检索结果-内蒙古大学图书馆

29th International Conference on Computational Linguistics, COLING 2022

作者： Lu, Xuantao Liu, Jingping Gu, Zhouhong Tong, Hanwen Xie, Chenhao Huang, Junyang Xiao, Yanghua Wang, Wenguang Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China SenseDeal Intelligent Technology Co. Ltd. Beijing China School of Information Science and Engineering East China University of Science and Technology China Fudan-Aishu Cognitive Intelligence Joint Research Center China DataGrand Inc. Shanghai China

Semantic parsing converts natural language utterances into structured logical expressions. We consider two such formal representations: Propositional Logic (PL) and First-order Logic (FOL). The paucity of labeled data is a major challenge in this field. In previous works, dual reinforcement learning has been proposed as an approach to reduce dependence on labeled data. However, this method has the following limitations: 1) The reward needs to be set manually and is not applicable to all kinds of logical expressions. 2) The training process easily collapses when models are trained with only the reward from dual reinforcement learning. In this paper, we propose a scoring model to automatically learn a model-based reward, and an effective training strategy based on curriculum learning is further proposed to stabilize the training process. In addition to the technical contribution, a Chinese-PL/FOL dataset is constructed to compensate for the paucity of labeled data in this field. Experimental results show that the proposed method outperforms competitors on several datasets. Furthermore, by introducing PL/FOL generated by our model, the performance of existing Natural Language Inference (NLI) models is further enhanced. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Object Detection with Depth Information in Road Scenes 8th

Object Detection with Depth Information in Road Scenes

引用

8th International Conference on cognitive Systems and Information Processing, ICCSIP 2023

作者： Liu, Ruowang Chen, Xinbo Tao, Bo Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education Wuhan University of Science and Technology Wuhan China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan China Precision Manufacturing Institute Wuhan University of Science and Technology Wuhan China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Wuhan China

ISBN: (纸本)9789819980208

In recent years, depth estimation has witnessed significant advancements because of the development of deep learning. It's important to note that depth estimation tasks focus solely on predicting the depth of each pixel in an image and do not include object detection or object recognition. Depth estimation is the use of pixel transformations in the image to obtain distance information from each point in the scene to the camera to generate a depth map. Object detection is the process of classifying and localizing an image, given a picture, so as to identify the objects in the picture and determine their location. To overcome this limitation and integrate object detection into the depth estimation process, this paper proposes a novel self-supervised monocular depth estimation algorithm that leverages an attention mechanism. By combining object detection and depth estimation, a real-time multi-task model is designed to enable simultaneous detection and depth estimation of objects. The framework comprises four essential components: an object detection sub-network, a depth estimation sub-network, a lateral sharing unit, and an attention loss. These components work collaboratively to enhance distance estimation accuracy for objects and improve the object detection performance. Throughout experiments, it is evident that the proposed approach can effectively estimate distances to objects and enhances the accuracy of object detection. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Sliding mode controller by using adaptive exponential reaching law based on nonlinear disturbance observer

引用

ISA Transactions 2025年

作者： Liu, Ying Li, Gongfa Du Jiang Yun, Juntong Tao, Bo Jiang, Guozhang Kong, Jianyi Chen, Baojia Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Wuhan430081 China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of science and Technology Wuhan430081 China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of science and Technology Wuhan430081 China Precision Manufacturing Research Institute Wuhan University of Science and Technology Wuhan430081 China Hubei Longzhong Laboratory Xiangyang441000 China Hubei Key Laboratory of Hydroelectric Machinery Design& Maintenance China Three Gorges University Yichang443002 China

Aiming at the position tracking control problem of flexible jointed manipulator in the uncertainties and external disturbances, this paper proposes an integrated nonlinear disturbance observer (NDOB) and a non-singular fast terminal sliding mode (NFTSM) control method based on adaptive exponential reaching law (AERL). The NDOB is designed to ensure that the time-varying disturbance is suppressed in finite time. The AERL is designed to improve the track tracking speed and reduce the chattering of the control input. Simulation results show that compared with the optimal ARL, the proposed method reduces the trajectory tracking error by 1.3 %, improves the trajectory tracking convergence speed. Experimental results show that the proposed method reduces the trajectory tracking error by 0.545 %. © 2025 ISA

