NSTL国家科技图书文献中心

1. Epileptic Seizure Detection in SEEG Signals Using a Signal Embedding Temporal-Spatial-Spectral Transformer Model NSTL国家科技图书文献中心

Li, Zhuoyi | Chen, Beibei ... - 《IEEE Transactions on Instrumentation and Measurement》 - 2025,74(Pt.1) - 4001111.1～4001111.11 - 共11页

摘要： signal embedding temporal-spatial-spectral transformer | in SEEG in the temporal, spatial, and spectral | unified multiscale temporal-spatial-spectral* (TSS* | (SE-TSS-Transformer) framework. First, we design | . Finally, we use the transformer* encoder to learn the*

关键词： Electroencephalography | Epilepsy | Feature extraction | Transformers | Electrodes | Brain modeling | Hospitals | Convolution | Scalability | Neurosurgery...

2. SSCDUF: Spatial-Spectral Correlation Transformer Based on Deep Unfolding Framework for Hyperspectral Image Reconstruction NSTL国家科技图书文献中心

Hui Zhao | Na Qi ... - 《MultiMedia Modeling,Part IV》 - International Conference on MultiMedia Modeling - 2025, - 71～84 - 共14页

摘要： not fully utilize the spatial* spectral prior of HSIs* | spectral-spatial representation capabilities in the prior | subproblems, we propose a Spatial-Spectral* Correlation* | ). Specifically, we introduce a multi-scale Spatial-Spectral | spectral features as well as local and non-local spatial

关键词： Hyperspectral image reconstruction | Deep unfolding framework | Spatial-Spectral transformer | Adaptive aggregation skip connection

3. Spectral-Spatial Attention Transformer Network for Hyperspectral Image Classification NSTL国家科技图书文献中心

Yuxiong Luo | Dong Tang ... - 《The International Conference Optoelectronic Information and Optical Engineering (OIOE2024),Part Two of Two Parts》 - International Conference Optoelectronic Information and Optical Engineering - 2025, - 1351334.1～1351334.6 - 共6页

摘要：-Spatial* Attention Transformer (SSAT) model, which* | (LPE) module to extract localized spectral-spatial | information from HSI data. The Spectral-Spatial* Attention* | ) mechanism may overlook subtle spectral* differences when* | enhancement. To address this, we propose the Spectral

关键词： Hyperspectral image (HSI) | Spectral-Spatial attention transformer (SSAT) | Spectral-Spatial attention (SSA) | CNN

4. Spectral-Spatial Blockwise Masked Transformer With Contrastive Multi-View Learning for Hyperspectral Image Classification NSTL国家科技图书文献中心

Han Hu | Zhenhui Liu ... - 《Pattern Recognition and Computer Vision,Part IV》 - Chinese Conference on Pattern Recognition and Computer Vision - 2025, - 481～495 - 共15页

摘要： framework, spectral-spatial blockwise masked transformer | spatial and spectral features may cause target confusion | HSI cube is transformed into spectral-spatial* tokens* | spatial-spectral encoder extracts dimensional features | and utilizes spectral-spatial* associate positional*

关键词： Hyperspectral image (HSI) classification | Spectral-spatial blockwise | Transformer | Self-supervised learning

5. Hybrid Spectral-Spatial ResNet and Transformer For Hyperspectral Image Classification NSTL国家科技图书文献中心

Fan Xiang | Zhaohui Wang - 《Sixteenth International Conference on Graphics and Image Processing (ICGIP 2024)》 - International Conference on Graphics and Image Processing - 2025, - 135390R.1～135390R.10 - 共10页

摘要： Spectral-Spatial ResNet and Transformer (HSSRT | are employed to extract fused spatial-spectral | spectral dimensions, achieving a deep fusion of spatial | layers grows. The Vision Transformer* (ViT), leveraging* | classification performance compared to CNNs, and Transformer

关键词： Convolutional neural networks (CNNs) | Hyperspectral image (HSI) classification | Self-attention mechanism | Transformer

