检索结果-内蒙古大学图书馆

Dynamic Mask Curriculum Learning for Non-Autoregressive Neural Machine Translation 1

18th China Conference on Machine Translation, CCMT 2022

作者： Wang, Yisong Hou, Hongxu Sun, Shuo Wu, Nier Jian, Weichen Yang, Zongheng Wang, Pengcong National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Key Laboratory of Mongolian Information Processing Technology College of Computer Science Inner Mongolia University Hohhot China

ISBN: (数字)9789811979606

ISBN: (纸本)9789811979590

Non-autoregressive neural machine translation is gradually becoming a research hotspot due to its advantages of fast decoding. However, the increase of decoding speed is often accompanied by the loss of model performance. The main reason is that the target language information obtained at the decoder side is insufficient, and the mandatory parallel decoding leads to a large number of mistranslation and missing translation problems. In order to solve the problem of insufficient target language information, this paper proposes a dynamic mask curriculum learning approach to provide target side language information to the model. The target side self-attention layer is added in the pre-training phase to capture the target side information and adjust the amount of information input at any time by way of curriculum learning. The fine-tuning and inference phases disable the module in the same way as the normal NAT model. In this paper, we experiment on two translation datasets of WMT16, and the BLEU improvement reaches 4.4 without speed reduction. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

A Compact Broadband Metasurface Antenna Based on Hybrid Via-Wall Structures

A Compact Broadband Metasurface Antenna Based on Hybrid Via-...

引用

2023 International Applied Computational Electromagnetics Society Symposium, ACES-China 2023

作者： Chen, Dongxu Liu, Haotian Yang, Wanchen Chen, Jiaqi Cao, Ning Che, Wenquan Xue, Quan Computer and Information College Hohai University Jiangsu Nanjing210098 China The School of Electronic and Information Engineering South China University of Technology Guangdong Key Laboratory of Millimeter-Waves and Terahertz Guangzhou510641 China

ISBN: (纸本)9781733509657

In this work, a compact broadband metasurface (MTS) antenna using hybrid via-wall structures is firstly proposed. First, different via-wall MTS structures are derived from a conventional square MTS structure by folding the square patches downward and loading stacked patches horizontally in various configurations. These modifications effectively lower the resonance frequency and enable miniaturization to varying degrees. Furtherly, for a multi-resonance wideband feature, a hybrid MTS structure consisting of different via-wall structures is presented and then utilized to construct a MTS-based antenna by employing a slot-coupled feeding structure. With these hybrid via-wall structures that resonant at different frequencies, the MTS-based antenna can exhibit a wideband impedance matching. Finally, Theoretical results demonstrate that the proposed antenna achieves remarkable performance. It features a wide impedance bandwidth of 53.4% (5.419.35GHz) and delivers a high gain of approximately 5.9dBi within a compact overall size only 0.44λ0× 0.44λ0× 0.07 λ0 © 2023 Applied Computational Electromagnetics Society (ACES).

关键词： Slot antennas

来源：评论

学校读者我要写书评

暂无评论

A thermo-responsive rewritable plasmonic bio-memory by regulating single core-satellite gold nanocluster dissociation

引用

Nano Research 2024年第8期17卷 7275-7282页

作者： Wen Zhang Yi Wang Yamin Wang Xiaomei Lu Weibing Wu Quli Fan Lei Zhang State Key Laboratory of Organic Electronics and Information Displays&Institute of Advanced Materials(IAM) Nanjing University of Posts&TelecommunicationsNanjing 210023China Jiangsu Co-Innovation Center for Efficient Processing and Utilization of Forest Resources College of Light Industry and Food EngineeringNanjing Forestry UniversityNanjing 210037China Zhengzhou Institute of Biomedical Engineering and Technology Zhengzhou 450001China Key Laboratory of Flexible Electronics(KLOFE) Institute of Advanced Materials(IAM)&School of Flexible Electronics(Future Technologies)Nanjing Tech University(Nanjing Tech)Nanjing 211816China

A thermo-responsive rewritable plasmonic bio-memory chip has been successfully fabricated on an indium tin oxide(ITO)glass slide by assembling core-satellite gold nanoclusters with different size of gold nanoparticles(AuNPs)using double-strand DNA(dsDNA)*** the prepared 70@DNA20@13 gold nanoclusters(AuNCs)exhibited more stable and greater photothermal conversion *** short time irradiation by 633 nm microbeam laser,every individual AuNCs could be excited and remove the satellite AuNPs on its ***,in the dissociation process of AuNCs with 3−5 satellite,its color would change from yellow to green,which showed more significant reduction in the red channel of the dark-field microscopy(DFM)images and could be defined to state“0”and“1”***,this plasmonic nano bio-memory could transform cyclically its state between 0 and 1 which exhibited excellent rewritable ability.

