检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2828-2839页

作者： Cheng, Jian Long, Kaifang Zhang, Shuang Zhang, Tian Ma, Lianbo Cheng, Shi Guo, Yinan State Key Laboratory for Intelligent Coal Mining and Strata Control Research Institute of Mine Big Data Chinese Institute of Coal Science Beijing100013 China Northeastern University College of Software Shenyang110819 China Shaanxi Normal University College of Computer Science Xi'an710062 China China University of Mining and Technology Xuzhou221116 China

With the popularity and widespread use of social media platforms, such as Twitter and Facebook, massive amounts of text and image information posted by a variety of users have flooded these social media platforms. Thus, multimodal named entity recognition (MNER) has become a research hotspot for the task of extracting named entities from multimodal data. Empirically, the visual clues unrelated to text data may introduce uncertain or even negative impacts on the named entity recognition. The considerations of the relevance of multimodal data have been ignored in the previous studies. In this article, to effectively measure the relationship between text data and visual cues for improving the accuracy of named entities, we propose a text-image scene graph fusion (TISGF) approach with a text-image similarity assessment module (TISA) and a text-image fusion module (TIF) for MNER. Specifically, we first construct two (visual and textual) scene graphs to exploit the joint features of objects and relations in text and image and encode the two scene graphs separately using a specific encoder pair. In this way, we can obtain both object-level and relationship-level cross-modal features. Subsequently, TISA is used to compute the similarity of the image and text data and to determine the proportion of visual information that will be retained for fusion. Finally, we use TIF to achieve a unified multimodal representation of each word and predict the entity type using conditional random fields. Extensive experiment results on two public datasets demonstrate the effectiveness and competitiveness of our proposed method for the MNER task. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Improved key-Recovery Attacks Under Imperfect SCA Oracle for Lattice-Based KEMs 17th

Improved Key-Recovery Attacks Under Imperfect SCA Oracle for...

引用

17th International Conference on Provable and Practical Security, ProvSec 2023

作者： Shi, Wenhao Han, Jiang Jiang, Haodong Ma, Zhi Henan Key Laboratory of Network Cryptography Technology Zhengzhou China TCA of State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783031455124

Plaintext-checking (PC) oracle-based side-channel-attacks (SCAs) is a major class of key recovery chosen-ciphertext SCAs on lattice-based key encapsulation mechanisms (KEMs). In practice, the PC oracle derived in SCAs is usually imperfect. In this paper, we propose an improved SCA for lattice-based KEMs with lower sample complexity (i.e. the required number of traces) when the PC oracle is imperfect. The basic idea of our method is to roughly recover the secret key and detect the erroneous position in the secret key, later correct the problematic entries with various known attacks for LWE (e.g., primal attack). We experimentally verified our method on Kyber512, and the reduction of sample complexity is significant. For example, it can reduce the sample complexity by 54.06 % when the accuracy is 0.890, for higher accuracy 0.950, the reduction of sample complexity is 35.81 %. We also estimate the concrete security of Kyber512 after the side-channel-attack for different accuracy levels, including the primal attack, dual attack, decoding approach and the hybrid attack. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Side channel attack

来源：评论

学校读者我要写书评

暂无评论

The Embedding Path Order for Lambda-Free Higher-Order Terms

Journal of Applied Logics

引用

Journal of Applied Logics 2021年第10期8卷 2447-2470页

作者： Bentkamp, Alexander Vrije Universiteit Amsterdam Netherlands State Key Lab. of Computer Science Institute of Software CAS Beijing China

The embedding path order, introduced in this article, is a variant of the recursive path order (RPO) for untyped λ-free higher-order terms (also called applicative first-order terms). Unlike other higher-order variants of RPO, it is a ground-total and well-founded simplification order, making it more suitable for the superposition calculus. I formally proved the order’s theoretical properties in Isabelle/HOL and evaluated the order in a prototype based on the superposition prover Zipperposition. © 2021, College Publications. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Safety guarantee for time-delay systems with disturbances

引用

science China(Information sciences) 2023年第3期66卷 118-132页

作者： Wenyou LIU Yunjun BAI Li JIAO Naijun ZHAN State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences

Time delays occur in various engineering applications because they may be inherent in the plants or caused by networks. In this paper, we investigate the safety verification problem of time-delay systems modeled by nonlinear delay differential equations subject to control inputs and disturbances in their dynamics. Building upon classical control barrier functionals, we develop the notions of input-to-state safety and input-to-state safe control barrier functionals, in which input-to-state safe control barrier functionals are used to guarantee the safety of time-delay systems with control inputs and disturbances. Three examples are provided to demonstrate the proposed approach.