6. Selective Spectral–Spatial Aggregation Transformer for Hyperspectral and LiDAR Classification NSTL国家科技图书文献中心

Kang Ni | Zirun Li ... - 《IEEE geoscience and remote sensing letters》 - 2025,22 - 1～5 - 共5页

摘要： mechanisms and spectral-spatial interactive transformer | characterizing the contextual information and spectral-spatial | -spatial* aggregation transformer network, named S2ATNet* | spatial-spectral learning and interactive fusion (CSLIF | feature learning style, proposing a selective spectral

关键词： Laser radar | Feature extraction | Land surface | Transformers | Convolution | Accuracy | Representation learning | Kernel | Principal component analysis | Training

7. Advanced Hyperspectral Image Classification via Spectral–Spatial Redundancy Reduction and TokenLearner-Enhanced Transformer NSTL国家科技图书文献中心

Jinbin Wu | Jiankang Zhao ... - 《IEEE Transactions on Geoscience and Remote Sensing》 - 2025,63 - 1～12 - 共12页

摘要： spectral-spatial information redundancy, which creates | HSI classification network via spectral-spatial | redundancy reduction and TokenLearner-enhanced transformer | convolutional neural networks (CNNs) and transformer | : spectral* redundancy reduction and multiscale information*

关键词： Feature extraction | Transformers | Termination of employment | Data mining | Principal component analysis | Iron | Logic gates | Hyperspectral imaging | Convolutional neural networks | Robustness

8. Spatial-Spectral Mixing Transformer With Hybrid Image Prior for Multispectral Image Demosaicing NSTL国家科技图书文献中心

Le Dong | Mengzu Liu ... - 《IEEE journal of selected topics in signal processing》 - 2025,19(1) - 221～233 - 共13页

摘要： framework, the spatial-spectral* mixing transformer (SSMT* | demosaicing method based on the spatial-spectral* mixing* | spatial and spectral characteristics of MSI. Furthermore | of scenes and obtain spectral* mosaic images. To* | obtain the complete MSI information from these spectral

关键词： Transformers | Image restoration | Image reconstruction | Multispectral imaging | GSM | Interpolation | Convolution | Three-dimensional displays | Mathematical models | Correlation

9. SSLT-Net: A Spatial–Spectral Linear Transformer Unmixing Network for Hyperspectral Image NSTL国家科技图书文献中心

Jiangwei Deng | Guanglian Zhang ... - 《IEEE geoscience and remote sensing letters》 - 2025,22 - 1～5 - 共5页

摘要： extract global spatial* and spectral features of images* | global and spectral* and spatial) in hyperspectral* | . Consequently, a few transformer-based unmixing networks have | , which is the combination of CNN and linear transformer | . This network capably extracts local, global, spatial

关键词： Feature extraction | Transformers | Data mining | Convolution | Hyperspectral imaging | Decoding | Image reconstruction | Geoscience and remote sensing | Vectors | Neural networks

10. Uncertainty-Driven Spectral Compressive Imaging with Spatial-Frequency Transformer NSTL国家科技图书文献中心

Lintao Peng | Siyu Xie ... - 《Computer Vision - ECCV 2024,Part VI》 - European Conference on Computer Vision - 2025, - 54～70 - 共17页

摘要： both the spatial sparsity and inter-spectral | -attention (FWSA) module, and combine it with a spatial | parallel to form a Spatial-Frequency (SF) block. LWSA can | spectral information, and FWSA can capture the inter | -spectral* similarity. Parallel design helps the network to*

摘要： signal embedding temporal-spatial-spectral transformer | in SEEG in the temporal, spatial, and spectral | unified multiscale temporal-spatial-spectral* (TSS* | (SE-TSS-Transformer) framework. First, we design | . Finally, we use the transformer* encoder to learn the*

关键词： Electroencephalography | Epilepsy | Feature extraction | Transformers | Electrodes | Brain modeling | Hospitals | Convolution | Scalability | Neurosurgery...

