检索结果-内蒙古大学图书馆

23rd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2024

作者： Chen, Zixuan Ji, Ze Liu, Shuyang Huo, Jing Chen, Yiyu Gao, Yang State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Cardiff University Cardiff United Kingdom

Enabling robots to effectively learn and imitate expert skills in long-horizon tasks remains challenging. Hierarchical imitation learning (HIL) approaches have made strides but often fall short in complex scenarios due to their reliance on self-exploration. This paper introduces a novel approach inspired by the human skill acquisition process, proposing a Cognition-Action-based Robotic Skill Imitation Learning (CasIL) framework. CasIL integrates human cognitive priors for task decomposition into a dual-layer architecture, enhancing robots' ability to cognize and imitate essential skills from expert demonstrations. Our experiments across four RLbench tasks demonstrate CasIL's superior performance, robustness, and generalizability in skill imitation compared to related methods. © 2024 International Foundation for Autonomous Agents and Multiagent Systems.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Exploration via Temporal Inconsistency in Reinforcement Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5530-5539页

作者： Gao, Zijian Xu, Kele Zhai, Yuanzhao Ding, Bo Feng, Dawei Mao, Xinjun Wang, Huaimin National University of Defense Technology School of Computer Changsha410000 China State Key Laboratory of Complex and Critical Software Environment Beijing100191 China

In sparse extrinsic reward settings, reinforcement learning remains a challenge despite increasing interest in this field. Existing approaches suggest that intrinsic rewards can alleviate issues caused by reward sparsity. However, many studies overlook the critical role of temporal information, essential for human curiosity. This article introduces a novel intrinsic reward mechanism inspired by human learning processes, where curiosity is evaluated by comparing current observations with historical knowledge. Our method involves training a self-supervised prediction model, periodically saving snapshots of the model parameters, and employing the nuclear norm to assess the temporal inconsistency between predictions from different snapshots as intrinsic rewards. Additionally, we propose a variational weighting mechanism to adaptively assign weights to the snapshots, enhancing the model's robustness and performance. Experimental results across various benchmark environments demonstrate the efficacy of our approach, which outperforms other state-of-the-art methods without incurring additional training costs and exhibits higher noise tolerance. Our findings indicate that leveraging temporal information in intrinsic rewards can significantly improve exploration performance, motivating future research to develop more robust and accurate reward systems for reinforcement learning. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Improved Lower Bounds for Approximating Parameterized Nearest Codeword and Related Problems Under ETH 51

Improved Lower Bounds for Approximating Parameterized Neares...

引用

51st International Colloquium on Automata, Languages, and Programming, ICALP 2024

作者： Li, Shuangle Lin, Bingkai Liu, Yuwei State Key Laboratory for Novel Software Technology Nanjing University China BASICS Shanghai Jiao Tong University China

ISBN: (纸本)9783959773225

In this paper we present a new gap-creating randomized self-reduction for the parameterized Maximum Likelihood Decoding problem over Fp (k-MLDp). The reduction takes a k-MLDp instance with k · n d-dimensional vectors as input, runs in O(d2O(k)n1.01) time for some computable function f, outputs a (3/2 − Ε)-Gap-k′-MLDp instance for any Ε > 0, where k′ = O(k2 log k). Using this reduction, we show that assuming the randomized Exponential Time Hypothesis (ETH), no algorithms can approximate k-MLDp (and therefore its dual problem k-NCPp) within factor (3/2−Ε) in f(k) · no(√k/ log k) time for any Ε > 0. We then use reduction by Bhattacharyya, Ghoshal, Karthik and Manurangsi (ICALP 2018) to amplify the (3/2 − Ε)-gap to any constant. As a result, we show that assuming ETH, no algorithms can approximate k-NCPp and k-MDPp within γ-factor in f(k) · no(kΕγ ) time for some constant Εγ > 0. Combining with the gap-preserving reduction by Bennett, Cheraghchi, Guruswami and Ribeiro (STOC 2023), we also obtain similar lower bounds for k-MDPp, k-CVPp and k-SVPp. These results improve upon the previous f(k) · nΩ(poly log k) lower bounds for these problems under ETH using reductions by Bhattacharyya et al. (*** 2021) and Bennett et al. (STOC 2023). © Shuangle Li, Bingkai Lin, and Yuwei Liu.

关键词： Parameterization

来源：评论

学校读者我要写书评

暂无评论

MoiréVib: Micron-level Vibration Detection based on Moiré Pattern 24

MoiréVib: Micron-level Vibration Detection based on Moiré ...