关键词： plasmonic assembly thermal-responsive single nanoparticle rewritable bio-memory

来源：评论

学校读者我要写书评

暂无评论

Document-Level Event Extraction via information Interactivion Based on Event Relation and Argument Correlation 30

Document-Level Event Extraction via Information Interactivio...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Pan, Bangze Li, Yang Wang, Suge Li, Xiaoli Li, Deyu Liao, Jian Zheng, JianXing School of Computer and Information Technology Shanxi University Taiyuan China School of Finance Shanxi University of Finance and Economics Taiyuan China Institute for Infocomm Research A*STAR Singapore Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Taiyuan China

ISBN: (纸本)9782493814104

Document-level Event Extraction (DEE) is a vital task in NLP as it seeks to automatically recognize and extract event information from a document. However, current approaches often overlook intricate relationships among events and subtle correlations among arguments within a document, which can significantly impact the effectiveness of event type recognition and the extraction of cross-sentence arguments in DEE task. This paper proposes a novel Correlation Association Interactive Network (CAINet), comprising two key components: event relationship graph and argument correlation graph. In particular, the event relationship graph models the relationship among various events through structural associations among event nodes and sentence nodes, to improve the accuracy of event recognition. On the other hand, the arguments correlation graph models the correlations among arguments by quantifying the strength of association among arguments, to effectively aggregate cross-sentence arguments, contributing to the overall success of DEE. Furthermore, we use the large language model to execute DEE task experiments. Experimental results show the proposed CAINet outperforms existing state-of-the-art models and large language models in terms of F1-score across two benchmark datasets. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Chinese Summary Generation Algorithm Based on Contrastive Attention Mechanism 4

Chinese Summary Generation Algorithm Based on Contrastive At...

引用

4th International Symposium on computer Engineering and Intelligent Communications, ISCEIC 2023

作者： Guo, Liupeng Xiao, Yannan Wen, Yayuan Wen, Peizhi Guilin University of Electronic Technology School of Computer and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China Guilin University of Electronic Technology School of Computer and Information Security Guilin China Guangxi Normal University School of Electronic and Information Engineering School of Integrated Circuits Guilin China

ISBN: (纸本)9798350306323

Generative summarization based on the seq2seq model has gained widespread adoption due to the advancements and efficacy of the sequence-to-sequence framework. However, these models encounter challenges in handling out-of-vocabulary words and may produce summaries with factual inaccuracies. This paper addresses these issues by proposing a summarization generation model, MBC, which is built upon the Transformer as the baseline model. Additionally, it incorporates the BERT pre-trained model, pointer generation network, contrastive attention mechanism, and coverage loss. The model employs a pointer generation network to augment its vocabulary coverage capabilities by generating new terms. To enhance the representation of key information from the source text, a contrastive attention mechanism is employed during summary generation. In addition, by introducing coverage loss, the model can reduce repetitive content in the summary. To assess the model's performance, this paper employs ROUGE values as evaluation metrics and conducts comparative experiments with other models using the LCSTS dataset. The experimental results demonstrate that, in comparison with other models, this model is more adept at attending to salient information within the source text and generating summaries of greater accuracy. © 2023 IEEE.

关键词： BERT pre-training model contrastive attention mechanism coverage loss pointer generation network seq2seq model

来源：评论

学校读者我要写书评

暂无评论

A Multi-Stage Goal-Driven Network for Pedestrian Trajectory Prediction 5

A Multi-Stage Goal-Driven Network for Pedestrian Trajectory ...

