检索结果-内蒙古大学图书馆

Embedding expert demonstrations into clustering buffer for effective deep reinforcement learning

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

Replace Anyone in Videos

arXiv

引用

arXiv 2024年

作者： Wang, Xiang Gao, Changxin Wang, Yuehuan Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China

Recent advancements in controllable human-centric video generation, particularly with the rise of diffusion models, have demonstrated considerable progress. However, achieving precise and localized control over human motion, e.g., replacing or inserting individuals into videos while exhibiting desired motion patterns, still remains challenging. In this work, we propose the ReplaceAnyone framework, which focuses on localizing and manipulating human motion in videos with diverse and intricate backgrounds. Specifically, we formulate this task as an image-conditioned pose-driven video inpainting paradigm, employing a unified video diffusion architecture that facilitates image-conditioned pose-driven video generation and inpainting within masked video regions. Moreover, we introduce diverse mask forms involving regular and irregular shapes to avoid shape leakage and allow granular local control. Additionally, we implement a two-stage training methodology, initially training an image-conditioned pose-driven video generation model, followed by joint training of the video inpainting within masked areas. In this way, our approach enables seamless replacement or insertion of characters while maintaining the desired pose motion and reference appearance within a single framework. Experimental results demonstrate the effectiveness of our method in generating realistic and coherent video content. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic Maximum Relevance and Modal Alignment for Cross-Modal Retrieval 11

Semantic Maximum Relevance and Modal Alignment for Cross-Mod...

引用

11th International Conference on Computing and Pattern Recognition, ICCPR 2022

作者： Sun, Pingping Qiang, Baohua Liu, Zhiguang Yang, Xianyi Xi, Guangyong Liu, Weigang Chen, Ruidong Zhang, Shihao Guilin University of Electronic Technology China The 54th Research Institute of Cetc Hebei Key Laboratory of Intelligent Information Perception and Processing China

ISBN: (纸本)9781450397056

With the increasing abundance of multimedia data resources, researches on mining the relationship between different modalities to achieve refined cross-modal retrieval are gradually emerging. In this paper, we propose a novel Semantic Maximum Relevance and Modal Alignment (SMR-MA) for Cross-Modal Retrieval, which utilizes the pre-trained model with abundant image text information to extract the features of each image text, and further promotes the modal information interaction between the same semantic categories through the modal alignment module and the multi-layer perceptron with shared weights. In addition, multi-modal embedding is distributed to the normalized hypersphere, and angular edge penalty is applied between feature embedding and weight in angular space to maximize the classification boundary, thus increasing both intra-class similarity and inter-class difference. Comprehensive analysis experiments on three benchmark datasets demonstrate that the proposed method has superior performance in cross-modal retrieval tasks and is significantly superior to the state-of-the-art cross-modal retrieval methods. © 2022 ACM.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Age estimation of Caenorhabditis elegans with label distribution learning

Age estimation of Caenorhabditis elegans with label distribu...

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Zhao, Zi-Kang Liu, Jun Wang, Jun-Ji Chen, Gong Li, Chen-Qian Zhao, Zihao Jiang, Min Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Caenorhabditis elegans (C. elegans) is widely used in life research as a model organism. Accurate measurement of its age has practical implications for follow-up research. However, due to the similar characteristics of nematodes in different age groups, the general method is difficult to estimate accurately. Aiming at this problem, this paper proposes a method of label distribution learning, and uses fluorescence microscopy images to estimate the age of C. elegans. First, the logical age label are mapped to the label distribution. Secondly, the distribution learning loss function is used to make the neural network learn the relationship between the label distribution and corresponding image. Finally, the distribution learning loss function and the classification loss function are combined to strengthen the learning of the neural network. Experiments show that the accuracy and mean absolute error (MAE) of the method in this paper are improved compared with the baseline. In the experiment of estimating the age on different parts' data set, it was also concluded that the fluorescent image of the torso of C. elegans can better reflect the age characteristics than the head and tail. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An English Pronunciation Quality Evaluation Model Based on Multi-dimensional Features 2

An English Pronunciation Quality Evaluation Model Based on M...