关键词： time-delay systems delay differential equations control barrier functionals controllers safety

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of Compression, Transmission and Computation for Cooperative Perception Aided Intelligent Vehicular Networks

引用

IEEE Transactions on Vehicular Technology 2025年第5期74卷 8201-8214页

作者： Lu, Binbin Huang, Xumin Wu, Yuan Qian, Liping Zhou, Sheng Niyato, Dusit University of Macau State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science 999078 China Guangdong University of Technology School of Automation Guangzhou510006 China University of Macau State Key Lab of Internet of Things for Smart City 999078 China University of Macau State Key Laboratory of Internet of Things for Smart City Department of Computer Information Science 999078 China Zhuhai UM Science and Technology AQ2 Research Institute Zhuhai519301 China Zhejiang University of Technology Institute of Cyberspace Security Hangzhou310023 China Tsinghua University Beijing National Research Center for Information Science and Technology Department of Electronic Engineering Beijing100084 China Nanyang Technological University School of Computer Science and Engineering 639815 Singapore

Cooperative perception is a promising paradigm to tackle the perception limitations of a single intelligent vehicle (IV) to enhance the driving safety and efficiency in intelligent vehicular networks. However, the real-time transmission and computation-intensive fusion of raw sensing data raise new challenges for satisfying the stringent delay requirement of delay-sensitive applications. In this paper, we formulate a joint optimization problem of the cooperative IV selection, compression ratio selection, transmit power control, task offloading decision and computation allocation to minimize the end-to-end delay consisting of compression, transmission and computation. In particular, to meet the perception probability requirement, the quality and quantity-aware matching algorithm is proposed to optimize the cooperative IV selection. To guarantee the queue stability of offloading tasks, we develop the Lyapunov optimization algorithm to determine the upper bound of the offloading tasks and the corresponding optimal computation allocation. The Lyapunov aided deep reinforcement learning algorithm is further proposed to dynamically adjust the task offloading decision and compression ratio selection to minimize the end-to-end delay with the transmit power control being optimized by the successive convex approximation algorithm. Simulation results demonstrate that, compared to several benchmark algorithms, our proposed algorithm achieves the lowest end-to-end delay while guaranteeing the requirements on perception probability and queue stability effectively. © 1967-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

SACM: spatial attributes of complex movements in multi-object tracking

引用

Multimedia Tools and Applications 2025年 1-20页

作者： Li, Hongjun Li, Jiaxin Sun, Xiaohu School of Information Science and Technology Nantong University Jiangsu Nantong226019 China State Key Lab. for Novel Software Technology Nanjing University Jiangsu Nantong210023 China Nantong Research Institute for Advanced Communication Technologies Jiangsu Nantong226019 China

Multi-object tracking is a crucial task in computer vision, but it faces significant challenges due to complex scenes and interactions between tracked objects. To address these challenges, we propose a complex movement-based spatial attribute tracking model (SACM). First, to enhance target detection, the model extracts both global and local features from the input feature maps to capture detailed spatial location information between different targets. Second, to strengthen the positional association of the same target across consecutive frames, position information from the previous frame is incorporated into the current frame, improving occlusion handling. Finally, a new target matching method is developed within the tracker, leveraging spatial relationships among targets to achieve precise matching of overlapping objects. Experimental results show that, compared to FairMOT, SACM achieves a 3.7% improvement in HOTA and a 4.8% improvement in IDF1 on the DanceTrack dataset. On the MOT17 dataset, SACM also improves HOTA by 3.7% and IDF1 by 4.8%. Furthermore, SACM achieves a processing speed of 30.5 FPS on a single GPU, resulting in improved tracking performance. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Towards More Efficient Local Search for Pseudo-Boolean Optimization 29

Towards More Efficient Local Search for Pseudo-Boolean Optim...

引用

29th International Conference on Principles and Practice of Constraint Programming, CP 2023

作者： Chu, Yi Cai, Shaowei Luo, Chuan Lei, Zhendong Peng, Cong Institute of Software Chinese Academy of Sciences Beijing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China School of Software Beihang University Beijing China Finovation in CCBFT Beijing China

