NSTL国家科技图书文献中心

1. Matryoshka: Exploiting the Over-Parametrization of Deep Learning Models for Covert Data Transmission NSTL国家科技图书文献中心

Xudong Pan | Mi Zhang ... - 《IEEE Transactions on Pattern Analysis and Machine Intelligence》 - 2025,47(2) - 663～678 - 共16页

摘要：) data* stored in local data centers becomes a key* | data even with no exposed interface. Our attack | model for covert transmission of secret models* which* | memorize the information of private ML data* that* | transmit over 10,000 real-world data* samples within a*

关键词： Data models | Training | Predictive models | Training data | Computational modeling | Task analysis | Data privacy

2. Diffusion Models as Data Mining Tools NSTL国家科技图书文献中心

Ioannis Siglidis | Aleksander Holynski ... - 《Computer Vision - ECCV 2024,Part LXI》 - European Conference on Computer Vision - 2025, - 393～409 - 共17页

摘要： models trained for image synthesis as tools for visual | data mining. Our insight is that since contemporary | generative models* learn an accurate representation of their* | training data, we can use them to summarize the data* by* | after finetuning conditional diffusion models* to*

关键词： Visual data mining | Diffusion models

3. Discovering ship maneuvering models from data NSTL国家科技图书文献中心

Agus Hasan - 《Journal of marine science and technology》 - 2025,30(1) - 255～267 - 共13页

摘要： discover ship maneuvering models* from data, leveraging* | the maneuvering models. Through extensive numerical | approach in solving system identification and data-driven | to advancing data-driven discovery of ship | In this paper, we introduce a methodology to

关键词： Ship dynamics | Maneuvering models | Data-driven discovery

4. Can Large Language Models Aid in Annotating Speech Emotional Data? Uncovering New Frontiers [Research Frontier] NSTL国家科技图书文献中心

Siddique Latif | Muhammad Usama ... - 《IEEE computational intelligence magazine》 - 2025,20(1) - 66～77 - 共12页

摘要： recognition (SER) models, state-of-the-art deep learning (DL | of annotated data. The advent of large language | models (LLMs) has revolutionised our understanding of | ChatGPT, to annotate abundant speech data* with the goal* | work achieves improved results through data

关键词： Deep learning | Emotion recognition | Annotations | Large language models | Face recognition | Natural languages | Speech recognition | Data augmentation | Chatbots | Data models

5. Solar Panels Segmentation in Remote Sensing Data Using Segment Anything Models 2 and 2.1 NSTL国家科技图书文献中心

Osher Rafaeli | Tal Svoray ... - 《IEEE geoscience and remote sensing letters》 - 2025,22 - 1～5 - 共5页

摘要： RGB aerial imagery. The study evaluates these models | achieving reasonable performance in low-resolution data | segmentation in high-resolution data. This research details | robustness of user-prompted image segmentation models. | This letter provides insights on the

关键词： Image segmentation | Image resolution | Lighting | YOLO | Computational modeling | Training | Data models | Accuracy | Atmospheric modeling | Adaptation models

6. Utilizing Neurons to Interrogate Cancer: Integrative Analysis of Cancer Omics Data With Deep Learning Models NSTL国家科技图书文献中心

Raid Halawani | Michael Buchert ... - 《IEEE reviews in biomedical engineering》 - 2025,18 - 281～299 - 共19页

摘要：-omics cancer genomics data. In recent years, deep | large cancer genomics data* and has the potential to* | learning models* in basic cancer omics research, including* | cancer omics data* and the importance of cross-platform* | data integration. The paper provides insights into

关键词： Cancer | Bioinformatics | Deep learning | DNA | Sequential analysis | Biological system modeling | Epigenetics | Tumors | Transcriptomics | Data models

7. Conditional Denoising Diffusion Probabilistic Models for Data Reconstruction Enhancement in Wireless Communications NSTL国家科技图书文献中心

