检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhou, Shibo Yang, Bo Yuan, Mengwen Jiang, Runhao Yan, Rui Pan, Gang Tang, Huajin Research Center for Data Hub and Security Zhejiang Lab Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China Research Center for High Efficiency Computing System Zhejiang Lab Hangzhou China College of Computer Science and Technology Zhejiang University of Technology Hangzhou China The State Key Lab of Brain-Machine Intelligence Zhejiang University Hangzhou China

Spiking Neural Networks (SNNs), renowned for their low power consumption, brain-inspired architecture, and spatio-temporal representation capabilities, have garnered considerable attention in recent years. Similar to Artificial Neural Networks (ANNs), high-quality benchmark datasets are of great importance to the advances of SNNs. However, our analysis indicates that many prevalent neuromorphic datasets lack strong temporal correlation, preventing SNNs from fully exploiting their spatio-temporal representation capabilities. Meanwhile, the integration of event and frame modalities offers more comprehensive visual spatio-temporal information. Yet, the SNN-based cross-modality fusion remains underexplored. In this work, we present a neuromorphic dataset called DVS-SLR that can better exploit the inherent spatio-temporal properties of SNNs. Compared to existing datasets, it offers advantages in terms of higher temporal correlation, larger scale, and more varied scenarios. In addition, our neuromorphic dataset contains corresponding frame data, which can be used for developing SNN-based fusion methods. By virtue of the dual-modal feature of the dataset, we propose a Cross-Modality Attention (CMA) based fusion method. The CMA model efficiently utilizes the unique advantages of each modality, allowing for SNNs to learn both temporal and spatial attention scores from the spatio-temporal features of event and frame modalities, subsequently allocating these scores across modalities to enhance their synergy. Experimental results demonstrate that our method not only improves recognition accuracy but also ensures robustness across diverse scenarios. © 2024, CC0.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Emergent mobility edges and intermediate phases in one-dimensional quasiperiodic plasmonic chains

引用

Physical Review Research 2024年第1期6卷 013322-013322页

作者： Yizhi Hu Kun Yan Xiaobin Chen School of Science State Key Laboratory on Tunable Laser Technology and Ministry of Industry and Information Technology Key Lab of Micro-Nano Optoelectronic Information System Harbin Institute of Technology Shenzhen Shenzhen 518055 China Collaborative Innovation Center of Extreme Optics Shanxi University Taiyuan 030006 China

Anderson localization has been widely studied in low-dimensional aperiodic electronic, photonic, and acoustic systems. However, the disorder effect in the plasmonic system, where retardation and long-range couplings interact in complex ways, remains an open question. In this work, we investigate the localization properties of one-dimensional quasiperiodic plasmonic chains using the coupled dipole method and linearized Green's function. Our models, which incorporate nearest-neighbor or long-range dipole interactions, reveal localization transitions, mobility edges, and intermediate phases. It is found that long-range dipole interactions and non-Hermiticity due to retardation both play crucial roles in Anderson localization, yielding the emergence of intermediate phases with varying widths. A link between non-Hermiticity and Anderson transition is established by the mean phase rigidity, revealing strong non-Hermiticity along the phase boundary. The plasmonic model involving long-range interplay and retarded effect presents richer localization phenomena than the electronic counterpart that usually includes only nearest-neighbor coupling, laying a foundation for experimental observations of Anderson localization on plasmonic platforms.

关键词： Anderson localization Localization Surface plasmons Disordered systems Green's function methods

来源：评论

学校读者我要写书评

暂无评论

6DoF-ICTC: A Deep Image Feature Extraction Network Combining Transformers and CNNs for 6DoF Pose Estimation 12

6DoF-ICTC: A Deep Image Feature Extraction Network Combining...