ISBN: (纸本)9783959773003

Pseudo-Boolean (PB) constraints are highly expressive, and many combinatorial optimization problems can be modeled using pseudo-Boolean optimization (PBO). It is recognized that stochastic local search (SLS) is a powerful paradigm for solving combinatorial optimization problems, but the development of SLS for solving PBO is still in its infancy. In this paper, we develop an effective SLS algorithm for solving PBO, dubbed NuPBO, which introduces a novel scoring function for PB constraints and a new weighting scheme. We conduct experiments on a broad range of six public benchmarks, including three real-world benchmarks, a benchmark from PB competition, an integer linear programming optimization benchmark, and a crafted combinatorial benchmark, to compare NuPBO against five state-of-the-art competitors, including a recently-proposed SLS PBO solver LS-PBO, two complete PB solvers PBO-IHS and RoundingSat, and two mixed integer programming (MIP) solvers Gurobi and SCIP. NuPBO has been exhibited to perform best on these three real-world benchmarks. On the other three benchmarks, NuPBO shows competitive performance compared to state-of-the-art competitors, and it significantly outperforms LS-PBO, indicating that NuPBO greatly advances the state of the art in SLS for solving PBO. © Yi Chu, Shaowei Cai, Chuan Luo, Zhendong Lei, and Cong Peng.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Humanizing Machine-Generated Content: Evading AI-Text Detection through Adversarial Attack 30

Humanizing Machine-Generated Content: Evading AI-Text Detect...

引用

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

作者： Zhou, Ying He, Ben Sun, Le University of Chinese Academy of Sciences Beijing China Chinese Information Processing Laboratory China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China

ISBN: (纸本)9782493814104

With the development of large language models (LLMs), detecting whether text is generated by a machine becomes increasingly challenging in the face of malicious use cases like the spread of false information, protection of intellectual property, and prevention of academic plagiarism. While well-trained text detectors have demonstrated promising performance on unseen test data, recent research suggests that these detectors have vulnerabilities when dealing with adversarial attacks such as paraphrasing. In this paper, we propose a framework for a broader class of adversarial attacks, designed to perform minor perturbations in machine-generated content to evade detection. We consider two attack settings: white-box and black-box, and employ adversarial learning in dynamic scenarios to assess the potential enhancement of the current detection model's robustness against such attacks. The empirical results reveal that the current detection models can be compromised in as little as 10 seconds, leading to the misclassification of machine-generated text as human-written content. Furthermore, we explore the prospect of improving the model's robustness over iterative adversarial learning. Although some improvements in model robustness are observed, practical applications still face significant challenges. These findings shed light on the future development of AI-text detectors, emphasizing the need for more accurate and robust detection methods. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

DLUE: Benchmarking Document Language Understanding 23

引用

23rd Chinese National Conference on Computational Linguistics, CCL 2024

作者： Xu, Ruoxi Lin, Hongyu Guan, Xinyan Sun, Yingfei Sun, Le University of Chinese Academy of Sciences Beijing China Chinese Information Processing Laboratory China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China

ISBN: (纸本)9780000000002

Understanding documents is central to many real-world tasks but remains a challenging topic. Unfortunately, there is no well-established consensus on how to comprehensively evaluate document understanding abilities, which significantly hinders the fair comparison and measuring the progress of the field. To benchmark document understanding researches, this paper summarizes four representative abilities, i.e., document classification, document structural analysis, document information extraction, and document transcription. Under the new evaluation framework, we propose Document Language Understanding Evaluation - DLUE, a new task suite which covers a wide-range of tasks in various forms, domains and document genres. We also systematically evaluate six well-established transformer models and representative LLMs on DLUE, and find that due to the lengthy content, complicated underlying structure and dispersed knowledge, document understanding is still far from being solved in complex real-world scenarios. © 2024 China National Conference on Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

KnowLA: Enhancing Parameter-efficient Finetuning with Knowledgeable Adaptation

KnowLA: Enhancing Parameter-efficient Finetuning with Knowle...

引用

2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024

作者： Luo, Xindi Sun, Zequn Zhao, Jing Zhao, Zhe Hu, Wei State Key Laboratory for Novel Software Technology Nanjing University China National Institute of Healthcare Data Science Nanjing University China Tencent AI Lab China

ISBN: (纸本)9798891761148

Parameter-efficient finetuning (PEFT) is a key technique for adapting large language models (LLMs) to downstream tasks. In this paper, we study leveraging knowledge graph embeddings to improve the effectiveness of PEFT. We propose a knowledgeable adaptation method called KnowLA. It inserts an adaptation layer into an LLM to integrate the embeddings of entities appearing in the input text. The adaptation layer is trained in combination with LoRA on instruction data. Experiments on six benchmarks with two popular LLMs and three knowledge graphs demonstrate the effectiveness and robustness of KnowLA. We show that KnowLA can help activate the relevant parameterized knowledge in an LLM to answer a question without changing its parameters or input prompts. © 2024 Association for Computational Linguistics.

关键词： Knowledge graph

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：