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Gaussian Prompter: Linking 2D Prompts for 3D Gaussian Segmentation

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 PP页

作者： Pan, Honghan Liu, Bangzhen Xu, Xuemiao Zheng, Chenxi Nie, Yongwei He, Shengfeng South China University of Technology School of Computer Science and Engineering Guangzhou China Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information Guangdong Engineering Center for Large Model and GenAI Technology State Key Laboratory of Subtropical Building and Urban Science Ministry of Education Key Laboratory of Big Data and Intelligent Robot China

Interactive 3D segmentation in radiance fields is crucial for advanced 3D scene understanding and manipulation. However, existing methods often struggle to achieve both volumetric completeness and segmentation accuracy, primarily because they fail to consider the critical links between 2D prompt-based segmentations across multiple views. Motivated by this gap, we introduce Gaussian Prompter, a novel approach specifically designed for 3D Gaussian Splatting. The core idea behind Gaussian Prompter is to seamlessly integrate a Gaussian-centric segmentation paradigm by effectively linking various 2D prompts from multi-view segmentations to ensure consistent 3D segmentation. To realize this, we employ two tailored approaches: GaussBlend and PinPrompt. GaussBlend aggregates multi-view 2D segmentation masks into a cohesive 3D segmentation, ensuring both accuracy and completeness. PinPrompt leverages high-confidence prompts from adjacent views to enhance segmentation precision further. Additionally, to address the lack of complex datasets in 3D segmentation, we introduce the SegMip-360 dataset, which includes over 350 precisely annotated masks across seven scenes. Extensive experiments demonstrate that the Gaussian Prompter significantly outperforms state-of-the-art methods in both segmentation accuracy and completeness. Our video demonstrations can be found at our project page. © 1979-2012 IEEE.

关键词： 3D segmentation Radiance fields User-interactive scene manipulation

来源：评论

学校读者我要写书评

暂无评论

A Portable System of Mental Fatigue Detection and Mitigation based on Physiological Signals

A Portable System of Mental Fatigue Detection and Mitigation...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Wu, Chao Tian, Fuze Shi, Qiuxia Zhao, Qinglin Hu, Bin Lanzhou University Gansu Provincial Key Laboratory of Wearable Computing School of Information Science and Engineering Lanzhou China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai Institutes for Biological Sciences Chinese Academy of Sciences Lanzhou China Joint Research Center for Cognitive Neurosensor Technology of Lanzhou University Institute of Semiconductors Chinese Academy of Sciences Lanzhou China Ministry of Education Lanzhou China

ISBN: (纸本)9781665468190

Mental fatigue of the brain will cause the weakening of the psychological and physiological functions of the human body, which increases the risk of mistakes and accidents. This paper designs a mental fatigue detection and mitigation system based on human physiological signals and classical music. Through the fatigue assessment and mitigation experiment on 20 healthy subjects, it is verified that the system is able to judge the mental fatigue state of the subjects and play classical music to mitigate fatigue via acquiring and analyzing (alpha+theta)/beta of electroencephalogram (EEG) and heart rate variability (HRV) of ballistocardiogram (BCG). The designed system realizes signal acquisition and fatigue analysis only through using portable device, this makes it have certain application value in office building, hospital, aircraft driving and other scenes. © 2022 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Detection of Key Components of Transmission Lines Based on the Improved YOLOv8

Detection of Key Components of Transmission Lines Based on t...

