NSTL国家科技图书文献中心

1. Data-Driven Quadratic Modeling in the Loewner Framework from Input-Output Time-Domain Measurements NSTL国家科技图书文献中心

Karachalios, D. S. | Gosea, I., V ... - 《SIAM journal on applied dynamical systems》 - 2025,24(1) - 457～500 - 共44页

摘要： identification of low-order in-state dimension quadratic state | nonlinear optimization techniques to infer quadratic | ) of the quasi-steady-state* system response under* | -space* models with nontrivial stable equilibria, such* | In this study, we present a purely data-driven

关键词： data-driven methods | model reduction | system identification | Loewner framework | quadratic state-space modeling | Lorenz attractor | viscous Burgers' equation | Volterra series | quadratic matrix | vector equations

2. ZigMa: A DiT-style Zigzag Mamba Diffusion Model NSTL国家科技图书文献中心

Vincent Tao Hu | Stefan Andreas Bauma...... - 《Computer Vision - ECCV 2024,Part XXI》 - European Conference on Computer Vision - 2025, - 148～166 - 共19页

摘要： capability of a State-Space* Model called Mamba to extend* | scalability and quadratic* complexity issues, especially* | aim to leverage the long sequence modeling | The diffusion model has long been plagued by | within transformer-based structures. In this study, we

关键词： Diffusion model | State-space model | Stochastic interpolants

3. Efficient Long-Range Context Modeling for Motion Forecasting with State Space Models NSTL国家科技图书文献中心

Zhiwei Dong | Ran Ding ... - 《Pattern Recognition,Part XXVI》 - International Conference on Pattern Recognition - 2025, - 186～201 - 共16页

摘要： efficiency. Inspired by the recent success of state space | heavily on modeling* the long-range global context in* | inherent quadratic* complexity of self-attention limits* | models with linear complexity in long sequence modeling | effectiveness and efficiency in modeling* long-range context*

关键词： Motion forecasting | State space models | Autonomous driving | Context modeling

4. Mamba-Based Light Field Super-Resolution with Efficient Subspace Scanning NSTL国家科技图书文献中心

Ruisheng Gao | Zeyu Xiao ... - 《Computer Vision - ACCV 2024,Part V》 - Asian Conference on Computer Vision - 2025, - 421～437 - 共17页

摘要： selective state-space* model, Mamba, has gained popularity* | -resolution by effectively modeling* long-range spatial* | -angular correlations, but their quadratic* complexity* | for its efficient long-range sequence modeling. In | Transformer-based methods have demonstrated

关键词： Light field | Super-resolution | State space model

5. HSIRMamba: An effective feature learning for hyperspectral image classification using residual Mamba NSTL国家科技图书文献中心

Arya R.K. | Jain S.... - 《Image and vision computing》 - 2025,154(Feb.) - 1.1～1.12 - 共12页

摘要：. Fortunately, the newly developed state* space model Mamba* | Transformer exhibits quadratic* computational complexity* | Transformer-like modeling* capabilities. Therefore, we* | competitive results compared to state-of-the-art methods. | © 2024 Elsevier B.V.Deep learning models have

关键词： Classification | Feature extraction | Hyperspectral image | Mamba | State space model

6. DemoireingMamba: Visual State Space Model for Image Demoireing NSTL国家科技图书文献中心

Chia-Hung Yeh | Chen Lo - 《International Workshop on Advanced Imaging Technology (IWAIT) 2025》 - International Workshop on Advanced Imaging Technology - 2025, - 1351003.1～1351003.6 - 共6页

摘要： quadratic computational complexity. Recently, the state | results. While CNNs struggle with modeling* remote* | space model (SSM) known as Mamba has emerged as a | outperforms state-of-the-art methods, achieving superior | Moire effect is important in image processing