引用

5th International Conference on computer Vision, Image and Deep Learning, CVIDL 2024

作者： Wu, Xiuen Wang, Tao Cai, Yuanzheng Liang, Lingyu Papageorgiou, George Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China Fuzhou University College of Computer and Data Science Fuzhou China South China University of Technology School of Electronic and Information Engineering Guangzhou China European University Cyprus Department of Computer Science and Engineering Nicosia Cyprus

ISBN: (纸本)9798350373820

Pedestrian trajectory prediction plays a pivotal role in ensuring the safety and efficiency of various applications, including autonomous vehicles and traffic management systems. This paper proposes a novel method for pedestrian trajectory prediction, called multi-stage goal-driven network (MGNet). Diverging from prior approaches relying on stepwise recursive prediction and the singular forecasting of a long-term goal, MGNet directs trajectory generation by forecasting intermediate stage goals, thereby reducing prediction errors. The network comprises three main components: a conditional variational autoencoder (CVAE), an attention module, and a multi-stage goal evaluator. Trajectories are encoded using conditional variational autoencoders to acquire knowledge about the approximate distribution of pedestrians' future trajectories, and combined with an attention mechanism to capture the temporal dependency between trajectory sequences. The pivotal module is the multi-stage goal evaluator, which utilizes the encoded feature vectors to predict intermediate goals, effectively minimizing cumulative errors in the recursive inference process. The effectiveness of MGNet is demonstrated through comprehensive experiments on the JAAD and PIE datasets. Comparative evaluations against state-of-the-art algorithms reveal significant performance improvements achieved by our proposed method. © 2024 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

BEVUDA++: Geometric-Aware Unsupervised Domain Adaptation for Multi-View 3D Object Detection

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第5期35卷 5109-5122页

作者： Zhang, Rongyu Liu, Jiaming Li, Xiaoqi Chi, Xiaowei Wang, Dan Du, Li Du, Yuan Zhang, Shanghang Nanjing University School of Electronic Science and Engineering Nanjing210093 China The Hong Kong Polytechnic University Department of Computing Hung Hom Hong Kong Peking University National Key Laboratory for Multimedia Information Processing School of Computer Science Beijing100871 China The Hong Kong University of Science and Technology Academy of Interdisciplinary Studies Hung Hom Hong Kong

Vision-centric Bird’s Eye View (BEV) perception holds considerable promise for autonomous driving. Recent studies have prioritized efficiency or accuracy enhancements, yet the issue of domain shift has been overlooked, leading to substantial performance degradation upon transfer. We identify major domain gaps in real-world cross-domain scenarios and initiate the first effort to address the Domain Adaptation (DA) challenge in multi-view 3D object detection for BEV perception. Given the complexity of BEV perception approaches with their multiple components, domain shift accumulation across multi-geometric spaces (e.g., 2D, 3D Voxel, BEV) poses a significant challenge for BEV domain adaptation. In this paper, we introduce an innovative geometric-aware teacher-student framework, BEVUDA++, to diminish this issue, comprising a Reliable Depth Teacher (RDT) and a Geometric Consistent Student (GCS) model. Specifically, RDT effectively blends target LiDAR with dependable depth predictions to generate depth-aware information based on uncertainty estimation, enhancing the extraction of Voxel and BEV features that are essential for understanding the target domain. To collaboratively reduce the domain shift, GCS maps features from multiple spaces into a unified geometric embedding space, thereby narrowing the gap in data distribution between the two domains. Additionally, we introduce a novel Uncertainty-guided Exponential Moving Average (UEMA) to further reduce error accumulation due to domain shifts informed by previously obtained uncertainty guidance. To demonstrate the superiority of our proposed method, we execute comprehensive experiments in four cross-domain scenarios, securing state-of-the-art performance in BEV 3D object detection tasks, e.g., 12.9% NDS and 9.5% mAP enhancement on Day-Night adaptation. © 1991-2012 IEEE.

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

A Quantitative Estimation Method of Migrating Insects Using Weather Radar by High Resolution Radar Joint Observation

A Quantitative Estimation Method of Migrating Insects Using ...

