检索结果-内蒙古大学图书馆

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

作者： Hu, Jiliang Li, Zuchao Wang, Ping Ai, Haojun Zhang, Lefei Zhao, Hai Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan China School of Computer Science Wuhan University Wuhan China School of Information Management Wuhan University Wuhan China Department of Computer Science and Engineering Shanghai Jiao Tong University China

ISBN: (纸本)9798891761643

The image-based multimodal automatic speech recognition (ASR) model enhances speech recognition performance by incorporating audio-related image. However, some works suggest that introducing image information to model does not help improving ASR performance. In this paper, we propose a novel approach effectively utilizing audio-related image information and set up VHASR, a multimodal speech recognition system that uses vision as hotwords to strengthen the model's speech recognition capability. Our system utilizes a dual-stream architecture, which firstly transcribes the text on the two streams separately, and then combines the outputs. We evaluate the proposed model on four datasets: Flickr8k, ADE20k, COCO, and OpenImages. The experimental results show that VHASR can effectively utilize key information in images to enhance the model's speech recognition ability. Its performance not only surpasses unimodal ASR, but also achieves SOTA among existing image-based multimodal ASR. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Embedding expert demonstrations into clustering buffer for effective deep reinforcement learning

引用

Frontiers of Information Technology & Electronic Engineering 2023年第11期24卷 1541-1556页

作者： Shihmin WANG Binqi ZHAO Zhengfeng ZHANG Junping ZHANG Jian PU Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China Institute of Science and Technology for Brain-inspired Intelligence Fudan UniversityShanghai 200433China

As one of the most fundamental topics in reinforcement learning(RL),sample efficiency is essential to the deployment of deep RL *** most existing exploration methods that sample an action from different types of posterior distributions,we focus on the policy sampling process and propose an efficient selective sampling approach to improve sample efficiency by modeling the internal hierarchy of the ***,we first employ clustering methods in the policy sampling process to generate an action candidate *** we introduce a clustering buffer for modeling the internal hierarchy,which consists of on-policy data,off-policy data,and expert data to evaluate actions from the clusters in the action candidate set in the exploration *** this way,our approach is able to take advantage of the supervision information in the expert demonstration *** on six different continuous locomotion environments demonstrate superior reinforcement learning performance and faster convergence of selective *** particular,on the LGSVL task,our method can reduce the number of convergence steps by 46.7%and the convergence time by 28.5%.Furthermore,our code is open-source for *** code is available at https://***/Shihwin/SelectiveSampling.

关键词： Reinforcement learning Sample eficiency Sampling process Clustering methods Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

Safety and Ethical Concerns of Large Language Models 22

Safety and Ethical Concerns of Large Language Models

引用

22nd Chinese National Conference on Computational Linguistics, CCL 2023

作者： Xi, Zhiheng Zheng, Rui Gui, Tao School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China Institute of Modern Languages and Linguistics Fudan University Shanghai China

ISBN: (纸本)9781713889915

Recent months have witnessed significant progress in the field of large language models (LLMs). Represented by ChatGPT and GPT-4, LLMs perform well in various natural language processing tasks and have been applied to many downstream applications to facilitate people’s lives. However, there still exist safety and ethical concerns. Specifically, LLMs suffer from social bias, robustness problems, and poisoning issues, all of which may induce LLMs to spew harmful contents. We propose this tutorial as a gentle introduction to the safety and ethical issues of LLMs. © 2023 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

Decentralized Multi-Authority Ciphertext-Policy Attribute-Based Encryption with Hidden Policy for Cloud data Sharing 4

Decentralized Multi-Authority Ciphertext-Policy Attribute-Ba...

引用

2023 4th International Conference on computer Engineering and Intelligent Control, ICCEIC 2023

作者： Xue, Lulu Li, Jiani Zhang, Kejia Yu, Tianqiu Heilongjiang University School of Mathematical Science Harbin China Shaanxi Normal University School of Computer Science Xian China Guizhou University State Key Laboratory of Public Big Data Guiyang China

ISBN: (纸本)9798350308877

Cloud storage services employ multi-authority attribute-based encryption (MA-ABE) with policy hiding extensively. However, in the existing MA-ABE schemes with policy hiding, all attributes are managed by a centralized authority (CA), which is also responsible for providing the user with the partial attribute keys needed for decryption. Thus, by calculating the required secret keys, CA may decrypt any ciphertext present in the cloud system. Moreover, it will increase the security risk of encrypted data in cloud. This paper proposes a decentralized multi-authority ciphertext-policy attribute-based encryption scheme that supports policy hiding. Participation in the proposed scheme does not require the centralized authority (CA), but rather numerous attribute authorities (AAS). Every AA manages several attribute sets and offers attribute keys for data users. In the encryption computation and key generation phase, we add an exponential operation to better protect the user's sensitive data. Our scheme outperforms the current schemes in terms of functionality, as demonstrated by the performance analysis. Furthermore, the standard model has demonstrated the full security of our scheme. © 2023 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based activity recognition and fine motor identification using 2D skeletons of cynomolgus monkeys