引用

2021 2nd International Symposium on Automation, Information and Computing, ISAIC 2021

作者： Li, Yiqun Huang, Guimin Guangxi Key Laboratory of Image and Graphic Intelligent Processing School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China

As a universal language, English has been paid more and more attention, among which oral English learning is very important. In this paper, the two key technologies of pronunciation error detection and quality evaluation are studied, both of them are effectively integrated, aiming to build a model for L2 learners' English pronunciation quality evaluation. This paper mainly studies two different methods of pronunciation error detection. Based on the speech recognition framework, the standard score is compared with the threshold to judge the correctness of phoneme pronunciation, and the phoneme-dependent threshold is set to improve the maximum Precision to 0.44. By judging the correct pronunciation and confusing phoneme, the accuracy of pronunciation error detection is improved to 81.26%. This paper proposes the fusion algorithm from multi-dimensions of speech fluency and intonation respectively, and a newly designed feature called word duration ratio, which significantly improve the correlation of pronunciation quality evaluation to 0.746. © Published under licence by IOP Publishing Ltd.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Extended NNs-Based Adaptive Event-Triggered Asymptotic Control for Nonlinear Systems Against Actuator Faults 7

Extended NNs-Based Adaptive Event-Triggered Asymptotic Contr...

引用

7th International Symposium on Autonomous Systems, ISAS 2024

作者： Liu, Shanlin Zhang, Yingwei Zhao, Xudong Wang, Hesheng Northeastern University College of Information Science and Engineering Shenyang China Northeastern University State Laboratory of Synthesis Automation of Process Industry Shenyang China Dalian University of Technology Faculty of Electronic Information and Electrical Engineering Dalian China Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798350363173

In this article, an adaptive event-triggered asymp¬totically fault-tolerant control (FTC) issue for nonlinear systems with actuator faults is investigated. An extended neural networks (NNs) technique is introduced to estimate unknown functions of the system under consideration. Compared with traditional NNs that ignore approximation errors, the proposed extended NNs further processes approximation errors, reducing the conservatism of the proposed algorithm. Then, within the framework of backstepping method, a new adaptive control strategy is developed by combining event-triggered mechanism (ETM) and bound estimation (BE) approach, which ensures the asymptotic convergence of system states while also reducing the transmission of unnecessary information, thus improving the utilization of communication resources. At the same time, the designed controller eliminates the adverse effects of actuator failures and system nonlinear terms. Finally, a simulation example of a single-link robot system is provided to demonstrate that the developed control strategy can ensure that all signals are bounded and system states are asymptotically convergent. © 2024 IEEE.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Scalable and Fast Electrophoresis-Accelerated Assembly of Chiroptical Carbon Fibers With Multi Functions

SSRN

引用

SSRN 2025年

作者： Jiao, Haixing Song, Baiqi Li, Fa Tang, Yuanhan Zhang, Na Zhang, Xiaofang Xu, Weilin State Key Laboratory of New Textile Materials and Advanced Processing Wuhan Textile University Wuhan430200 China School of Transportation Science and Engineering Harbin Institute of Technology Harbin150090 China

Colorful carbon fibers (CFs) with combinations of structural robustness, environmental stability, and advanced functions are very promising in the cutting-edge fields. However, the efficient coloration simultaneously with the functionalization for CFs in a fast, scalable, and sustainable manner remains a grand challenge. In this work, we develop large-area chiroptical CFs with long-ranged chirality decoration via the electrophoresis-accelerated self-assembly of renewable cellulose nanocrystals (CNCs).That leads a cholesteric photonic "cast" conformally and tightly coated on CFs surface in a seamlessly tessellated way to bring chiroptical functionalities and mechanical adaption. The resulting chiroptical CFs not only comprise strong optical properties with controllable and brilliant colors, but also demonstrate impressive opt-mechanical combination against external mechanical forces, hydration effect, and extreme environments. More importantly, chiroptical CFs with customized patterns on the surface can be used as programmable infrared display for encryption and anti-counterfeiting. Those exciting findings extend the potentials of CF materials towards optical encryption, wearable device display, defense, and aerospace special applications. © 2025, The Authors. All rights reserved.