引用

Image Processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Yuhang Xie Lianfang Tian Qiliang Du Ling Yuan School of Automation Science and Engineering South China University of Technology Guangzhou China School of Automation Science and Engineering South China University of Technology Guangdong Engineering Research Center of Cloud-Edge-End Collaboration Technology for Smart City Guangzhou China School of Automation Science and Engineering South China University of Technology Key Laboratory of Large-Model Embodied-Intelligent Humanoid Robot (2024KSYS004) Guangzhou China

ISBN: (数字)9798350355413

ISBN: (纸本)9798350355420

The detection of key components in transmission lines faces challenges such as significant variations in object scales, complex backgrounds, and difficulties in detecting small targets, leading to low detection accuracy and missed detections. In this study, we propose an improved YOLOv8 algorithm for detecting key components of transmission lines. First, we incorporate Deformable Convolution (DCNv3) to improve the backbone network's feature extraction capability and mitigate accuracy degradation caused by occlusion and angle variations. Subsequently, we use the Adaptively Spatial Feature Fusion (ASFF) to progressively fuse features of different scales and add same-layer skip connections, enabling efficient feature fusion and strengthening the model's ability to detect small objects. Finally, we replaced the original CIoU with the RIoU to further boost the detection capability for small objects. The modified algorithm achieves an mAP 50 of 96.5%, an mAP 50:95 of 79.2%, representing a 3.1% and 4.8% improvement compared to the original YOLOv8 model.

关键词： Power transmission lines Accuracy Convolution Shape Computational modeling Feature extraction Propagation losses Neck Standards Load modeling

来源：评论

学校读者我要写书评

暂无评论

Multi-Resolution Convolution for 3D Semantic Segmentation

Multi-Resolution Convolution for 3D Semantic Segmentation

引用

Intelligent robotics and Automatic Control (IRAC), International Conference on

作者： Qihui Li Lianfang Tian Qiliang Du Yuhang Xie School of Automation Science and Engineering South China University of Technology Guangzhou China School of Automation Science and Engineering South China University of Technology Guangdong Engineering Research Center of Cloud-Edge-End Collaboration Technology for Smart City Guangzhou China School of Automation Science and Engineering South China University of Technology Key Laboratory of Large-Model Embodied-Intelligent Humanoid Robot (2024KSYS004) Guangzhou China

ISBN: (数字)9798350389807

ISBN: (纸本)9798350389814

Effective capture of multi-scale features is crucial for improving performance in 3D point cloud semantic segmentation tasks. This paper introduces a novel framework that enhances the extraction of semantic information from complex objects in 3D point clouds using multi-resolution techniques. By utilizing varying voxel resolutions and convolutional kernel sizes, we integrate high-resolution voxels to capture fine details and low-resolution voxels to extract global features, achieving robust feature fusion. Experimental results demonstrate the effectiveness of our proposed network validated on the ScanNet v2 dataset, particularly excelling in the semantic segmentation task for small objects and complex scenes. This study highlights the significance of multi-resolution strategies in 3D scene understanding, providing new insights for future research in the field.

关键词： Point cloud compression Solid modeling Three-dimensional displays Convolution Semantic segmentation Semantics Feature extraction Data models Kernel robots

来源：评论

学校读者我要写书评

暂无评论

Event-aided Semantic Scene Completion

arXiv

引用

arXiv 2025年

作者： Guo, Shangwei Shi, Hao Wang, Song Yin, Xiaoting Yang, Kailun Wang, Kaiwei State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University Hangzhou310027 China School of Robotics the National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China College of Computer Science and Technology Zhejiang University Hangzhou310027 China