引用

Zoological Research 2023年第5期44卷 967-980页

作者： Chuxi Li Zifan Xiao Yerong Li Zhinan Chen Xun Ji Yiqun Liu Shufei Feng Zhen Zhang Kaiming Zhang Jianfeng Feng Trevor W.Robbins Shisheng Xiong Yongchang Chen Xiao Xiao School of Information Science and Technology Micro Nano System Center Fudan UniversityShanghai 200433China Department of Anesthesiology Huashan HospitalKey Laboratory of Computational Neuroscience and Brain-Inspired IntelligenceMinistry of EducationBehavioral and Cognitive Neuroscience CenterInstitute of Science and Technology for Brain-Inspired IntelligenceMOE Frontiers Center for Brain ScienceFudan UniversityShanghai 200433China Kuang Yaming Honors School Nanjing UniversityNanjingJiangsu 210023China Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China State Key Laboratory of Primate Biomedical Research Institute of Primate Translational MedicineKunming University of Science and TechnologyKunmingYunnan 650500China New Vision World LLC. Aliso ViejoCalifornia 92656USA Behavioural and Clinical Neuroscience Institute University of CambridgeCambridgeCB21TNUK

Video-based action recognition is becoming a vital tool in clinical research and neuroscientific study for disorder detection and ***,action recognition currently used in non-human primate(NHP)research relies heavily on intense manual labor and lacks standardized *** this work,we established two standard benchmark datasets of NHPs in the laboratory:Monkeyin Lab(Mi L),which includes 13 categories of actions and postures,and MiL2D,which includes sequences of two-dimensional(2D)skeleton ***,based on recent methodological advances in deep learning and skeleton visualization,we introduced the Monkey Monitor Kit(Mon Kit)toolbox for automatic action recognition,posture estimation,and identification of fine motor activity in *** the datasets and Mon Kit,we evaluated the daily behaviors of wild-type cynomolgus monkeys within their home cages and experimental environments and compared these observations with the behaviors exhibited by cynomolgus monkeys possessing mutations in the MECP2 gene as a disease model of Rett syndrome(RTT).Mon Kit was used to assess motor function,stereotyped behaviors,and depressive phenotypes,with the outcomes compared with human manual *** Kit established consistent criteria for identifying behavior in NHPs with high accuracy and efficiency,thus providing a novel and comprehensive tool for assessing phenotypic behavior in monkeys.

关键词： Action recognition Fine motor identification Two-stream deep model 2D skeleton Non-human primates Rett syndrome

来源：评论

学校读者我要写书评

暂无评论

AUTOSCRAPER: A Progressive Understanding Web Agent for Web Scraper Generation

arXiv

引用

arXiv 2024年

作者： Huang, Wenhao Gu, Zhouhong Peng, Chenghao Li, Zhixu Liang, Jiaqing Xiao, Yanghua Wen, Liqian Chen, Zulong Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China School of Data Science Fudan University China Alibaba Holding-Aicheng Technology-Enterprise China

Web scraping is a powerful technique that extracts data from websites, enabling automated data collection, enhancing data analysis capabilities, and minimizing manual data entry efforts. Existing methods, wrappers-based methods suffer from limited adaptability and scalability when faced with a new website, while language agents, empowered by large language models (LLMs), exhibit poor reusability in diverse web environments. In this work, we introduce the paradigm of generating web scrapers with LLMs and propose AUTOSCRAPER, a two-stage framework that can handle diverse and changing web environments more efficiently. AUTOSCRAPER leverages the hierarchical structure of HTML and similarity across different web pages for generating web scrapers. Besides, we propose a new executability metric for better measuring the performance of web scraper generation tasks. We conduct comprehensive experiments with multiple LLMs and demonstrate the effectiveness of our framework. Our work is now open-source.1 © 2024, CC BY.

关键词： Web crawler

来源：评论

学校读者我要写书评

暂无评论

Vision Mamba Mender 38

Vision Mamba Mender

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Hu, Jiacong Cao, Anda Feng, Zunlei Zhang, Shengxuming Wang, Yi Jia, Lingxiang Song, Mingli College of Computer Science and Technology Zhejiang University China School of Software Technology Zhejiang University China State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China

Mamba, a state-space model with selective mechanisms and hardware-aware architecture, has demonstrated outstanding performance in long sequence modeling tasks, particularly garnering widespread exploration and application in the field of computer vision. While existing works have mixed opinions of its application in visual tasks, the exploration of its internal workings and the optimization of its performance remain urgent and worthy research questions given its status as a novel model. Existing optimizations of the Mamba model, especially when applied in the visual domain, have primarily relied on predefined methods such as improving scanning mechanisms or integrating other architectures, often requiring strong priors and extensive trial and error. In contrast to these approaches, this paper proposes the Vision Mamba Mender, a systematic approach for understanding the workings of Mamba, identifying flaws within, and subsequently optimizing model performance. Specifically, we present methods for predictive correlation analysis of Mamba's hidden states from both internal and external perspectives, along with corresponding definitions of correlation scores, aimed at understanding the workings of Mamba in visual recognition tasks and identifying flaws therein. Additionally, tailored repair methods are proposed for identified external and internal state flaws to eliminate them and optimize model performance. Extensive experiments validate the efficacy of the proposed methods on prevalent Mamba architectures, significantly enhancing Mamba's performance. For more information, please visit https://***/. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models

arXiv

引用

arXiv 2024年

作者： He, Qianyu Zeng, Jie He, Qianxi Liang, Jiaqing Xiao, Yanghua Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China School of Data Science Fudan University China Fudan-Aishu Cognitive Intelligence Joint Research Center Shanghai China