引用

30th International Conference on Mobile Computing and Networking, ACM MobiCom 2024

作者： Ning, Jingyi Yan, Zhihao Wu, Zhaowei Xie, Lei Wang, Chuyu Chen, Yingying Ye, Baoliu Lu, Sanglu State Key Laboratory for Novel Software Technology Nanjing University China Wireless Information Network Laboratory Rutgers University United States

ISBN: (纸本)9798400704895

Detection and assessment of micro vibrations are crucial tasks in both industrial settings and daily life. However, vibration sensors attached to the target vibrator may introduce potential resonance, and wireless detection methods suffer from severe multipath interference. Fortunately, moiré-based sensing methods have gained recognition in recent years due to their ability to perceive micro motion changes. In this paper, we propose MoiréVib, a micro-vibration detection solution based on moiré patterns for dynamic and high-frequency environments. We attach a printed marker with periodic gratings to the surface of vibration devices to generate moiré patterns, which can amplify micro vibrations due to their low-frequency magnification effect. However, moiré pattern's changes caused by micro vibrations are often overwhelmed by random pixel-level noises, and the limited frame rate of the camera fails to capture high-frequency moiré features. To deal with these problems, we propose a spectrum-based method to refine and enhance the dynamic and micro moiré features. Additionally, we propose a dual-frame-rate-based fusion mechanism to realize high-frequency reconstruction of moiré features. Extensive experimental results show that MoiréVib can realize a median amplitude detection error of 4.37 μm and achieve frequency detection up to 300Hz with a frame rate range of 10∼30 fps. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Vibration analysis

来源：评论

学校读者我要写书评

暂无评论

Crowdsourcing aggregation with deep Bayesian learning

引用

science China(Information sciences) 2021年第3期64卷 46-56页

作者： Shao-Yuan LI Sheng-Jun HUANG Songcan CHEN College of Computer Science and Technology College of Artificial IntelligenceNanjing University of Aeronautics and Astronautics State Key Laboratory for Novel Software Technology Nanjing University

In this study, we consider a crowdsourcing classification problem in which labeling information from crowds is aggregated to infer latent true labels. We propose a fully Bayesian deep generative crowdsourcing model(Bayes DGC), which combines the strength of deep neural networks(DNNs) on automatic representation learning and the interpretable probabilistic structure encoding of probabilistic graphical models. The model comprises a DNN classifier as a prior for the true labels and a probabilistic model for the annotation generation process. The DNN classifier and annotation generation process share the latent true label variables. To address the inference challenge, we developed a natural-gradient stochastic variational inference, which combines variational message passing for conjugate parameters and stochastic gradient descent for DNN and learns the distribution of latent true labels and workers' confusion matrix via end-to-end training. We illustrated the effectiveness of the proposed model using empirical results on 22 real-world datasets.

关键词： crowdsourcing classification fully Bayesian deep generative models natural gradient stochastic variational inference

来源：评论

学校读者我要写书评

暂无评论

MLLM-I2W: Harnessing Multimodal Large Language Model for Zero-Shot Composed Image Retrieval 31

MLLM-I2W: Harnessing Multimodal Large Language Model for Zer...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Bao, Tong Liu, Che Xu, Derong Zheng, Zhi Xu, Tong State Key Laboratory of Cognitive Intelligence School of Computer Science and Technology University of Science and Technology of China China

ISBN: (纸本)9798891761964

Combined Image Retrieval (CIR) involves retrieving an image based on a reference image and a brief text description, which is widely present in various scenarios such as fashion recommendation. Existing methods can be mainly divided into two categories, respectively supervised CIR methods and Zero-Shot CIR (ZS-CIR) methods. In contrast to supervised CIR methods, which need manually annotated triples for training task-specific models, ZS-CIR models can be trained using images datasets only and performs well. However, ZS-CIR still faces the primary challenge of learning how to map pseudo-words to images within the joint image-text embedding space. Therefore, in this paper, we propose a novel image-text mapping network, named MLLM-I2W, which adaptively converts description-related image information into pseudo-word markers for precise ZS-CIR. Specifically, the image and text encoding enhancement module within the MLLM prompt selects subject headings and generates text descriptions. It then reduces the modality gap between images and text using uncertainty modeling. An adaptive weighting module and a prototype are proposed to adjust and learn the deep fusion features, which are further mapped to pseudo-word markers via well-designed MOE-based mapping network. Our model demonstrates consistent improvements across common CIR benchmarks, including COCO, CIRR, and Fashion-IQ. © 2025 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

VFIMamba: Video Frame Interpolation with state Space Models 38

VFIMamba: Video Frame Interpolation with State Space Models

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhang, Guozhen Liu, Chunxu Cui, Yutao Zhao, Xiaotong Ma, Kai Wang, Limin State Key Laboratory for Novel Software Technology Nanjing University China Tencent China Shanghai AI Lab China

Inter-frame modeling is pivotal in generating intermediate frames for video frame interpolation (VFI). Current approaches predominantly rely on convolution or attention-based models, which often either lack sufficient receptive fields or entail significant computational overheads. Recently, Selective state Space Models (S6) have emerged, tailored specifically for long sequence modeling, offering both linear complexity and data-dependent modeling capabilities. In this paper, we propose VFIMamba, a novel frame interpolation method for efficient and dynamic inter-frame modeling by harnessing the S6 model. Our approach introduces the Mixed-SSM Block (MSB), which initially rearranges tokens from adjacent frames in an interleaved fashion and subsequently applies multi-directional S6 modeling. This design facilitates the efficient transmission of information across frames while upholding linear complexity. Furthermore, we introduce a novel curriculum learning strategy that progressively cultivates proficiency in modeling inter-frame dynamics across varying motion magnitudes, fully unleashing the potential of the S6 model. Experimental findings showcase that our method attains state-of-the-art performance across diverse benchmarks, particularly excelling in high-resolution scenarios. In particular, on the X-TEST dataset, VFIMamba demonstrates a noteworthy improvement of 0.80 dB for 4K frames and 0.96 dB for 2K frames. © 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

Time series classification based on Unet with 2D transformation 12

Time series classification based on Unet with 2D transformat...

