全部 |
  • 全部
  • 题名
  • 作者
  • 机构
  • 关键词
  • NSTL主题词
  • 摘要
检索 二次检索 AI检索
外文文献 中文文献
筛选条件:

1. Dataset Distribution Impacts Model Fairness: Single Vs. Multi-task Learning NSTL国家科技图书文献中心

Ralf Raumanns |  Gerard Schouten... -  《Ethics and Fairness in Medical Imaging》 -  International Conference onedical Image Computing and Computer Assisted Interventions |  International Workshop on Fairness of AI in Medical Imaging |  International Workshop on Ethical and Philosophical Issues in Medical Imaging - 2025, - 14~23 - 共10页

摘要: different learning strategies: a single-task model, a |  reinforcing multi-task model, and an adversarial learning |  training data yields better results, 2) single-task |  data and three different learning strategies. We | The influence of bias in datasets on the
关键词: Skin lesions |  Bias |  Fairness |  Multi-task learning |  Adversarial learning

2. DREAMS: Diverse Reactions of Engagement and Attention Mind States Dataset NSTL国家科技图书文献中心

Monisha Singh |  Gulshan Sharma... -  《Pattern Recognition,Part XIV》 -  International Conference on Pattern Recognition - 2025, - 163~179 - 共17页

摘要:. In single and transfer learning task settings |  and multitask learning compared to single-task | -task, transfer learning task, and multi-task settings |  in improving users' learning experiences |  individuals show towards a particular task. Attention, on
关键词: Engagement |  Attention |  Single-Task learning |  Transfer learning |  Multi-Task learning |  Transformers

3. Single-shot fringe projection profilometry based on multi-task learning: efficient depth reconstruction without explicit system calibrations NSTL国家科技图书文献中心

Zhong, Xiaopin |  Huang, Junhao... -  《Physica Scripta》 - 2025,100(2) - 共21页

摘要: image. In this study, we propose a multi-task learning |  learning method for single-shot calibrationless FPP |  only a single projected fringe, which is important |  reliable depth reconstruction from a single-shot fringe |  reconstruction from single-shot FPP, eliminating the need for
关键词: Fringe projection profilometry |  depth reconstruction |  multi-task learning |  deep neural network |  system calibration

4. You Only Learn One Query: Learning Unified Human Query for Single-Stage Multi-person Multi-task Human-Centric Perception NSTL国家科技图书文献中心

Sheng Jin |  Shuhuai Li... -  《Computer Vision - ECCV 2024,Part XVIII》 -  European Conference on Computer Vision - 2025, - 126~146 - 共21页

摘要: single-stage multi-person multi-task human-centric |  multi-task learning of HCP tasks has not been fully |  perception (HCP). Our approach centers on learning a |  have been well-studied individually, single-stage | -art performance among multi-task HCP models and its
关键词: Human-Centric perception |  Unified vision model

5. Single-task regression naturally adapts to multi-species (eco)toxicological modelling: a case study on animals NSTL国家科技图书文献中心

Suyu,Mei -  《Environmental Science and Pollution Research》 - 2025,32(8) - 4910~4925 - 共16页

摘要: of single-task regression to naturally adapt |  single-task regression model achieves a 0.08 ~ 0.49 R2 | ) exhibits top importance to single-task regression and |  health. Existing local and multi-task models commonly |  pesticides among tested species as multi-task regression
关键词: In silico (eco)toxicological modelling |  Multi-task regression |  Single-task regression |  Chemical fingerprints |  QSAR |  Transfer learning

6. Multi-swarm multi-tasking ensemble learning for multi-energy demand prediction NSTL国家科技图书文献中心

Song H. |  Jalili M.... -  《Applied energy》 - 2025,377(Jan.1 Pt.C) - 1.1~1.12 - 共12页

摘要: is evaluated against single-task learning (STL) and | . The proposed method comprises single-task |  learning (EL). For each prediction task, several subtasks | -tasking ensemble learning (MSMTEL) framework for solving |  pretraining, multi-task optimization (MTO), and ensemble
关键词: Deep neural network |  Energy demand prediction |  Ensemble learning |  Multi-swarm particle swarm optimization |  Multi-task optimization

7. MG-SIN: Multigraph Sparse Interaction Network for Multitask Stance Detection NSTL国家科技图书文献中心

Heyan Chai |  Jinhao Cui... -  《IEEE transactions on neural networks and learning systems》 - 2025,36(2) - 3111~3125 - 共15页

摘要: degrading performance. Although several single-task |  boost the learning of task-specific representations. A |  learning methods have been proposed to capture richer |  multitask learning (MTL) to identify the stances and |  task-specific and task-related graphs (tr-graphs), to
关键词: Task analysis |  Pragmatics |  Social networking (online) |  Sentiment analysis |  Feature extraction |  Fuses |  Noise measurement

8. Enhanced NSCLC subtyping and staging through attention-augmented multi-task deep learning: A novel diagnostic tool NSTL国家科技图书文献中心

Yang R. |  Li W.... -  《International journal of medical informatics》 - 2025,193(Jan.) - 1.1~1.9 - 共9页

摘要: and those configured for single-task learning, as |  allocated. We evaluated multiple multi-task learning |  multi-task learning model enhanced with attention |  of this study is to develop a novel multi-task |  learning approach with attention encoders for classifying
关键词: Computed tomography |  Deep learning |  Histologic subtype |  Multi-task learning |  Non-small cell lung cancer

9. Deep multi-task learning based detection of correlated mental disorders using audio modality NSTL国家科技图书文献中心

Rohan Kumar Gupta |  Rohit Sinha -  《Computer speech & language》 - 2025,89(Jan.) - 101710.1~101710.14 - 共14页

摘要: disorders is a well-known phenomenon. Multi-task learning | -learning models, outperformed the corresponding single | -task learning (STL). The best relative improvement in |  interchangeably employed as an auxiliary task when the other is |  the main task. In addition, a few other tasks are
关键词: Human-computer interaction |  Correlated mental disorders |  Hybrid deep learning model |  Representation learning |  Cross-corpus generalization

10. A flow rate estimation method for gas-liquid two-phase flow based on filter-enhanced convolutional neural network NSTL国家科技图书文献中心

Yuxiao Jiang |  Yinyan Liu... -  《Engineering Applications of Artificial Intelligence》 - 2025,139(Jan. Pt.B) - 109593.1~109593.20 - 共20页

摘要: focused on a few human-set points with single task |  through multi-task learning (MTL). The adaptive noise |  challenging problem. Previously, deep learning-based methods |  learning. In addition, the data were not denoised. In |  estimate each single-phase flow rate simultaneously
关键词: Flow rate estimation |  Gas-liquid two-phase flow |  Frequency domain filtering |  Convolutional neural networks |  Multi-task learning
检索条件Single-Task learning

NSTL主题词

  • NSTL学科导航