It is imperative for Large language models (LLMs) to follow instructions with elaborate requirements (i.e. Complex Instructions Following). Yet, it remains under-explored how to enhance the ability of LLMs to follow complex instructions with multiple constraints. To bridge the gap, we initially study what training data is effective in enhancing complex constraints following abilities. We found that training LLMs with instructions containing multiple constraints enhances their understanding of complex instructions, especially those with lower complexity levels. Additionally, we further propose methods addressing how to obtain and utilize the effective training data. Finally, we conduct extensive experiments to prove the effectiveness of our methods in terms of overall performance and training efficiency. We also demonstrate that our methods improve models’ ability to follow instructions generally and generalize effectively across out-of-domain, in-domain, and adversarial settings, while maintaining general capabilities. The datasets and code are publicly available at https://***/meowpass/ FollowComplexInstruction. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

An inverse design method for supercritical airfoil based on conditional generative models

引用

Chinese Journal of Aeronautics 2022年第3期35卷 62-74页

作者： Jing WANG Runze LI Cheng HE Haixin CHEN Ran CHENG Chen ZHAI Miao ZHANG Shanghai Aircraft Design and Research Institute Shanghai 200436China School of Aerospace Engineering Tsinghua UniversityBeijing 100084China Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China

Inverse design has long been an efficient and powerful design tool in the aircraft *** this paper,a novel inverse design method for supercritical airfoils is proposed based on generative models in deep learning.A Conditional Variational Auto Encoder(CVAE)and an integrated generative network CVAE-GAN that combines the CVAE with the Wasserstein Generative Adversarial Networks(WGAN),are conducted as generative *** are used to generate target wall Mach distributions for the inverse design that matches specified features,such as locations of suction peak,shock and aft *** and quantitative results show that both adopted generative models can generate diverse and realistic wall Mach number distributions satisfying the given *** CVAE-GAN model outperforms the CVAE model and achieves better reconstruction accuracies for all the samples in the ***,a deep neural network for nonlinear mapping is adopted to obtain the airfoil shape corresponding to the target wall Mach number *** performances of the designed deep neural network are fully demonstrated and a smoothness measurement is proposed to quantify small oscillations in the airfoil surface,proving the authenticity and accuracy of the generated airfoil shapes.

关键词： Conditional Variational AutoEncoder(CVAE) Deep learning Generative Adversarial Networks(GAN) Generative models Inverse design Supercritical airfoil

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal Semantic Feature Interaction Network for Semantic Change Detection in Remote Sensing Images

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 12090-12102页

作者： Zhang, Yuhang Zhang, Wuxia Ding, Songtao Wu, Siyuan Lu, Xiaoqiang Xi'an University of Posts and Telecommunications Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing School of Computer Science and Technology Xi'an710121 China Xi'an University of Technology College of Computer Science and Engineering Shaanxi Xi'an710048 China Fuzhou University College of Physics and Information Engineering Fuzhou350002 China

Semantic Change Detection (SCD) in Remote Sensing Images (RSI) aims to identify changes in the type of Land Cover/Land Use (LCLU). The "from-to" information of the acquired image has more profound practical significance than Binary Change Detection (BCD). However, most deep learning-based SCD algorithms do not fully exploit the spatial-temporal information of multilevel features, leading to challenges in extracting LCLU features in complex scenes. To address these issues, we propose a Spatial-Temporal Semantic Feature Interaction Network (STS-FINet) to improve the performance of SCD in RSI. The proposed STS-FINet comprises a Multi-Scale Feature Extraction Encoder (MS-FEE), a Transformer-based Multilevel Feature Interaction module (TML-FI), and a Multilevel Feature Fusion Decoder (ML-FFD). The MS-FEE extracts deep semantic and differential information from the RSI. The TML-FI is designed to mine the spatial-temporal information by extracting long-range dependencies and spatial information from multilevel features to improve spatial perception. Moreover, Mixed Spatial Reasoning Convolution block (MixSrc) is presented to enrich the spatial information by extracting the multiscale features, thus improving the model's capability to interpret complex scenes. Finally, ML-FFD integrates the multilevel features, resulting in the generation of the semantic change map. The effectiveness of the proposed STS-FINet is verified on two high-resolution RSI datasets. Experimental results show that the proposed STS-FINet achieves better change detection performance than SOTA methods. © 2008-2012 IEEE.

关键词： Change detection

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：