检索结果-内蒙古大学图书馆

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Shao, Chenze Ma, Zhengrui Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Non-autoregressive models achieve significant decoding speedup in neural machine translation but lack the ability to capture sequential dependency. Directed Acyclic Transformer (DA-Transformer) was recently proposed to model sequential dependency with a directed acyclic graph. Consequently, it has to apply a sequential decision process at inference time, which harms the global translation accuracy. In this paper, we present a Viterbi decoding framework for DA-Transformer, which guarantees to find the joint optimal solution for the translation and decoding path under any length constraint. Experimental results demonstrate that our approach consistently improves the performance of DA-Transformer while maintaining a similar decoding speedup. © 2022 Association for Computational Linguistics.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

A Unified Framework Integrating Knowledge and Data for Collaborative Root Cause Identification 5

A Unified Framework Integrating Knowledge and Data for Colla...

引用

5th International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2024

作者： Yu, Jiefei Cao, Zicheng He, Siyi Gu, Zuyi Xu, Yingcheng Zhong, Kai Institutes of Physical Science and Information Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui China School of Big Data and Statistics Anhui University Anhui China

ISBN: (纸本)9798331529192

Capturing the root cause and propagation path of the fault is critical to ensuring the safety and efficiency of industrial processes, especially those that inadequately utilize process knowledge and data. To address this issue, a unified framework integrating knowledge and data for collaborative root cause identification is proposed. First, the knowledge causal graph (KCG) is constructed using expert knowledge and industrial flow charts, providing a preliminary reference for subsequent causality analysis. Next, by replacing the traditional vector autoregression (VAR) model in Granger Causality (GC) with the gated recurrent unit (GRU), a more reliable causal relationship between variables is obtained. Additionally, a causality fusion propagation path identification method (CF-PPI) is designed to identify the root cause and propagation path of the fault, so that the obtained fault propagation path has less redundancy and higher accuracy. Finally, the method is validated using data from the ASHRAE RP-1043 centrifugal chiller. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

In-Context Compositional Generalization for Large Vision-Language Models

In-Context Compositional Generalization for Large Vision-Lan...

引用

2024 Conference on Empirical Methods in Natural Language processing, EMNLP 2024

作者： Li, Chuanhao Jing, Chenchen Li, Zhen Zhai, Mingliang Wu, Yuwei Jia, Yunde Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China School of Computer Science Zhejiang University Hangzhou China

ISBN: (纸本)9798891761643

Recent work has revealed that in-context learning for large language models exhibits compositional generalization capacity, which can be enhanced by selecting in-context demonstrations similar to test cases to provide contextual information. However, how to exhibit in-context compositional generalization (ICCG) of large vision-language models (LVLMs) is non-trival. Due to the inherent asymmetry between visual and linguistic modalities, ICCG in LVLMs faces an inevitable challenge-redundant information on the visual modality. The redundant information affects in-context learning from two aspects: (1) Similarity calculation may be dominated by redundant information, resulting in sub-optimal demonstration selection. (2) Redundant information in in-context demonstrations brings misleading contextual information to in-context learning. To alleviate these problems, we propose a demonstration selection method to achieve ICCG for LVLMs, by considering two key factors of demonstrations: content and structure, from a multimodal perspective. Specifically, we design a diversity-coverage-based matching score to select demonstrations with maximum coverage, and avoid selecting demonstrations with redundant information via their content redundancy and structural complexity. We build a GQA-ICCG dataset to simulate the ICCG setting, and conduct experiments on GQA-ICCG and the VQA v2 dataset. Experimental results demonstrate the effectiveness of our method. © 2024 Association for Computational Linguistics.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Improving Fake News Detection of Influential Domain via Domain- and Instance-Level Transfer 29

Improving Fake News Detection of Influential Domain via Doma...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Nan, Qiong Wang, Danding Zhu, Yongchun Sheng, Qiang Shi, Yuhui Cao, Juan Li, Jintao Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Both real and fake news in various domains, such as politics, health, and entertainment are spread via online social media every day, necessitating fake news detection for multiple domains. Among them, fake news in specific domains like politics and health has more serious potential negative impacts on the real world (e.g., the infodemic led by COVID-19 misinformation). Previous studies focus on multi-domain fake news detection, by equally mining and modeling the correlation between domains. However, these multi-domain methods suffer from a seesaw problem: the performance of some domains is often improved at the cost of hurting the performance of other domains, which could lead to an unsatisfying performance in specific domains. To address this issue, we propose a Domain- and Instance-level Transfer Framework for Fake News Detection (DITFEND), which could improve the performance of specific target domains. To transfer coarse-grained domain-level knowledge, we train a general model with data of all domains from the meta-learning perspective. To transfer fine-grained instance-level knowledge and adapt the general model to a target domain, we train a language model on the target domain to evaluate the transferability of each data instance in source domains and re-weigh each instance’s contribution. Offline experiments on two datasets demonstrate the effectiveness of DITFEND. Online experiments show that DITFEND brings additional improvements over the base models in a real-world scenario. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Fake detection

来源：评论

学校读者我要写书评

暂无评论

A Semantic Overlay on Blockchain for Supporting Traceability in Cross-border Logistics 2

A Semantic Overlay on Blockchain for Supporting Traceability...