Mehdi Letafati | Samad Ali ... - 《IEEE Transactions on Machine Learning in Communications and Networking》 - 2025,3 - 133～146 - 共14页

摘要： probabilistic models (CDiffs) are proposed to enhance the data | underlying mechanism of diffusion models* is to decompose* | the data* generation process over the so-called* | leverage the generative prior of diffusion models* in* | information signal to help enhance data* reconstruction. The*

关键词： Diffusion models | Wireless communication | Noise reduction | Image reconstruction | Vectors | Diffusion processes | Signal to noise ratio | Gaussian distribution | Receivers | Data models

8. Data Fusion and Models Integration for Enhanced Semantic Segmentation in Remote Sensing NSTL国家科技图书文献中心

Xiaorui Dong | Jiansheng Li ... - 《IEEE journal of selected topics in applied earth observations and remote sensing》 - 2025,18 - 7134～7151 - 共18页

摘要：, we propose a novel data* fusion method for remote* | sensing data* from different sources and segmentation* | and complexity of different remote sensing data* but* | efficient semantic segmentation models. | Remote sensing semantic segmentation is a key

关键词： Remote sensing | Semantic segmentation | Data models | Training | Benchmark testing | Deep learning | Data integration | Semantics | Data mining | Biological system modeling

9. Enhancing Recipe Retrieval with Foundation Models: A Data Augmentation Perspective NSTL国家科技图书文献中心

Fangzhou Song | Bin Zhu ... - 《Computer Vision - ECCV 2024,Part LI》 - European Conference on Computer Vision - 2025, - 111～127 - 共17页

摘要： utilizing foundation models* for data augmentation* | models (i.e., Llama2 and SAM), we propose to augment | make full use of the augmented data, we introduce | Data Augmented Retrieval framework (DAR) to enhance | the original and augmented data* pairs, which assigns*

关键词： Recipe retrieval | Data augmentation | Foundation models

10. Industrial Process Soft Sensing Based on Bidirectional Optimization Learning of Data Augmentation and Prediction Models Under Limited Data NSTL国家科技图书文献中心

Li, He | Wang, Zhaojing ... - 《IEEE Transactions on Instrumentation and Measurement》 - 2025,74(Pt.1) - 1001211.1～1001211.11 - 共11页

摘要： dependency between data* generation and predictive models, a* | soft sensing models. Consequently, this study | develops a bidirectional optimization learning of data | extraction process of soft sensing models, a nonlinear | loss function flow between the two models. This

关键词： Soft sensors | Data models | Predictive models | Data augmentation | Accuracy | Optimization | Feature extraction | Decoding | Correlation | Vectors...

摘要：) data stored in local data centers becomes a key | data even with no exposed interface. Our attack | model for covert transmission of secret models which | memorize the information of private ML data that | transmit over 10,000 real-world data samples within a

关键词： Data models | Training | Predictive models | Training data | Computational modeling | Task analysis | Data privacy

摘要： models trained for image synthesis as tools for visual | data mining. Our insight is that since contemporary | generative models learn an accurate representation of their | training data, we can use them to summarize the data by | after finetuning conditional diffusion models to

关键词： Visual data mining | Diffusion models

摘要： discover ship maneuvering models from data, leveraging | the maneuvering models. Through extensive numerical | approach in solving system identification and data-driven | to advancing data-driven discovery of ship | In this paper, we introduce a methodology to

关键词： Ship dynamics | Maneuvering models | Data-driven discovery

摘要： recognition (SER) models, state-of-the-art deep learning (DL | of annotated data. The advent of large language | models (LLMs) has revolutionised our understanding of | ChatGPT, to annotate abundant speech data with the goal | work achieves improved results through data

关键词： Deep learning | Emotion recognition | Annotations | Large language models | Face recognition | Natural languages | Speech recognition | Data augmentation | Chatbots | Data models

摘要： RGB aerial imagery. The study evaluates these models | achieving reasonable performance in low-resolution data | segmentation in high-resolution data. This research details | robustness of user-prompted image segmentation models. | This letter provides insights on the