关键词： Cellulose nanocrystals

来源：评论

学校读者我要写书评

暂无评论

Chinese image captioning via double decoding based on visual prompts 5

Chinese image captioning via double decoding based on visual...

引用

5th International Conference on Computer Vision and Data Mining, ICCVDM 2024

作者： Tan, Weiguo Xiao, Yannan Wen, Yayuan Deng, Zhenrong Huang, Wenming School of Computer Science and Information Security Guilin University of Electronic Technology Guangxi Guilin541004 China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guangxi Guilin China College of Electronic Engineering Guangxi Normal University Guangxi Guilin China

ISBN: (纸本)9781510682863

The significant progress of vision-language pre-trained models (VLMs) and large language models (LLMs) have provided a feasible new mode for image captioning, which relies on VLMs to process images and then utilizes LLMs to generate captions, simplifying the caption generation process and making it lighter. Based on this mode, to address the issues of deviation between the generated captions and the content of image expressions, incomplete descriptive information, and resource hungry in previous Chinese image captioning models, we propose a Chinese image captioning model via double decoding based on Visual Prompts, DDVP. This model employs the CLIP model as the encoder, the GPT2 model as the decoder, and introduces Visual Prompts, which are keywords related to image content. The model adopts a double decoding approach, first decoding to generate Visual Prompts and then decoding to generate the final captions based on the Visual Prompts. Through evaluation, we have demonstrated that our model achieves competitive results on the AIC-ICC dataset, and while maintaining fluency, the generated captions of DDVP can also cover the information in the image more comprehensively and accurately. © 2024 SPIE.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

CAMG: Context-Aware Moment Graph Network for Multimodal Temporal Activity Localization via Language 12th

CAMG: Context-Aware Moment Graph Network for Multimodal Tem...

引用

12th National CCF Conference on Natural Language processing and Chinese Computing, NLPCC 2023

作者： Hu, Yuelin Xu, Yuanwu Zhang, Yuejie Feng, Rui Zhang, Tao Lu, Xuequan Gao, Shang School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University Shanghai200433 China School of Information Management and Engineering Shanghai Key Laboratory of Financial Information Technology Shanghai University of Finance and Economics Shanghai200433 China School of Information Technology Deakin University Waurn PondsVIC3216 Australia

ISBN: (纸本)9783031446924

Temporal Activity Localization via Language (TALL) is a challenging task for language based video understanding, especially when a video contains multiple moments of interest and the language query has words describing complex context dependencies between the moments. Latest studies have proposed various ways to exploit the temporal context of adjacent moments, but two apparent limitations remained. First, only limited context information was encoded based on RNNs or 2-D convolutions, which highly depended on the pre-sorting of proposals and lacked flexibility. Second, semantically correlated content in different moments was ignored, i.e., semantic context. To address these limitations, we propose a novel GCN-based framework, i.e., Context-Aware Moment Graph (CAMG) network, to jointly model the temporal context and semantic context. Also, we design a multi-step fusion scheme to aggregate object, motion and textual features. A Query-Gated Integration Module is further designed to select queried objects and filter out noisy ones. Our model achieves superior performance to state-of-the-art methods on two widely-used benchmark datasets. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

DisGNet: A Distance Graph Neural Network for Forward Kinematics Learning of Gough-Stewart Platform

arXiv

引用

arXiv 2024年

作者： Zhu, Huizhi Xu, Wenxia Huang, Jian The Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan430205 China Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

In this paper, we propose a graph neural network, DisGNet, for learning the graph distance matrix to address the forward kinematics problem of the Gough-Stewart platform. DisGNet employs the k-FWL algorithm for message-passing, providing high expressiveness with a small parameter count, making it suitable for practical deployment. Additionally, we introduce the GPU-friendly Newton-Raphson method, an efficient parallelized optimization method executed on the GPU to refine DisGNet’s output poses, achieving ultra-high-precision pose. This novel two-stage approach delivers ultra-high precision output while meeting real-time requirements. Our results indicate that on our dataset, DisGNet can achieves error accuracys below 1mm and 1deg at 79.8% and 98.2%, respectively. As executed on a GPU, our two-stage method can ensure the requirement for real-time computation. Codes are released at https://***/FLAMEZZ5201/DisGNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Newton-Raphson method

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：