引用

2nd IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2022

作者： Sun, Xiaoping Institute of Computing Technology Chinese Academy of Sciences Key Lab of Intelligent Information Processing Beijing China

ISBN: (纸本)9781665492270

Traceability is important for maintaining quality of logistics transactions and improving logistics efficiency. Implementing traceability for cross-border logistics is facing challenges when it lacks global centralized logistics information management services. Blockchain techniques enable a decentralized cross-border logistics management by publishing logistics transaction on blockchain transactions to support privacy protection and traceability. Logistics transactions involves complex interactions among participants. How to publish those interactions on a blockchain platform is a challenge. We propose a semantic overlay model that publishes a logistics transaction as a semantic link on a blockchain platform for supporting traceability. A semantic link schema model is designed and published on the blockchain platform to validate semantics links for ensuring the correctness of logistics transaction execution. The proposed semantic overlay on blockchain supports further extension of semantic computing in decentralized applications. © 2022 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

A Fast Clustering Based Evolutionary Algorithm for Super-Large-Scale Sparse Multi-Objective Optimization

引用

IEEE/CAA Journal of Automatica Sinica 2023年第4期10卷 1048-1063页

作者： Ye Tian Yuandong Feng Xingyi Zhang Changyin Sun Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information TechnologyAnhui UniversityHefei 230601China School of Computer Science and Technology Anhui UniversityHefei 230601China School of Artificial Intelligence Anhui UniversityHefei 230601China School of Automation Southeast UniversityNanjing 210096China

During the last three decades,evolutionary algorithms(EAs)have shown superiority in solving complex optimization problems,especially those with multiple objectives and non-differentiable ***,due to the stochastic search strategies,the performance of most EAs deteriorates drastically when handling a large number of decision *** tackle the curse of dimensionality,this work proposes an efficient EA for solving super-large-scale multi-objective optimization problems with sparse optimal *** proposed algorithm estimates the sparse distribution of optimal solutions by optimizing a binary vector for each solution,and provides a fast clustering method to highly reduce the dimensionality of the search *** importantly,all the operations related to the decision variables only contain several matrix calculations,which can be directly accelerated by *** existing EAs are capable of handling fewer than 10000 real variables,the proposed algorithm is verified to be effective in handling 1000000 real ***,since the proposed algorithm handles the large number of variables via accelerated matrix calculations,its runtime can be reduced to less than 10%of the runtime of existing EAs.

关键词： Evolutionary computation fast clustering sparse multi-objective optimization super-large-scale optimization

来源：评论

学校读者我要写书评

暂无评论

Optical performance monitoring of mode division multiplexing signal based on multi-task convolutional neural network 7

Optical performance monitoring of mode division multiplexing...

引用

7th Optics Young Scientist Summit, OYSS 2024

作者： He, Ting Chang, Huan Gao, Ran Wang, Fei Guo, Dong Beijing Institute of Technology No.5 Zhongguancun South Street Haidian District Beijing100081 China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China

ISBN: (数字)9781510688377

ISBN: (纸本)9781510688360

Mode division multiplexing (MDM) optical fiber communication technology enhances bandwidth utilization and communication capacity to address the increasing demand for high-capacity data transmission in the era of rapid network traffic growth. For MDM optical fiber communication systems affected by various impairments, optical performance monitoring (OPM) can effectively characterize the impairments in received optical signals, directly reflecting the transmission signal state and channel conditions, and help ensure efficient and stable network operation. In this paper, we propose a multi-task convolutional neural network (MT-CNN) aided OPM method for MDM signals. The proposed MTCNN combines convolutional neural networks and a multi-task learning framework to extract the transmission link information and predict the optical signal-to-noise ratio (OSNR) of few-mode channels synchronously. Simulation results show that the proposed MT-CNN-based OPM scheme can achieve accurate OSNR performance evaluation for MDM fiber transmission signals. © 2025 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