关键词： Hyperspectral image reconstruction | Deep unfolding framework | Spatial-Spectral transformer | Adaptive aggregation skip connection

摘要：-Spatial* Attention Transformer (SSAT) model, which* | (LPE) module to extract localized spectral-spatial | information from HSI data. The Spectral-Spatial* Attention* | ) mechanism may overlook subtle spectral* differences when* | enhancement. To address this, we propose the Spectral

关键词： Hyperspectral image (HSI) | Spectral-Spatial attention transformer (SSAT) | Spectral-Spatial attention (SSA) | CNN

摘要： framework, spectral-spatial blockwise masked transformer | spatial and spectral features may cause target confusion | HSI cube is transformed into spectral-spatial* tokens* | spatial-spectral encoder extracts dimensional features | and utilizes spectral-spatial* associate positional*

关键词： Hyperspectral image (HSI) classification | Spectral-spatial blockwise | Transformer | Self-supervised learning

摘要： Spectral-Spatial ResNet and Transformer (HSSRT | are employed to extract fused spatial-spectral | spectral dimensions, achieving a deep fusion of spatial | layers grows. The Vision Transformer* (ViT), leveraging* | classification performance compared to CNNs, and Transformer

关键词： Convolutional neural networks (CNNs) | Hyperspectral image (HSI) classification | Self-attention mechanism | Transformer

关键词： Laser radar | Feature extraction | Land surface | Transformers | Convolution | Accuracy | Representation learning | Kernel | Principal component analysis | Training

摘要： spectral-spatial information redundancy, which creates | HSI classification network via spectral-spatial | redundancy reduction and TokenLearner-enhanced transformer | convolutional neural networks (CNNs) and transformer | : spectral* redundancy reduction and multiscale information*

关键词： Feature extraction | Transformers | Termination of employment | Data mining | Principal component analysis | Iron | Logic gates | Hyperspectral imaging | Convolutional neural networks | Robustness

摘要： framework, the spatial-spectral* mixing transformer (SSMT* | demosaicing method based on the spatial-spectral* mixing* | spatial and spectral characteristics of MSI. Furthermore | of scenes and obtain spectral* mosaic images. To* | obtain the complete MSI information from these spectral

关键词： Transformers | Image restoration | Image reconstruction | Multispectral imaging | GSM | Interpolation | Convolution | Three-dimensional displays | Mathematical models | Correlation

关键词： Feature extraction | Transformers | Data mining | Convolution | Hyperspectral imaging | Decoding | Image reconstruction | Geoscience and remote sensing | Vectors | Neural networks

摘要： both the spatial sparsity and inter-spectral | -attention (FWSA) module, and combine it with a spatial | parallel to form a Spatial-Frequency (SF) block. LWSA can | spectral information, and FWSA can capture the inter | -spectral* similarity. Parallel design helps the network to*

关键词： Hyperspectral imaging | Spatial-Frequency transformer | Uncertainty-Driven learning

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： signal embedding temporal-spatial-spectral transformer | in SEEG in the temporal, spatial, and spectral | unified multiscale temporal-spatial-spectral (TSS | (SE-TSS-Transformer) framework. First, we design | . Finally, we use the transformer encoder to learn the

关键词： Electroencephalography | Epilepsy | Feature extraction | Transformers | Electrodes | Brain modeling | Hospitals | Convolution | Scalability | Neurosurgery...

关键词： Hyperspectral image reconstruction | Deep unfolding framework | Spatial-Spectral transformer | Adaptive aggregation skip connection

摘要：-Spatial Attention Transformer (SSAT) model, which | (LPE) module to extract localized spectral-spatial | information from HSI data. The Spectral-Spatial Attention | ) mechanism may overlook subtle spectral differences when | enhancement. To address this, we propose the Spectral

关键词： Hyperspectral image (HSI) | Spectral-Spatial attention transformer (SSAT) | Spectral-Spatial attention (SSA) | CNN

摘要： framework, spectral-spatial blockwise masked transformer | spatial and spectral features may cause target confusion | HSI cube is transformed into spectral-spatial tokens | spatial-spectral encoder extracts dimensional features | and utilizes spectral-spatial associate positional

关键词： Hyperspectral image (HSI) classification | Spectral-spatial blockwise | Transformer | Self-supervised learning