关键词： Image segmentation | Image resolution | Lighting | YOLO | Computational modeling | Training | Data models | Accuracy | Atmospheric modeling | Adaptation models

摘要：-omics cancer genomics data. In recent years, deep | large cancer genomics data and has the potential to | learning models in basic cancer omics research, including | cancer omics data and the importance of cross-platform | data integration. The paper provides insights into

关键词： Cancer | Bioinformatics | Deep learning | DNA | Sequential analysis | Biological system modeling | Epigenetics | Tumors | Transcriptomics | Data models

摘要： probabilistic models (CDiffs) are proposed to enhance the data | underlying mechanism of diffusion models is to decompose | the data generation process over the so-called | leverage the generative prior of diffusion models in | information signal to help enhance data reconstruction. The

关键词： Diffusion models | Wireless communication | Noise reduction | Image reconstruction | Vectors | Diffusion processes | Signal to noise ratio | Gaussian distribution | Receivers | Data models

摘要：, we propose a novel data fusion method for remote | sensing data from different sources and segmentation | and complexity of different remote sensing data but | efficient semantic segmentation models. | Remote sensing semantic segmentation is a key

关键词： Remote sensing | Semantic segmentation | Data models | Training | Benchmark testing | Deep learning | Data integration | Semantics | Data mining | Biological system modeling

摘要： utilizing foundation models for data augmentation | models (i.e., Llama2 and SAM), we propose to augment | make full use of the augmented data, we introduce | Data Augmented Retrieval framework (DAR) to enhance | the original and augmented data pairs, which assigns

关键词： Recipe retrieval | Data augmentation | Foundation models

摘要： dependency between data generation and predictive models, a | soft sensing models. Consequently, this study | develops a bidirectional optimization learning of data | extraction process of soft sensing models, a nonlinear | loss function flow between the two models. This

关键词： Soft sensors | Data models | Predictive models | Data augmentation | Accuracy | Optimization | Feature extraction | Decoding | Correlation | Vectors...

4008-161-200 800-990-8900

国家科技图书文献中心

摘要：) data* stored in local data centers becomes a key* | data even with no exposed interface. Our attack | model for covert transmission of secret models* which* | memorize the information of private ML data* that* | transmit over 10,000 real-world data* samples within a*

摘要： models trained for image synthesis as tools for visual | data mining. Our insight is that since contemporary | generative models* learn an accurate representation of their* | training data, we can use them to summarize the data* by* | after finetuning conditional diffusion models* to*

摘要： discover ship maneuvering models* from data, leveraging* | the maneuvering models. Through extensive numerical | approach in solving system identification and data-driven | to advancing data-driven discovery of ship | In this paper, we introduce a methodology to

摘要： recognition (SER) models, state-of-the-art deep learning (DL | of annotated data. The advent of large language | models (LLMs) has revolutionised our understanding of | ChatGPT, to annotate abundant speech data* with the goal* | work achieves improved results through data

摘要：-omics cancer genomics data. In recent years, deep | large cancer genomics data* and has the potential to* | learning models* in basic cancer omics research, including* | cancer omics data* and the importance of cross-platform* | data integration. The paper provides insights into

摘要：, we propose a novel data* fusion method for remote* | sensing data* from different sources and segmentation* | and complexity of different remote sensing data* but* | efficient semantic segmentation models. | Remote sensing semantic segmentation is a key

摘要： utilizing foundation models* for data augmentation* | models (i.e., Llama2 and SAM), we propose to augment | make full use of the augmented data, we introduce | Data Augmented Retrieval framework (DAR) to enhance | the original and augmented data* pairs, which assigns*

摘要： dependency between data* generation and predictive models, a* | soft sensing models. Consequently, this study | develops a bidirectional optimization learning of data | extraction process of soft sensing models, a nonlinear | loss function flow between the two models. This