NSTL国家科技图书文献中心

1. Enhancing Mechanical Property Consistency in AE81 Alloy Low-Pressure Die-Casting Wheels Through Ca Addition NSTL国家科技图书文献中心

Ziwen Li | Tian Li ... - 《75th World Foundry Congress (WFC 2024),Volume 1 of 2》 - World Foundry Congress - 2024, - 305～306 - 共2页

摘要：AE81M and AE81M+Ca magnesium alloy were employed in the production of 16-inch wheels through a low-pressure die casting (LPDC) process. Defects in the castings were inspected and analysed, revealing e...

关键词： Mg alloy | low pressure die casting | oxides

2. Half Aggregation Transformer for Exposure Correction NSTL国家科技图书文献中心

Ziwen Li | Jinpu Zhang ... - 《Pattern Recognition and Computer Vision: 6th Chinese Conference, PRCV 2023, Xiamen, China, October 13-15, 2023, Proceedings, Part X》 - Chinese Conference on Pattern Recognition and Computer Vision - 2024, - 469～481 - 共13页

摘要：Photos taken under poor illumination conditions often suffer from unsatisfactory visual effects. Recently, Transformer, avoiding the shortcomings of CNN models, has shown impressive performance on var...

关键词： Exposure correction | Transformer | Illumination guidance

3. KD-FORMER: TRANSFORMER KNOWLEDGE DISTILLATION FOR IMAGE MATTING NSTL国家科技图书文献中心

Ziwen Li | Bo Xu ... - 《ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2024), Vol.4: Seoul, South Korea.14-19 April 2024》 - IEEE International Conference on Acoustics, Speech and Signal Processing - 2024, - 2490～2494 - 共5页

摘要：Vision transformers (ViTs) have been outstanding in multiple dense prediction tasks, including image matting. However, the high computational and training costs of ViTs lead to a bottleneck for applic...

关键词： matting | dense prediction | knowledge distillation

4. Short-Term Prediction of Multi-Load in Integrated Energy Systems Based on Coupling Characteristic Analysis and Multi-Task Learning NSTL国家科技图书文献中心

Ziwen Li | Guangdi Li ... - 《2024 Second International Conference on Cyber-Energy Systems and Intelligent Energy》 - International Conference on Cyber-Energy Systems and Intelligent Energy - 2024, - 1～6 - 共6页

摘要：With the continuous development of integrated energy technology and the diversification of users' energy demand, the current single load forecasting method is no longer satisfied with the requirements...

关键词： Couplings | Training | Correlation coefficient | Analytical models | Load forecasting | Heuristic algorithms | Predictive models | Prediction algorithms | Multitasking | Load modeling

5. Cross Layer Weakly Supervised Data Augmentation Network for Offline Signature Verification NSTL国家科技图书文献中心

Yongliang Zhang | Jiahang Wang ... - 《2024 International Joint Conference on Neural Networks,[v.1]》 - International Joint Conference on Neural Networks - 2024, - 1～8 - 共8页

摘要：Current Offline Signature Verification(OSV) methods based on deep learning predominantly rely on deep semantic information for discrimination, while often neglecting shallow visual features. This negl...

关键词： Training | Cross layer design | Visualization | Accuracy | Supervised learning | Semantics | Training data

6. Spiking-NeRF: Spiking Neural Network for Energy-Efficient Neural Rendering NSTL国家科技图书文献中心

ZIWEN LI | YU MA ... - 《ACM Journal on Emerging Technologies in Computing Systems》 - 2024,20(3) - 10～ - 共23页

摘要：Artificial Neural Networks (ANNs) have achieved remarkable performance in many artificial intelligence tasks. As the application scenarios become more sophisticated, the computation and energy consump...

关键词： Spiking neural network (SNN) | Neural rendering | Neural radiance field

7. A Dynamic Tracking Framework Based on Scene Perception NSTL国家科技图书文献中心

Jinpu Zhang | Ziwen Li ... - 《Pattern Recognition and Computer Vision: 6th Chinese Conference, PRCV 2023, Xiamen, China, October 13-15, 2023, Proceedings, Part XII》 - Chinese Conference on Pattern Recognition and Computer Vision - 2024, - 185～197 - 共13页

摘要：While recent large models have greatly improved tracking performance, not all scenes require a large and complex network. Dynamic networks can adapt the architecture to different inputs, leading to no...

