Výsledky vyhledávání - "encoder–decoder architecture"

ST-3DView: Multi-Scale Contrast-Enhanced 3D Point Cloud Reconstruction of Single-View Objects From Video Scene Transition

Autoři: Dipanita Chakraborty Werapon Chiracharit Kosin Chamnongthai

Zdroj: IEEE Access, Vol 13, Pp 69596-69618 (2025)

Témata: 3D neural network, 3D reconstruction, object segmentation, Electrical engineering. Electronics. Nuclear engineering, scene transition detection, encoder-decoder architecture, point cloud, TK1-9971

Přístupová URL adresa: https://doaj.org/article/9fc22eed249e49a7aa1ba7cd65bced3f

Optical Chemical Structure Recognition Based on Multi-order Gated Aggregation Network

Autoři: LIN Fan, LI Jianhua

Zdroj: Jisuanji gongcheng, Vol 51, Iss 8, Pp 364-372 (2025)

Témata: optical chemical structure recognition (ocsr), encoder-decoder architecture, deep learning, smiles notation, multi-order gated aggregation network(moganet), Computer engineering. Computer hardware, TK7885-7895, Computer software, QA76.75-76.765

Popis souboru: electronic resource

Relation: https://www.ecice06.com/fileup/1000-3428/PDF/jsjgc-51-8-364.pdf; https://doaj.org/toc/1000-3428

Přístupová URL adresa: https://doaj.org/article/ac24a0abc25c4d05abe843b605028679

Enhancing SPARQL query generation for question answering with a hybrid encoder–decoder and cross-attention model

Autoři: Yi-Hui Chen Eric Jui-Lin Lu Kwan-Ho Cheng

Zdroj: Web Semantics, Vol 87, Iss , Pp 100869- (2025)

Témata: Neural Machine Translation (NMT), Text-to-SPARQL, Encoder–decoder architecture, Cross attention mechanism, Information resources (General), ZA3040-5185, Management information systems, T58.6-58.62

Popis souboru: electronic resource

Relation: http://www.sciencedirect.com/science/article/pii/S1570826825000101; https://doaj.org/toc/1570-8268

Přístupová URL adresa: https://doaj.org/article/88a73e232d0c440c835a7cb3d2096262

CWRepViT-Net: An encoder-decoder deep learning framework with RepViT blocks for crop weed semantic segmentation in soybean fields through their life journey

Autoři: Masoomeh Gomroki Dilshan Benaragama Christopher James Henry a další

Zdroj: Smart Agricultural Technology, Vol 12, Iss , Pp 101472- (2025)

Témata: Crop and weed semantic segmentation, Soybean, Encoder-decoder architecture, RepViT, Precision agriculture, Agriculture (General), S1-972, Agricultural industries, HD9000-9495

Popis souboru: electronic resource

Relation: http://www.sciencedirect.com/science/article/pii/S2772375525007038; https://doaj.org/toc/2772-3755

Přístupová URL adresa: https://doaj.org/article/65fcf468bd8a474588d2a70f2631dc70

Short-term load forecasting by a hybrid attention scheme: Multi-feature attention and context awareness

Autoři: Fang Su Hao Tang Shengchun Yang a další

Zdroj: International Journal of Electrical Power & Energy Systems, Vol 172, Iss , Pp 111065- (2025)

Témata: Context awareness, Encoder–decoder architecture, Multi-feature attention, Short-term load forecasting, Production of electric energy or power. Powerplants. Central stations, TK1001-1841

Popis souboru: electronic resource

Relation: http://www.sciencedirect.com/science/article/pii/S0142061525006131; https://doaj.org/toc/0142-0615

Přístupová URL adresa: https://doaj.org/article/f8204336f2d846928d555efa4b3bcf75

Transformer Encoder–Decoder Framework for Nonlinear Pulse Evolution and Inverse Modeling

Autoři: Dinesh Kumar Murugan Rajkumar Joseph Nithyanandan Kanagaraj

Zdroj: Advanced Photonics Research, Vol 6, Iss 11, Pp n/a-n/a (2025)

Témata: deep learning, encoder–decoder architecture, nonlinear pulse evolution, optical fibers, supercontinuum generation, transformer neural networks, Applied optics. Photonics, TA1501-1820, Optics. Light, QC350-467

Popis souboru: electronic resource

Relation: https://doaj.org/toc/2699-9293

Přístupová URL adresa: https://doaj.org/article/22b4cb514d8b494b809885762237bae3

Analysis of the effectiveness of two different loss functions in training a neural network in lung image reconstruction using impedance tomography

Autoři: Malgorzata Lalak-Dybała Barbara Stefaniak Paweł Olszewski

Zdroj: Journal of Modern Science, Vol 57, Iss 3, Pp 594-608 (2024)

Témata: 0301 basic medicine, neural network with encoder-decoder architecture, 03 medical and health sciences, resnet, 0202 electrical engineering, electronic engineering, information engineering, convolutional neural network, Social Sciences, 02 engineering and technology, lung reconstruction, electrical impedance tomography