关键词： Moire pattern | Deep learning | Mamba | Image restoration

7. Visual State Space Model for Image Super-Resolution NSTL国家科技图书文献中心

Zhang, Jinhang | Gao, Min ... - 《IEEE Transactions on Instrumentation and Measurement》 - 2025,74(Pt.1) - 5004208.1～5004208.8 - 共8页

摘要： create a new dense-residual state-space* block (DRSSB* | Transformers suffer from the quadratic* complexity of* | CNN and provides new advanced modeling* capabilities* | complexity, thereby achieving state-of-the-art performance | Transformers and convolutional neural networks

关键词： Dense connection | image super-resolution (SR) | mamba | state space model (SSM)

8. Self-prior Guided Mamba-UNet Networks for Medical Image Super-Resolution NSTL国家科技图书文献中心

Zexin Ji | Beiji Zou ... - 《Pattern Recognition,Part XI》 - International Conference on Pattern Recognition - 2025, - 160～174 - 共15页

摘要： complexity. Recently, State* Space Models (SSMs) especially* | calculation challenges due to their quadratic* computational* | Mamba have emerged, capable of modeling* long-range* | approach outperforms current state-of-the-art methods on | In this paper, we propose a self-prior guided

关键词： Medical imaging | Super-Resolution | State space models | Mamba | Unet | Deep learning

9. Pocket convolution Mamba for brain tumor segmentation NSTL国家科技图书文献中心

Hao Zhang | Jiashu Wang ... - 《The Journal of Supercomputing》 - 2025,81(1) - 235.1～235.23 - 共23页

摘要： computational complexity. Recently, state* space models (SSM* | long-range modeling, and although transformers can | model at long distances, they have quadratic | In the field of brain tumor segmentation | , models based on CNNs and transformer have received a

关键词： Brain tumor segmentation | State space models | Feature complement | Spatial channel attention

10. Speech-Mamba: Long-Context Speech Recognition with Selective State Spaces Models NSTL国家科技图书文献中心

Xiaoxue Gao | Nancy F. Chen - 《2024 IEEE Spoken Language Technology Workshop,[v.1]》 - IEEE Spoken Language Technology Workshop - 2024, - 1～8 - 共8页

摘要： selective state* space modeling in Transformer neural* | . Selective state* space models such as Mamba has performed* | state space models in Speech-Mamba is complemented | struggle with modeling* long speech sequences due to high* | quadratic complexity of Transformer-based models

关键词： Computer vision | Speech coding | Computational modeling | Conferences | Speech recognition | Computer architecture | Transformers | Natural language processing | Complexity theory | Speech processing

摘要： identification of low-order in-state dimension quadratic state | nonlinear optimization techniques to infer quadratic | ) of the quasi-steady-state system response under | -space models with nontrivial stable equilibria, such | In this study, we present a purely data-driven

关键词： data-driven methods | model reduction | system identification | Loewner framework | quadratic state-space modeling | Lorenz attractor | viscous Burgers' equation | Volterra series | quadratic matrix | vector equations

摘要： capability of a State-Space Model called Mamba to extend | scalability and quadratic complexity issues, especially | aim to leverage the long sequence modeling | The diffusion model has long been plagued by | within transformer-based structures. In this study, we

关键词： Diffusion model | State-space model | Stochastic interpolants

摘要： efficiency. Inspired by the recent success of state space | heavily on modeling the long-range global context in | inherent quadratic complexity of self-attention limits | models with linear complexity in long sequence modeling | effectiveness and efficiency in modeling long-range context

关键词： Motion forecasting | State space models | Autonomous driving | Context modeling

摘要： selective state-space model, Mamba, has gained popularity | -resolution by effectively modeling long-range spatial | -angular correlations, but their quadratic complexity | for its efficient long-range sequence modeling. In | Transformer-based methods have demonstrated

关键词： Light field | Super-resolution | State space model

摘要：. Fortunately, the newly developed state space model Mamba | Transformer exhibits quadratic computational complexity | Transformer-like modeling capabilities. Therefore, we | competitive results compared to state-of-the-art methods. | © 2024 Elsevier B.V.Deep learning models have