引用

12th International Conference on CYBER technology in Automation, Control, and Intelligent systems, CYBER 2022

作者： Zhang, Liming Zhou, Xin Zhu, Baixian Wang, Can Wu, Xinyu Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology China University of Science and Technology of China China Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

In this work, we propose a new image feature extraction network for 6D pose estimation tasks. The majority of existing 6D pose estimation networks are based on the RGBD input, which is the fusion of images and point clouds. They are mainly working on keypoint extraction, point cloud feature extraction, and other tasks, however, image features, on the other hand, mainly rely on CNN networks that are currently advanced. With the development of Vision Transformer in the field of computer vision, the results on ImageNet demonstrate its benefit of extracting global features, and we see new directions that the Transformers can bring to the area of image feature extraction. ICTC is a Transformer paired with a CNN network that fuses the retrieved global features into each pixel and then does local feature extraction. This provides greater robustness to 6D pose estimation In complex situations such as shifting lighting conditions and object occlusion. Our method achieves 96% accuracy using the average ADD metric on the LineMOD dataset, demonstrating our method's effectiveness. © 2022 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Meta-device:advanced manufacturing

引用

Light(Advanced Manufacturing) 2024年第1期5卷 115-130页

作者： Borui Leng Yao Zhang Din Ping Tsai Shumin Xiao Department of Electrical Engineering City University of Hong KongHong Kong999077China Centre for Biosystems Neuroscience and NanotechnologyCity University of Hong KongHong Kong999077China The State Key Laboratory of Terahertz and Millimeter Waves City University of Hong KongHong Kong999077China Ministry of Industry and Information Technology Key Lab of Micro-Nano Optoelectronic Information System Guangdong Provincial Key Laboratory of Semiconductor Optoelectronic Materials and Intelligent Photonic SystemsHarbin Institute of TechnologyShenzhen 518055China Pengcheng Laboratory Shenzhen 518055China

Metasurfaces are one of the most promising devices to break through the limitations of bulky optical *** offering a new method of light manipulation based on the light-matter interaction in subwavelength nanostructures,metasurfaces enable the efficient manipulation of the amplitude,phase,polarization,and frequency of light and derive a series of possibilities for important ***,one key challenge for the realization of applications for meta-devices is how to fabricate large-scale,uniform nanostructures with high *** this review,we review the state-of-the-art nanofabrication techniques compatible with the manufacture of *** lithography,masked lithography,and other nanofabrication techniques are highlighted in *** also delve into the constraints and limitations of the current fabrication methods while providing some insights on solutions to overcome these challenges for advanced nanophotonic applications.

关键词： Meta-device Metasurface Nanofabrication COMS-compatible fabrication

来源：评论

学校读者我要写书评

暂无评论

Instruction Pre-Training: Language Models are Supervised Multitask Learners

arXiv

引用

arXiv 2024年

作者： Cheng, Daixuan Gu, Yuxian Huang, Shaohan Bi, Junyu Huang, Minlie Wei, Furu Microsoft Research The CoAI Group DCST Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University China

Unsupervised multitask pre-training has been the critical method behind the recent success of language models (LMs). However, supervised multitask learning still holds significant promise, as scaling it in the post-training stage trends towards better generalization. In this paper, we explore supervised multitask pretraining by proposing Instruction Pre-Training, a framework that scalably augments massive raw corpora with instruction-response pairs to pre-train LMs. The instruction-response pairs are generated by an efficient instruction synthesizer built on open-source models. In our experiments, we synthesize 200M instruction-response pairs covering 40+ task categories to verify the effectiveness of Instruction Pre-Training. In pre-training from scratch, Instruction Pre-Training not only consistently enhances pre-trained base models but also benefits more from further instruction tuning. In continual pre-training, Instruction Pre-Training enables Llama3-8B to be comparable to or even outperform Llama3-70B. Our model, code, and data are available at https://***/microsoft/LMOps. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

arXiv

引用

arXiv 2023年

作者： Liu, Yuanhao Cao, Qi Shen, Huawei Wu, Yunfan Tao, Shuchang Cheng, Xueqi Data Intelligence System Research Center Institute of Computing Technology CAS University of Chinese Academy of Sciences Beijing China Data Intelligence System Research Center Institute of Computing Technology CAS China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology CAS University of Chinese Academy of Sciences Beijing China

