore IINF-05/A - Sistemi di elaborazione delle informazioni

Popis souboru: application/pdf

Přístupová URL adresa: http://arxiv.org/abs/2307.06701
https://hdl.handle.net/10447/672963

Attention-Guided Vector Quantized Variational Autoencoder for Brain Tumor Segmentation

Autoři: Danish Ali Ajmal Mian Naveed Akhtar a další

Zdroj: Lecture Notes in Computer Science ISBN: 9783032049261

Quaternion Vector Quantized Variational Autoencoder

Autoři: Hui Luo Xin Liu Jian Sun a další

Zdroj: IEEE Signal Processing Letters. 32:151-155

Generation of Ocular Anatomy and Disease Images Using Vector Quantized Variational Autoencoder for Image Quality Improvement and Feature Extraction

Autoři: Zuyan Zhang Jingyan Han Hou-Bin Huan

Zdroj: Journal of Circuits, Systems and Computers.

Predicting anatomical variations in radiotherapy with a vector quantized variational autoencoder generative model

Autoři: Yue Zou Zhenhao Li Menghan Zhang a další

Zdroj: Medical Physics. 52

Augmenting Training Data with Vector-Quantized Variational Autoencoder for Classifying RF Signals

Autoři: Kompella, Srihari Kamesh Davaslioglu, Kemal Sagduyu, Yalin E. a další

Zdroj: MILCOM 2024 - 2024 IEEE Military Communications Conference (MILCOM). :1-6

Témata: Computer Science - Networking and Internet Architecture, Networking and Internet Architecture (cs.NI), Signal Processing (eess.SP), FOS: Computer and information sciences, Computer Science - Machine Learning, FOS: Electrical engineering, electronic engineering, information engineering, Electrical Engineering and Systems Science - Signal Processing, Machine Learning (cs.LG)

Přístupová URL adresa: http://arxiv.org/abs/2410.18283

EGGesture: Entropy-Guided Vector Quantized Variational AutoEncoder for Co-Speech Gesture Generation

Autoři: Yiyong Xiao Kai Shu Haoyi Zhang a další

Zdroj: Proceedings of the 32nd ACM International Conference on Multimedia. :6113-6122

Decomposed Vector-Quantized Variational Autoencoder for Human Grasp Generation

Autoři: Zhe Zhao Mengshi Qi Huadong Ma

Zdroj: Lecture Notes in Computer Science ISBN: 9783031733963

Témata: Computer Science - Computer Vision and Pattern Recognition

Přístupová URL adresa: http://arxiv.org/abs/2407.14062

Weakly Supervised Marine Animal Detection from Remote Sensing Images Using Vector-Quantized Variational Autoencoder

Autoři: Pham, Minh-Tan Gangloff, Hugo Lefèvre, Sébastien a další

Přispěvatelé: Pham, Minh-Tan Gangloff, Hugo Lefèvre, Sébastien a další

Zdroj: IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium. :5559-5562

Témata: FOS: Computer and information sciences, aerial remote sensing, weakly-supervised learning, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, 14. Life underwater, Anomaly detection, marine animal monitoring, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing

Popis souboru: application/pdf

Přístupová URL adresa: http://arxiv.org/abs/2307.06720

Vector-Quantized Variational AutoEncoder for pansharpening

Autoři: Farid Talbi Miloud Chikr Elmezouar Elhocine Boutellaa a další

Zdroj: International Journal of Remote Sensing. 44:6329-6349

Attention-based vector quantized variational autoencoder for anomaly detection by using orthogonal subspace constraints

Autoři: Qien Yu Shengxin Dai Ran Dong a další

Zdroj: Pattern Recognition. 164:111500

Modeling Wound Healing Using Vector Quantized Variational Autoencoders and Transformers

Autoři: Backová, Lenka Bengoetxea, Guillermo Rogalla, Svana a další

Přispěvatelé: Backová, Lenka Bengoetxea, Guillermo Rogalla, Svana a další

Zdroj: Digital.CSIC. Repositorio Institucional del CSIC
Consejo Superior de Investigaciones Científicas (CSIC)

Témata: Video prediction, Wound healing, Deep learning, 3. Good health

Přístupová URL adresa: http://hdl.handle.net/10261/352620

Leveraging Vector-Quantized Variational Autoencoder Inner Metrics for Anomaly Detection

Autoři: Gangloff, Hugo Pham, Minh-Tan Courtrai, Luc a další

Přispěvatelé: Gangloff, Hugo Pham, Minh-Tan Courtrai, Luc a další

Zdroj: 2022 26th International Conference on Pattern Recognition (ICPR). :435-441