DeepPointMap2: Accurate and Robust LiDAR-Visual SLAM with Neural Descriptors 24

DeepPointMap2: Accurate and Robust LiDAR-Visual SLAM with Ne...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhang, Xiaze Ding, Ziheng Jing, Qi Cheng, Ying Ding, Wenchao Feng, Rui Fudan University Shanghai China The School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University China The Academy for Engineering and Technology Fudan University China The Shanghai Collaborative Innovation Center of Intelligent Visual Computing China

ISBN: (纸本)9798400706868

Simultaneous Localization and Mapping (SLAM) plays a pivotal role in autonomous driving and robotics. Existing methods often rely on hand-craft feature extraction and cross-modal fusion techniques, resulting in limited feature representation capability and reduced robustness. To address this challenge, we introduce DeepPointMap2, a novel learning-based LiDAR-Visual SLAM architecture that leverages neural descriptors to tackle multiple SLAM sub-tasks in a unified manner. Our approach employs neural networks to extract multi-modal tokens, which are then adaptively fused by the Visual-Point Fusion Module to generate sparse 3D neural descriptors, ensuring precise and robust performance. As a pioneering work, our method achieves state-of-the-art localization performance among various Visual-, LiDAR-, and Visual-LiDAR-based methods in widely-used benchmarks, as shown in the experiment results. Furthermore, the approach proves to be robust in scenarios involving camera failure and LiDAR obstruction. © 2024 ACM.

关键词： SLAM robotics

来源：评论

学校读者我要写书评

暂无评论

Feature Attention Complex-Valued-Based CNN for Ship Target Recognition of SAR Images 2

Feature Attention Complex-Valued-Based CNN for Ship Target R...

引用

2nd IEEE International Conference on Signal, information and Data processing, ICSIDP 2024

作者： Pan, Hongxin Yang, Chao Yin, Yifei Liang, Bin Shi, Hao Wu, Guanghui Beijing Institute of Technology Chongqing Innovation Center Chongqing China Shanghai Institute of Satellite Engineering Shanghai China Beijing Institute of Technology National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing China

ISBN: (纸本)9798331515669

The details regarding targets within Synthetic Aperture Radar (SAR) imagery are typically conveyed and maintained in complex-valued form. Namely, the information regarding both the amplitude and phase is essential. In the process of recognizing targets with SAR, the network only utilizes the amplitude image as input, while the phase information is neglected, resulting in poor recognition performance. This paper proposes a Feature Attention Complex-Valued-Based convolutional neural Network (FACV-Net) for SAR ship recognition to overcome these issues, which effectively utilizes phase information to improve target recognition. Firstly, to meet the requirements of network training in complex domains, a series of complex-valued operation blocks have been constructed. Moreover, a new complex-valued Attention Module (CAM) is introduced to ensure that the network focuses on the amplitude and phase characteristics of the target separately. Additionally, to address the mismatch problem between the amplitude and phase data, two distinct methods for complex-valued max-pooling are utilized. Ultimately, the performance of the proposed FACV-Net is assessed using the OpenSARship dataset, and the results indicate that this novel approach surpasses conventional networks in terms of recognition accuracy. When the CAM is added, the performance of the network sees a further enhancement of around 3% in accuracy. These findings confirm the proposed method's effectiveness and advantage over others. © 2024 IEEE.

关键词： Cams

来源：评论

学校读者我要写书评

暂无评论

Solo Adaptation for Distributed Synchronization With Application to Event-Triggered Linear Multi-Agent Systems

引用

IEEE Transactions on Automatic Control 2025年第6期70卷 4225-4232页

作者： Chen, Ci Zheng, Zhiyang Lewis, Frank L. Xie, Kan Xie, Shengli Guangdong University of Technology Guangdong Provincial Key Laboratory of Intelligent Systems and Optimization Integration Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education School of Automation Guangzhou510006 China Guangdong University of Technology School of Automation Guangdong Guangzhou510006 China The University of Texas at Arlington UTA Research Institute Fort Worth76118 United States Guangdong University of Technology 111 Center for Intelligent Batch Manufacturing Based on IoT Technology School of Automation Guangzhou China Guangdong University of Technology Key Laboratory of Intelligent Detection and The Internet of Things in Manufacturing Ministry of Education School of Automation Guangzhou510006 China

We study a solo adaptation-based protocol design problem for distributed synchronization of event-triggered linear multi-agent systems (MAS) over general directed graphs. We show that a solo adaptive gain, a locally static control gain matrix, and a distributed state measurement are sufficient for obtaining adaptive distributed synchronization of linear MAS over directed graphs without any prior knowledge of the global communication network. We then extend the solo adaptation structure to formulate an event-triggered synchronization control protocol. The main feature of our result is that the time for triggering a subsequent event is now computed using the distributed event-triggered state measurement, rather than the continuous-time state measurement. © 1963-2012 IEEE.

关键词： Continuous time systems

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：