摘要： Spectral-Spatial ResNet and Transformer (HSSRT | are employed to extract fused spatial-spectral | spectral dimensions, achieving a deep fusion of spatial | layers grows. The Vision Transformer (ViT), leveraging | classification performance compared to CNNs, and Transformer

关键词： Convolutional neural networks (CNNs) | Hyperspectral image (HSI) classification | Self-attention mechanism | Transformer

关键词： Laser radar | Feature extraction | Land surface | Transformers | Convolution | Accuracy | Representation learning | Kernel | Principal component analysis | Training

摘要： spectral-spatial information redundancy, which creates | HSI classification network via spectral-spatial | redundancy reduction and TokenLearner-enhanced transformer | convolutional neural networks (CNNs) and transformer | : spectral redundancy reduction and multiscale information

关键词： Feature extraction | Transformers | Termination of employment | Data mining | Principal component analysis | Iron | Logic gates | Hyperspectral imaging | Convolutional neural networks | Robustness

摘要： framework, the spatial-spectral mixing transformer (SSMT | demosaicing method based on the spatial-spectral mixing | spatial and spectral characteristics of MSI. Furthermore | of scenes and obtain spectral mosaic images. To | obtain the complete MSI information from these spectral

关键词： Transformers | Image restoration | Image reconstruction | Multispectral imaging | GSM | Interpolation | Convolution | Three-dimensional displays | Mathematical models | Correlation

摘要： extract global spatial and spectral features of images | global and spectral and spatial) in hyperspectral | . Consequently, a few transformer-based unmixing networks have | , which is the combination of CNN and linear transformer | . This network capably extracts local, global, spatial

关键词： Feature extraction | Transformers | Data mining | Convolution | Hyperspectral imaging | Decoding | Image reconstruction | Geoscience and remote sensing | Vectors | Neural networks

摘要： both the spatial sparsity and inter-spectral | -attention (FWSA) module, and combine it with a spatial | parallel to form a Spatial-Frequency (SF) block. LWSA can | spectral information, and FWSA can capture the inter | -spectral similarity. Parallel design helps the network to

关键词： Hyperspectral imaging | Spatial-Frequency transformer | Uncertainty-Driven learning

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： signal embedding temporal-spatial-spectral transformer | in SEEG in the temporal, spatial, and spectral | unified multiscale temporal-spatial-spectral* (TSS* | (SE-TSS-Transformer) framework. First, we design | . Finally, we use the transformer* encoder to learn the*

摘要：-Spatial* Attention Transformer (SSAT) model, which* | (LPE) module to extract localized spectral-spatial | information from HSI data. The Spectral-Spatial* Attention* | ) mechanism may overlook subtle spectral* differences when* | enhancement. To address this, we propose the Spectral

摘要： framework, spectral-spatial blockwise masked transformer | spatial and spectral features may cause target confusion | HSI cube is transformed into spectral-spatial* tokens* | spatial-spectral encoder extracts dimensional features | and utilizes spectral-spatial* associate positional*

摘要： Spectral-Spatial ResNet and Transformer (HSSRT | are employed to extract fused spatial-spectral | spectral dimensions, achieving a deep fusion of spatial | layers grows. The Vision Transformer* (ViT), leveraging* | classification performance compared to CNNs, and Transformer

摘要： spectral-spatial information redundancy, which creates | HSI classification network via spectral-spatial | redundancy reduction and TokenLearner-enhanced transformer | convolutional neural networks (CNNs) and transformer | : spectral* redundancy reduction and multiscale information*

摘要： framework, the spatial-spectral* mixing transformer (SSMT* | demosaicing method based on the spatial-spectral* mixing* | spatial and spectral characteristics of MSI. Furthermore | of scenes and obtain spectral* mosaic images. To* | obtain the complete MSI information from these spectral

摘要： both the spatial sparsity and inter-spectral | -attention (FWSA) module, and combine it with a spatial | parallel to form a Spatial-Frequency (SF) block. LWSA can | spectral information, and FWSA can capture the inter | -spectral* similarity. Parallel design helps the network to*