Přístupová URL adresa: https://doaj.org/article/080fe2c0e5ff4f89b9924bad2ae2f2e4

MPOCSR: optical chemical structure recognition based on multi-path Vision Transformer

Autoři: Fan Lin Jianhua Li

Zdroj: Complex & Intelligent Systems, Vol 10, Iss 6, Pp 7553-7563 (2024)

Témata: 0301 basic medicine, 03 medical and health sciences, Optical chemical structure recognition, Multi-path Vision Transformer, Encoder–decoder architecture, Electronic computers. Computer science, Deep learning, QA75.5-76.95, Information technology, T58.5-58.64, 01 natural sciences, 0104 chemical sciences

Přístupová URL adresa: https://doaj.org/article/22d13e77b8da4cedb58e336ff95e3a3f

TST: Tree Structured Transformer for Handwritten Mathematical Expression Recognition

Autoři: Xie, Yejing Mouchère, Harold Image Perception Interaction (LS2N - équipe IPI) a další

Přispěvatelé: Xie, Yejing Mouchère, Harold Image Perception Interaction (LS2N - équipe IPI) a další

Zdroj: ICDAR 2025 ; https://hal.science/hal-05154311 ; ICDAR 2025, Sep 2025, Wuhan, China

Témata: Handwritten Mathematical Expression Recognition Tree Transformer Handwriting Recognition Encoder-Decoder Architecture, Handwritten Mathematical Expression Recognition, Tree Transformer, Handwriting Recognition, Encoder-Decoder Architecture, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]

Geografické téma: Wuhan, China

Dostupnost: https://hal.science/hal-05154311
https://hal.science/hal-05154311v1/document
https://hal.science/hal-05154311v1/file/43.pdf

Research on prediction of nanocrystalline alloy hysteresis properties based on long short-term memory network

Autoři: Hailin Li Bo Zhang Yongpeng Shen a další

Zdroj: Scientific Reports, Vol 15, Iss 1, Pp 1-11 (2025)

Témata: Magnetic hysteresis characteristic, Data-driven, Long short-term memory network, Encoder–decoder architecture, Medicine, Science

Popis souboru: electronic resource

Relation: https://doaj.org/toc/2045-2322

Přístupová URL adresa: https://doaj.org/article/43593bc1d62f4347a082fd4de88d368c

HMSA-Net: A Hierarchical Multi-Scale Attention Network for Brain Tumor Segmentation From Multi-Modal MRI

Autoři: Gayathri Ramasamy Tripty Singh Xiaohui Yuan a další

Zdroj: IEEE Access, Vol 13, Pp 167672-167683 (2025)

Témata: Attention mechanisms, brain tumor segmentation, deep learning, encoder–decoder architecture, hierarchical multi-scale attention, magnetic resonance imaging (MRI), Electrical engineering. Electronics. Nuclear engineering, TK1-9971

Popis souboru: electronic resource

Relation: https://ieeexplore.ieee.org/document/11151976/; https://doaj.org/toc/2169-3536

Přístupová URL adresa: https://doaj.org/article/8d61bb121b47416c91d5dfc254e5fa4f

Hybrid Supply Chain Model for Wheat Market

Autoři: Yulia Otmakhova Dmitry Devyatkin He Zhou

Zdroj: Systems, Vol 13, Iss 11, p 1026 (2025)

Témata: wheat supply chain, wheat trade forecasting, graph transformers, recurrent networks, encoder-decoder architecture, strategic decision making, Systems engineering, TA168, Technology (General), T1-995

Popis souboru: electronic resource

Relation: https://www.mdpi.com/2079-8954/13/11/1026; https://doaj.org/toc/2079-8954

Přístupová URL adresa: https://doaj.org/article/3f1e899d298a4d03b3c072597bcf0cdf

A comparative study of LSTM-ED architectures in forecasting day-ahead solar photovoltaic energy using Weather Data

Autoři: Ekinci, Ekin Ekinci, E Enstitüler, Lisansüstü Eğitim Enstitüsü, Bilgisayar Mühendisliği Ana Bilim Dalı

Přispěvatelé: Ekinci, Ekin Ekinci, E Enstitüler, Lisansüstü Eğitim Enstitüsü, Bilgisayar Mühendisliği Ana Bilim Dalı

Zdroj: Scopus
Web of Science

Témata: 13. Climate action, Solar photovoltaic energy, 0211 other engineering and technologies, 0202 electrical engineering, electronic engineering, information engineering, Time-series, Encoder-decoder architecture, 02 engineering and technology, Foecasting, 7. Clean energy

Přístupová URL adresa: https://aperta.ulakbim.gov.tr/record/278415

An Improved VGG-19 Network Induced Enhanced Feature Pooling for Precise Moving Object Detection in Complex Video Scenes