Recommender systems often suffer from popularity bias, where popular items are overly recommended while sacrificing unpopular items. Existing researches generally focus on ensuring the number of recommendations (exposure) of each item is equal or proportional, using inverse propensity weighting, causal intervention, or adversarial training. However, increasing the exposure of unpopular items may not bring more clicks or interactions, resulting in skewed benefits and failing in achieving real reasonable popularity debiasing. In this paper, we propose a new criterion for popularity debiasing, i.e., in an unbiased recommender system, both popular and unpopular items should receive Interactions Proportional to the number of users who Like it, namely IPL criterion. Under the guidance of the criterion, we then propose a debiasing framework with IPL regularization term which is theoretically shown to achieve a win-win situation of both popularity debiasing and recommendation performance. Experiments conducted on four public datasets demonstrate that when equipping two representative collaborative filtering models with our framework, the popularity bias is effectively alleviated while maintaining the recommendation performance. © 2023, CC BY.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Multimodal Biological Knowledge Graph Completion via Triple Co-Attention Mechanism

Multimodal Biological Knowledge Graph Completion via Triple ...

引用

International Conference on Data Engineering

作者： Derong Xu Jingbo Zhou Tong Xu Yuan Xia Ji Liu Enhong Chen Dejing Dou State Key Laboratory of Cognitive Intelligence University of Science and Technology of China Business Intelligence Lab Baidu Research Intelligent Healthcare Unit Baidu Big Data Lab Baidu Research BCG X

ISBN: (数字)9798350322279

ISBN: (纸本)9798350322286

Biological Knowledge Graphs (BKGs) can help to model complex biological systems in a structural way to support various tasks. Nevertheless, the incompleteness problem may limit the performance of existing BKGs, which still deserves new methods to reveal the missing relations. Though great efforts have been made to knowledge graph completion, existing methods are not easy to be adapted to the multimodal biological information such as molecular structures and textual descriptions. To this end, we propose a novel co-attention-based multimodal embedding framework, named CamE, for the multimodal BKG completion task. Specifically, we design a Triple Co-Attention (TCA) operator to capture and highlight the same semantic features among different modalities. Based on TCA, we further propose two components to handle multimodal fusion and multimodal entity-relation interaction, respectively. One is the multimodal TCA fusion module to achieve a multimodal joint representation for each entity in the BKG. It aims to project different modal information into a common space by capturing the same semantic features and overcoming the modality gap. The other is the relation-aware interactive TCA module to learn interactive representation by modelling the deep interaction between multimodal entities and relations. Extensive experiments on two real-world multimodal BKG datasets demonstrate that our method significantly outperforms several state-of-the-art baselines, including 10.3% and 16.2% improvement w.r.t MRR and Hits@1 metrics over its best competitors on public DRKG-MM dataset.

关键词： Measurement Knowledge engineering Adaptation models Fuses Biological system modeling Semantics Knowledge graphs

来源：评论

学校读者我要写书评

暂无评论

Communication-Efficient Distributed Learning with Local Immediate Error Compensation

arXiv

引用

arXiv 2024年

作者： Cheng, Yifei Shen, Li Xu, Linli Qian, Xun Wu, Shiwei Zhou, Yiming Zhang, Tie Tao, Dacheng Chen, Enhong The Anhui Province Key Lab of Big Data Analysis and Application State Key Laboratory of Cognitive Intelligence School of Data Science School of Computer Science University of Science and Technology China The JD Explore Academy China The Shanghai Artificial Intelligence Laboratory China

Gradient compression with error compensation has attracted significant attention with the target of reducing the heavy communication overhead in distributed learning. However, existing compression methods either perform only unidirectional compression in one iteration with higher communication cost, or bidirectional compression with slower convergence rate. In this work, we propose the Local Immediate Error Compensated SGD (LIEC-SGD) optimization algorithm to break the above bottlenecks based on bidirectional compression and carefully designed compensation approaches. Specifically, the bidirectional compression technique is to reduce the communication cost, and the compensation technique compensates the local compression error to the model update immediately while only maintaining the global error variable on the server throughout the iterations to boost its efficacy. Theoretically, we prove that LIEC-SGD is superior to previous works in either the convergence rate or the communication cost, which indicates that LIEC-SGD could inherit the dual advantages from unidirectional compression and bidirectional compression. Finally, experiments of training deep neural networks validate the effectiveness of the proposed LIEC-SGD algorithm. Copyright © 2024, The Authors. All rights reserved.