引用

IET International Radar Conference 2023, IRC 2023

作者： Li, Jiayi Cui, Kai Hu, Cheng Wang, Rui Mao, Huafeng Radar Research Laboratory School of Information and Electronics Beijing Institute of Technology Beijing100081 China Key Laboratory of Embedded Real-time Information Processing Technology Radar Research Laboratory School of Information and Electronic Beijing Institute of Technology Beijing100081 China School of Computer Sciences Beijing Institute of Technology Beijing100081 China Advanced Technology Research Institute Beijing Institute of Technology Jinan250300 China

ISBN: (纸本)9781839539954

The main migration animals in China are insects, and a large number of large-scale seasonal migration insects have a great impact on ecology. The establishment of a comprehensive early warning system for migratory insects necessitates the implementation of large-scale macro monitoring. Among the array of methodologies available, weather radar stands out as an efficacious tool for facilitating extensive macro-level monitoring. Nonetheless, several unresolved challenges persist in accurately quantifying the density of vast insect populations on a large scale. This article introduces an innovative method for insect quantification through the collaborative use of weather radar and high-resolution phased array radar for insect target observation and joint data analysis. This novel method harnesses the collective observational data derived from both weather radar and high-resolution radar systems, harmonizing the temporal and spatial dimensions of these datasets. By establishing a nuanced mapping correlation between insect density and weather radar reflectivity, this method enables the determination of insect density within specific geographical regions. In the final part of this article, joint observation experiments were conducted to examine the experimental data collected from operating weather radar and specialized phased array radar systems. A total of 244 days of data were analysed, and the proposed method was rigorously validated. © The Institution of Engineering & technology 2023.

关键词： Radar reflection

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Context Modeling for Road Obstacle Detection 1

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Wu, Xiuen Wang, Tao Liang, Lingyu Li, Zuoyong Ching, Fum Yew College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350108 China The Key Laboratory of Cognitive Computing and Intelligent Information Processing of Fujian Education Institutions Wuyi University Wuyishan354300 China School of Electronic and Information Engineering South China University of Technology Guangzhou510641 China Ministry of Education Key Laboratory of Computer Network and Information Integration Southeast University Nanjing211189 China Guangzhou510320 China Penang11800 Malaysia

ISBN: (数字)9783031200960

ISBN: (纸本)9783031200953

Road obstacle detection is an important problem for vehicle driving safety. In this paper, we aim to obtain robust road obstacle detection based on spatio-temporal context modeling. Firstly, a data-driven spatial context model of the driving scene is constructed with the layouts of the training data. Then, obstacles in the input image are detected via the state-of-the-art object detection algorithms, and the results are combined with the generated scene layout. In addition, to further improve the performance and robustness, temporal information in the image sequence is taken into consideration, and the optical flow is obtained in the vicinity of the detected objects to track the obstacles across neighboring frames. Qualitative and quantitative experiments were conducted on the Small Obstacle Detection (SOD) dataset and the Lost and Found dataset. The results indicate that our method with spatio-temporal context modeling is superior to existing methods for road obstacle detection. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Improving the Robustness of Low-Resource Neural Machine Translation with Adversarial Examples 1

引用

18th China Conference on Machine Translation, CCMT 2022

作者： Sun, Shuo Hou, Hongxu Wu, Nier Yang, Zongheng Wang, Yisong Wang, Pengcong Jian, Weichen Inner Mongolia Key Laboratory of Mongolian Information Processing Technology National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian College of Computer Science Inner Mongolia University Hohhot China

ISBN: (数字)9789811979606

ISBN: (纸本)9789811979590

Weak robustness and noise adaptability are major issues for Low-Resource Neural Machine Translation (NMT) models. That is, once some tiny perturbs are added to the input sentence, the model will produce completely different translation with high confidence. Adversarial example is currently a major tool to improve model robustness and how to generate an adversarial examples that can degrade the performance of the model and ensure semantic consistency is a challenging task. In this paper, we adopt reinforcement learning to generate adversarial example for low-resource NMT. Specifically, utilizing the actor-critic algorithm to modify the source sentence, the discriminator and translation model in the environment are used to determine whether the generated adversarial examples maintain semantic consistency and the overall deterioration of the model. Furthermore, we also install a language model reward to measure the fluency of adversarial examples. Experimental results on low-resource translation tasks show that our method highly aggressive to the model while maintaining semantic constraints greatly. Moreover, the model performance is significantly improved after fine-tuning with adversarial examples. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Neural machine translation

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：