Témata: [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology

Přístupová URL adresa: https://hal.science/hal-03991178v1
https://doi.org/10.1109/icpr56361.2022.9956102

A Vector Quantized Masked Autoencoder for Speech Emotion Recognition

Autoři: Sadok, Samir Leglaive, Simon Séguier, Renaud

Přispěvatelé: Sadok, Samir Leglaive, Simon Séguier, Renaud

Zdroj: 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW). :1-5

Témata: Self-supervised learning, [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], FOS: Computer and information sciences, Computer Science - Machine Learning, Sound (cs.SD), masked autoencoder, [INFO.INFO-SD] Computer Science [cs]/Sound [cs.SD], [STAT.ML] Statistics [stat]/Machine Learning [stat.ML], Computer Science - Sound, Machine Learning (cs.LG), vector-quantized variational autoencoder, speech emotion recognition, Audio and Speech Processing (eess.AS), FOS: Electrical engineering, electronic engineering, information engineering, [SPI.SIGNAL] Engineering Sciences [physics]/Signal and Image processing, Electrical Engineering and Systems Science - Audio and Speech Processing

Popis souboru: application/pdf

Přístupová URL adresa: http://arxiv.org/abs/2304.11117
https://hal.science/hal-04080024v1/document
https://hal.science/hal-04080024v1

Hierarchical Residual Learning Based Vector Quantized Variational Autoencoder for Image Reconstruction and Generation

Autoři: Adiban M. Stefanov K. Siniscalchi S. M. a další

Témata: Settore ING-INF/05 - Sistemi Di Elaborazione Delle Informazioni, I.2, FOS: Computer and information sciences, Computer Science - Machine Learning, I.4, Computer Sciences, namely VQVAE and VQVAE-2. HR-VQVAE can also generate high-quality and diverse images that outper- form state-of-the-art generative models, Computer Vision and Pattern Recognition (cs.CV), the representations at each layer are hierarchically linked to those at previous layers. We evaluate our method on the tasks of image reconstruction and generation. Experimental results demonstrate that the discrete representations learned by HR-VQVAE enable the decoder to reconstruct high-quality images with less distortion than the baseline methods, Computer Science - Computer Vision and Pattern Recognition, 02 engineering and technology, each layer in HR-VQVAE learns a discrete representation of the residual from previous layers through a vector quantized encoder. Furthermore, We propose a multi-layer variational autoencoder method, we call HR-VQVAE, that learns hierarchical discrete representations of the data. By utilizing a novel objective function, each layer in HR-VQVAE learns a discrete representation of the residual from previous layers through a vector quantized encoder. Furthermore, the representations at each layer are hierarchically linked to those at previous layers. We evaluate our method on the tasks of image reconstruction and generation. Experimental results demonstrate that the discrete representations learned by HR-VQVAE enable the decoder to reconstruct high-quality images with less distortion than the baseline methods, namely VQVAE and VQVAE-2. HR-VQVAE can also generate high-quality and diverse images that outper- form state-of-the-art generative models, providing further verification of the efficiency of the learned representations. The hierarchical nature of HR-VQVAE i) reduces the decoing search time, making the method particularly suitable for high-load tasks and ii) allows to increase the codebook size without incurring the codebook collapse problem, that learns hierarchical discrete representations of the data. By utilizing a novel objective function, Machine Learning (cs.LG), 03 medical and health sciences, Datavetenskap (datalogi), 0302 clinical medicine, We propose a multi-layer variational autoencoder method, providing further verification of the efficiency of the learned representations. The hierarchical nature of HR-VQVAE i) reduces the decoing search time, making the method particularly suitable for high-load tasks and ii) allows to increase the codebook size without incurring the codebook collapse problem, 0202 electrical engineering, electronic engineering, information engineering, we call HR-VQVAE

Popis souboru: application/pdf

Přístupová URL adresa: http://arxiv.org/abs/2208.04554
https://hdl.handle.net/10447/637533
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-324770

STORM: A Spatio-Temporal Factor Model Based on Dual Vector Quantized Variational Autoencoders for Financial Trading

Autoři: Zhao, Yilei Zhang, Wentao Yang, Tingran a další

Témata: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, text

URL: http://arxiv.org/abs/2412.09468

FactorVQVAE: Discrete latent factor model via Vector Quantized Variational Autoencoder

Autoři: Namhyoung Kim Seung Eun Ock Jae Wook Song

Zdroj: Knowledge-Based Systems. 318:113460