关键词： Error compensation

来源：评论

学校读者我要写书评

暂无评论

Biochar technology cannot offset land carbon emissions in Guangdong province, China

引用

Carbon Research 2024年第1期3卷 1-14页

作者： Wang, Funing Zhou, Wenneng Wang, Xili Zhao, Qing Han, Mengjie State Key Lab of Clean Energy Utilization Institute of Carbon Neutrality State Environmental Protection Engineering Center for Coal-Fired Air Pollution Control Zhejiang University Hangzhou310027 China Jiaxing Research Institute Zhejiang University Jiaxing314000 China Guangdong Provincial Key Laboratory of Water Quality Improvement and Ecological Restoration for Watersheds School of Ecology Environment and Resources Guangdong University of Technology Guangzhou510006 China Economic & amp Information center Zhejiang310006 China Department of Earth System Science Ministry of Education Key Laboratory for Earth System Modeling Institute for Global Change Studies Tsinghua University Beijing100084 China Guangdong Key Laboratory of Integrated Agro-environmental Pollution Control and Management Institute of Eco-environmental and Soil Sciences Guangdong Academy of Sciences Guangzhou510650 China National-Regional Joint Engineering Research Center for Soil Pollution Control and Remediation in South China Guangzhou510650 China

As a highly developed region, Guangdong province has substantial industrial emissions. Its subtropical monsoon climate, characterized by abundant hydrothermal conditions, contributes to a substantial biomass potential. The adoption of potential biomass-based carbon dioxide removal (CDR) technologies, such as biochar, presents an opportunity to mitigate emissions and work towards carbon neutrality in the future. However, the current state of the land carbon balance and the CDR potential of biochar in Guangdong province remains unclear. We first calculated the land carbon balance based on inventory data. Then we estimated the CDR potential of biochar derived from agricultural residues, forestry residues, and bioenergy crops cultivated on marginal lands in Guangdong province using life cycle analysis (LCA). Results show that Guangdong province has not yet achieved carbon neutrality, with a net emission (carbon emissions remaining after offsetting by carbon sinks) of 925.63 Tg CO2e (CO2 equivalent, 1Tg = 106 t) in 2021. Emissions from energy consumption account for the highest proportion, contributing 83.8% of total emissions. In the highest biomass utilization scenario, the maximum CDR potential of biochar derived from all biomass types reaches 84.30 Tg CO2e yr-1, which could offset 9.11% of net carbon emissions in Guangdong province. Our findings provide crucial guidance for setting emission reduction targets and implementing effective mitigation strategies in Guangdong province under temperature warming. Graphical Abstract: (Figure presented.) © The Author(s) 2024.

关键词： Carbon capture and utilization

来源：评论

学校读者我要写书评

暂无评论

A LiDAR-Camera Fusion Network for Small Object Detection in Open-Pit Mining Areas

A LiDAR-Camera Fusion Network for Small Object Detection in ...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Muzhuo Liu Jie Wang Bin Zhou Zhangyu Wang Wentao Liu Mingyuan Wang State Key Lab of Intellgent Transportation system The Key Laboratory of Autonomous Transportation Technology for Special Vehicles School of Transportation Science and Engineering M1nistry of Industr and Information Technology Beihang University Beijing China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

As intelligent and autonomous driving technologies advance, the secure and productive functioning of mining trucks during autonomous operations is critically dependent on precise object detection within open-pit mining environments. Due to the sparse nature of point cloud data for small objects such as stones, cones, and equipment parts, they are susceptible to generating false negatives and false positives. Although camera images are rich in semantic content, the absence of precise depth cues renders them vulnerable to interference from background noise. Currently, the technology of fusing LiDAR point cloud and camera image data for 3D object detection is gaining popularity in this field. In this paper, we introduce a query feature generation strategy based on multi-scale image features in the cross-attention-based feature fusion module to generate high-quality fusion features for small objects. Additionally, within the traditional non-maximum suppression strategy, we introduce size factors and shape factors to alleviate the sensitivity of small objects to bounding box offsets. Notably, our network model has achieved an mAP of 88.0 and an NDS of 77.9 on the mining dataset, significantly enhancing the precision of detecting small objects over previous approaches.

关键词： Point cloud compression Training Three-dimensional displays Semantics Object detection Feature extraction Cameras Transformers Data models Data mining

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：