关键词： Classification | Feature extraction | Hyperspectral image | Mamba | State space model

摘要： quadratic computational complexity. Recently, the state | results. While CNNs struggle with modeling remote | space model (SSM) known as Mamba has emerged as a | outperforms state-of-the-art methods, achieving superior | Moire effect is important in image processing

关键词： Moire pattern | Deep learning | Mamba | Image restoration

摘要： create a new dense-residual state-space block (DRSSB | Transformers suffer from the quadratic complexity of | CNN and provides new advanced modeling capabilities | complexity, thereby achieving state-of-the-art performance | Transformers and convolutional neural networks

关键词： Dense connection | image super-resolution (SR) | mamba | state space model (SSM)

摘要： complexity. Recently, State Space Models (SSMs) especially | calculation challenges due to their quadratic computational | Mamba have emerged, capable of modeling long-range | approach outperforms current state-of-the-art methods on | In this paper, we propose a self-prior guided

关键词： Medical imaging | Super-Resolution | State space models | Mamba | Unet | Deep learning

摘要： computational complexity. Recently, state space models (SSM | long-range modeling, and although transformers can | model at long distances, they have quadratic | In the field of brain tumor segmentation | , models based on CNNs and transformer have received a

关键词： Brain tumor segmentation | State space models | Feature complement | Spatial channel attention

摘要： selective state space modeling in Transformer neural | . Selective state space models such as Mamba has performed | state space models in Speech-Mamba is complemented | struggle with modeling long speech sequences due to high | quadratic complexity of Transformer-based models

关键词： Computer vision | Speech coding | Computational modeling | Conferences | Speech recognition | Computer architecture | Transformers | Natural language processing | Complexity theory | Speech processing

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： identification of low-order in-state dimension quadratic state | nonlinear optimization techniques to infer quadratic | ) of the quasi-steady-state* system response under* | -space* models with nontrivial stable equilibria, such* | In this study, we present a purely data-driven

摘要： capability of a State-Space* Model called Mamba to extend* | scalability and quadratic* complexity issues, especially* | aim to leverage the long sequence modeling | The diffusion model has long been plagued by | within transformer-based structures. In this study, we

摘要： selective state-space* model, Mamba, has gained popularity* | -resolution by effectively modeling* long-range spatial* | -angular correlations, but their quadratic* complexity* | for its efficient long-range sequence modeling. In | Transformer-based methods have demonstrated

摘要：. Fortunately, the newly developed state* space model Mamba* | Transformer exhibits quadratic* computational complexity* | Transformer-like modeling* capabilities. Therefore, we* | competitive results compared to state-of-the-art methods. | © 2024 Elsevier B.V.Deep learning models have

摘要： quadratic computational complexity. Recently, the state | results. While CNNs struggle with modeling* remote* | space model (SSM) known as Mamba has emerged as a | outperforms state-of-the-art methods, achieving superior | Moire effect is important in image processing

摘要： create a new dense-residual state-space* block (DRSSB* | Transformers suffer from the quadratic* complexity of* | CNN and provides new advanced modeling* capabilities* | complexity, thereby achieving state-of-the-art performance | Transformers and convolutional neural networks

摘要： complexity. Recently, State* Space Models (SSMs) especially* | calculation challenges due to their quadratic* computational* | Mamba have emerged, capable of modeling* long-range* | approach outperforms current state-of-the-art methods on | In this paper, we propose a self-prior guided

摘要： computational complexity. Recently, state* space models (SSM* | long-range modeling, and although transformers can | model at long distances, they have quadratic | In the field of brain tumor segmentation | , models based on CNNs and transformer have received a

摘要： selective state* space modeling in Transformer neural* | . Selective state* space models such as Mamba has performed* | state space models in Speech-Mamba is complemented | struggle with modeling* long speech sequences due to high* | quadratic complexity of Transformer-based models