Autoři: Prabodh Kumar Sahoo Manoj Kumar Panda Upasana Panigrahi a další

Zdroj: IEEE Access, Vol 12, Pp 45847-45864 (2024)

Témata: TK5101-6720 Telecommunication. Including telegraphy, 02 engineering and technology, television, Deep neural network, transfer learning, TK1-9971, radio, feature pooling framework, 0202 electrical engineering, electronic engineering, information engineering, telephone, Electrical engineering. Electronics. Nuclear engineering, encoder-decoder architecture, radar, background subtraction

Popis souboru: text

Přístupová URL adresa: https://doaj.org/article/95ca06ae62764f5d99334e1e5a1db83f

Semantic Scene Object-Camera Motion Recognition for Scene Transition Detection Using Dense Spatial Frame Segments and Temporal Trajectory Analysis

Autoři: Dipanita Chakraborty Werapon Chiracharit Kosin Chamnongthai

Zdroj: IEEE Access, Vol 12, Pp 21673-21697 (2024)

Témata: frame segmentation, motion pattern, shot boundary detection, scene change detection, 0202 electrical engineering, electronic engineering, information engineering, object and camera motion recognition, Encoder-decoder architecture, Electrical engineering. Electronics. Nuclear engineering, 02 engineering and technology, TK1-9971

Přístupová URL adresa: https://doaj.org/article/b131b119d9334c5998263e4233633838

Deep Learning With Noisy Labels for Spatiotemporal Drought Detection

Autoři: Cortés-Andrés, Jordi Fernández-Torres, Miguel-Ángel Camps-Valls, Gustau a další

Přispěvatelé: Cortés-Andrés, Jordi Fernández-Torres, Miguel-Ángel Camps-Valls, Gustau a další

Zdroj: e-Archivo. Repositorio Institucional de la Universidad Carlos III de Madrid
Universidad Carlos III de Madrid (UC3M)
IEEE Transactions on Geoscience and Remote Sensing

Témata: Informática, Noise measurement, Drought detection, Data models, Biological system modeling, Convolutional neural networks (CNNS), Droughts, Predictive models, Europe, Label correction (LC), Noisy labels (NLs), Medio Ambiente, Solid modeling, Training, Three-dimensional displays, Spatiotemporal data, Encoder-decoder architecture, Noise, Hydro-climatological data

Popis souboru: application/pdf

Přístupová URL adresa: https://hdl.handle.net/10016/46966

Cognisynth: A Study of Multimodal Capabilities in Translation and Image Generation

Autoři: K U, Sreerag orcid:0000-0002-5970- Joseph, Binumon

Témata: Transformer neural networks, TNN, translation, stable diffusion, text-to-image generation, image-to-image generation, encoder-decoder architecture, diffusion models, UNET, DDPM, CLIP

Relation: https://zenodo.org/communities/amaljyothi/; https://zenodo.org/records/15581875; oai:zenodo.org:15581875; https://doi.org/10.5281/zenodo.15581875

Dostupnost: https://doi.org/10.5281/zenodo.15581875
https://zenodo.org/records/15581875

A novel lightweight 3D CNN for accurate deformation time series retrieval in MT-InSAR

Autoři: Mahmoud Abdallah Xiaoli Ding Samaa Younis a další

Zdroj: Science of Remote Sensing, Vol 11, Iss , Pp 100206- (2025)

Témata: MT-InSAR, Deformation retrieval, Lightweight, 3D encoder-decoder architecture, Separable CNN, Physical geography, GB3-5030, Science

Popis souboru: electronic resource

Relation: http://www.sciencedirect.com/science/article/pii/S2666017225000124; https://doaj.org/toc/2666-0172

Přístupová URL adresa: https://doaj.org/article/7ce5e628f5fa40d1a5f2babbb8155481

Forecasting Stock Market Indices Using Integration of Encoder, Decoder, and Attention Mechanism

Autoři: Tien Thanh Thach

Zdroj: Entropy ; Volume 27 ; Issue 1 ; Pages: 82

Témata: recurrent neural networks, long short-term memory, gated recurrent units, encoder–decoder architecture, attention mechanism, Bayesian optimization

Popis souboru: application/pdf

Relation: Statistical Physics; https://dx.doi.org/10.3390/e27010082

Dostupnost: https://doi.org/10.3390/e27010082

Human Trajectory Imputation Model: A Hybrid Deep Learning Approach for Pedestrian Trajectory Imputation

Autoři: Deb Kanti Barua Mithun Halder Shayanta Shopnil a další

Zdroj: Applied Sciences ; Volume 15 ; Issue 2 ; Pages: 745

Témata: human trajectory, autonomous vehicle, encoder–decoder architecture, deep learning, inD dataset

Geografické téma: agris

Popis souboru: application/pdf

Relation: Transportation and Future Mobility; https://dx.doi.org/10.3390/app15020745

Dostupnost: https://doi.org/10.3390/app15020745