关键词： Object tracking | Dynamic network | Scene router

8. SDNet: An Extremely Efficient Portrait Matting Model via Self-Distillation NSTL国家科技图书文献中心

Ziwen Li | Bo Xu ... - 《2024 IEEE/CVF Winter Conference on Applications of Computer Vision: WACV 2024, Waikoloa, Hawaii, USA, 3-8 January 2024, [v.11]》 - IEEE/CVF Winter Conference on Applications of Computer Vision - 2024, - 5613～5622 - 共10页

摘要：Most existing portrait matting models either require expensive auxiliary information or try to decompose the task into sub-tasks that are usually resource-hungry. These challenges limit its applicatio...

关键词： Training | Performance evaluation | Adaptation models | Computer vision | Fuses | Computational modeling | Pipelines

9. An Integrated Learning Carbon Emission Prediction Algorithm Optimized for Stacking Based On Genetic Algorithm NSTL国家科技图书文献中心

Hai He | Yuan Pan ... - 《2024 Second International Conference on Cyber-Energy Systems and Intelligent Energy》 - International Conference on Cyber-Energy Systems and Intelligent Energy - 2024, - 1～5 - 共5页

摘要：With the proposed double carbon goal, it is of great practical significance to forecast the carbon emission of energy industry. This paper presents a carbon emission prediction method based on genetic...

关键词： Accuracy | Electricity | Stacking | Steel industry | Carbon dioxide | Production | Predictive models | Prediction algorithms | Steel | Genetic algorithms

10. Research on Data-Driven Carbon Emission Prediction Method for the Steel Industry NSTL国家科技图书文献中心

Hai He | Yuan Pan ... - 《2024 Second International Conference on Cyber-Energy Systems and Intelligent Energy》 - International Conference on Cyber-Energy Systems and Intelligent Energy - 2024, - 1～6 - 共6页

摘要：With the increasing global attention to environmental issues, carbon reduction has become a crucial task across industries. The steel industry, as one of the significant sources of carbon emissions, p...

关键词： Stacking | Steel industry | Error compensation | Carbon dioxide | Predictive models | Data models | Bayes methods | Ensemble learning | Steel | Optimization

摘要：AE81M and AE81M+Ca magnesium alloy were employed in the production of 16-inch wheels through a low-pressure die casting (LPDC) process. Defects in the castings were inspected and analysed, revealing e...

关键词： Mg alloy | low pressure die casting | oxides

摘要：Photos taken under poor illumination conditions often suffer from unsatisfactory visual effects. Recently, Transformer, avoiding the shortcomings of CNN models, has shown impressive performance on var...

关键词： Exposure correction | Transformer | Illumination guidance

摘要：Vision transformers (ViTs) have been outstanding in multiple dense prediction tasks, including image matting. However, the high computational and training costs of ViTs lead to a bottleneck for applic...

关键词： matting | dense prediction | knowledge distillation

摘要：With the continuous development of integrated energy technology and the diversification of users' energy demand, the current single load forecasting method is no longer satisfied with the requirements...

关键词： Couplings | Training | Correlation coefficient | Analytical models | Load forecasting | Heuristic algorithms | Predictive models | Prediction algorithms | Multitasking | Load modeling

摘要：Current Offline Signature Verification(OSV) methods based on deep learning predominantly rely on deep semantic information for discrimination, while often neglecting shallow visual features. This negl...

关键词： Training | Cross layer design | Visualization | Accuracy | Supervised learning | Semantics | Training data

摘要：Artificial Neural Networks (ANNs) have achieved remarkable performance in many artificial intelligence tasks. As the application scenarios become more sophisticated, the computation and energy consump...

关键词： Spiking neural network (SNN) | Neural rendering | Neural radiance field

摘要：While recent large models have greatly improved tracking performance, not all scenes require a large and complex network. Dynamic networks can adapt the architecture to different inputs, leading to no...

关键词： Object tracking | Dynamic network | Scene router

摘要：Most existing portrait matting models either require expensive auxiliary information or try to decompose the task into sub-tasks that are usually resource-hungry. These challenges limit its applicatio...

关键词： Training | Performance evaluation | Adaptation models | Computer vision | Fuses | Computational modeling | Pipelines

摘要：With the proposed double carbon goal, it is of great practical significance to forecast the carbon emission of energy industry. This paper presents a carbon emission prediction method based on genetic...

关键词： Accuracy | Electricity | Stacking | Steel industry | Carbon dioxide | Production | Predictive models | Prediction algorithms | Steel | Genetic algorithms

摘要：With the increasing global attention to environmental issues, carbon reduction has become a crucial task across industries. The steel industry, as one of the significant sources of carbon emissions, p...

关键词： Stacking | Steel industry | Error compensation | Carbon dioxide | Predictive models | Data models | Bayes methods | Ensemble learning | Steel | Optimization

4008-161-200 800-990-8900

国家科技图书文献中心