引用

12th IEEE International Conference on Identification, Information and Knowledge in the Internet of Things, IIKI 2024

作者： Du, Mingsen Wang, Yunxia Wei, Yanxuan Wu, Xiaona Ji, Cun Shandong Normal University School of Information Science and Engineering Jinan China Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Jinan China

ISBN: (纸本)9798331510633

Time series classification has gained significant attention in the data mining field in recent years. Despite the proposal of numerous methods over the past decades, most of these approaches focus on feature extraction in one-dimensional space, which often results in lower classification accuracy. To address this issue, this paper proposes a Time Series Classification method based on U-Net with 2D transformation (TSC-Unet). This method first transforms univariate time series into 2D space and augments the data, effectively enhancing the diversity of the dataset. Subsequently, features are extracted from the 2D space using a fully convolutional network, fully exploiting multi-scale feature information. U-Netwith skip connections, effectively retains and transmits high-resolution features, significantly reducing information loss and improving segmentation performance. Additionally, the ability to learn multi-scale features enables the model to capture details at different levels, thereby enhancing its understanding of complex data. Experimental results demonstrate that TSC-Unet achieves high classification accuracy on the UCR datasets, validating the effectiveness and superiority of the proposed method. © 2024 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

SCaR: Refining Skill Chaining for Long-Horizon Robotic Manipulation via Dual Regularization 38

SCaR: Refining Skill Chaining for Long-Horizon Robotic Manip...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chen, Zixuan Ji, Ze Huo, Jing Gao, Yang State Key Laboratory for Novel Software Technology Nanjing University China School of Engineering Cardiff University United Kingdom

Long-horizon robotic manipulation tasks typically involve a series of interrelated sub-tasks spanning multiple execution stages. Skill chaining offers a feasible solution for these tasks by pre-training the skills for each sub-task and linking them sequentially. However, imperfections in skill learning or disturbances during execution can lead to the accumulation of errors in skill chaining process, resulting in execution failures. In this paper, we investigate how to achieve stable and smooth skill chaining for long-horizon robotic manipulation tasks. Specifically, we propose a novel skill chaining framework called Skill Chaining via Dual Regularization (SCaR). This framework applies dual regularization to sub-task skill pre-training and fine-tuning, which not only enhances the intra-skill dependencies within each sub-task skill but also reinforces the inter-skill dependencies between sequential sub-task skills, thus ensuring smooth skill chaining and stable long-horizon execution. We evaluate the SCaR framework on two representative long-horizon robotic manipulation simulation benchmarks: IKEA furniture assembly and kitchen organization. Additionally, we conduct a simple real-world validation in tabletop robot pick-and-place tasks. The experimental results show that, with the support of SCaR, the robot achieves a higher success rate in long-horizon tasks compared to relevant baselines and demonstrates greater robustness to perturbations. © 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

FedIERF: Federated Incremental Extremely Random Forest for Wearable Health Monitoring

引用

Journal of computer science & technology 2023年第5期38卷 970-984页

作者：胡春雨忽丽莎袁林陆佃杰吕蕾陈益强 Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center(National Supercomputer Center in Jinan)Qilu University of Technology(Shandong Academy of Sciences)Jinan 250353China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer ScienceJinan 250000China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan 25000China Institute of Information Technology Hebei University of Economics and BusinessShijiazhuang 050061China School of Information Science and Engineering Shandong Normal UniversityJinan 250358China Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China

Wearable health monitoring is a crucial technical tool that offers early warning for chronic diseases due to its superior portability and low power ***,most wearable health data is distributed across dfferent organizations,such as hospitals,research institutes,and companies,and can only be accessed by the owners of the data in compliance with data privacy *** first challenge addressed in this paper is communicating in a privacy-preserving manner among different *** second technical challenge is handling the dynamic expansion of the federation without model *** address the first challenge,we propose a horizontal federated learning method called Federated Extremely Random Forest(FedERF).Its contribution-based splitting score computing mechanism significantly mitigates the impact of privacy protection constraints on model *** on FedERF,we present a federated incremental learning method called Federated Incremental Extremely Random Forest(FedIERF)to address the second technical *** introduces a hardness-driven weighting mechanism and an importance-based updating scheme to update the existing federated model *** experiments show that FedERF achieves comparable performance with non-federated methods,and FedIERF effectively addresses the dynamic expansion of the *** opens up opportunities for cooperation between different organizations in wearable health monitoring.

关键词： federated learning incremental learning random forest wearable health monitoring

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：