Autonomous driving systems rely on robust 3D scene understanding. Recent advances in Semantic Scene Completion (SSC) for autonomous driving underscore the limitations of RGB-based approaches, which struggle under motion blur, poor lighting, and adverse weather. Event cameras, offering high dynamic range and low latency, address these challenges by providing asynchronous data that complements RGB inputs. We present DSEC-SSC, the first real-world benchmark specifically designed for event-aided SSC, which includes a novel 4D labeling pipeline for generating dense, visibility-aware labels that adapt dynamically to object motion. Our proposed RGB-Event fusion framework, EvSSC, introduces an Event-aided Lifting Module (ELM) that effectively bridges 2D RGB-Event features to 3D space, enhancing view transformation and the robustness of 3D volume construction across SSC models. Extensive experiments on DSEC-SSC and simulated SemanticKITTI-E demonstrate that EvSSC is adaptable to both transformer-based and LSS-based SSC architectures. Notably, evaluations on SemanticKITTI-C demonstrate that EvSSC achieves consistently improved prediction accuracy across five degradation modes and both In-domain and Out-of-domain settings, achieving up to a 52.5% relative improvement in mIoU when the image sensor partially fails. Additionally, we quantitatively and qualitatively validate the superiority of EvSSC under motion blur and extreme weather conditions, where autonomous driving is challenged. The established datasets and our codebase will be made publicly at https://***/Pandapan01/EvSSC. Copyright © 2025, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Learning to Learn Transferable Generative Attack for Person Re-Identification

arXiv

引用

arXiv 2024年

作者： Bian, Yuan Liu, Min Wang, Xueping Ma, Yunfeng Wang, Yaonan College of Electrical and Information Engineering Hunan University National Engineering Research Center of Robot Visual Perception and Control Technology Hunan Changsha China College of Information Science and Engineering Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Changsha China

Deep learning-based person re-identification (re-id) models are widely employed in surveillance systems and inevitably inherit the vulnerability of deep networks to adversarial attacks. Existing attacks merely consider cross-dataset and cross-model transferability, ignoring the cross-test capability to perturb models trained in different domains. To powerfully examine the robustness of real-world re-id models, the Meta Transferable Generative Attack (MTGA) method is proposed, which adopts meta-learning optimization to promote the generative attacker producing highly transferable adversarial examples by learning comprehensively simulated transfer-based cross-model&dataset&test black-box meta attack tasks. Specifically, cross-model&dataset black-box attack tasks are first mimicked by selecting different re-id models and datasets for meta-train and meta-test attack processes. As different models may focus on different feature regions, the Perturbation Random Erasing module is further devised to prevent the attacker from learning to only corrupt model-specific features. To boost the attacker learning to possess cross-test transferability, the Normalization Mix strategy is introduced to imitate diverse feature embedding spaces by mixing multi-domain statistics of target models. Extensive experiments show the superiority of MTGA, especially in cross-model&dataset and cross-model&dataset&test attacks, our MTGA outperforms the SOTA methods by 20.0% and 11.3% on mean mAP drop rate, respectively. The source codes are available at https://***/yuanbianGit/MTGA. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Research on Lightweight Intervertebral Disc Segmentation Method for Spine Magnetic Resonance Images: Lightweight Segmentation Method for Spine MRI 22

Research on Lightweight Intervertebral Disc Segmentation Met...

引用

Proceedings of the 2022 4th International Conference on robotics, Intelligent Control and Artificial Intelligence

作者： Xianda Li Qi Li James Zhiqing Wen Huiyuan Luo Siyuan He School of Computer Science and Technology Changchun University of Science and Technology China School of Computer Science and Technology Changchun University of Science and Technology China and Zhongshan Institute of Changchun University of Science and Technology China Intelligent Robot Engineering Research Center Ji Hua Laboratory China

ISBN: (纸本)9781450398343

To address the problem of conflicting segmentation accuracy and model parametric numbers in many lumbar MR image disc segmentation methods, we propose a lightweight segmentation pipeline named Lite-snake for lumbar MR image disc instances. We use Nanodet as a lightweight target detection model, a parallel feature aggregation module to aggregate multi-scale features, and a depth-separable cyclic convolution to reconstruct deep snake. The method achieves an IoU of 79.49% and a DSC of 88.50% on the test set of lumbar MR images with only 5,670,000 parameters. The experimental results show that compared to many current deep-learning image segmentation methods, our method dramatically reduces the number of parameters of the model while ensuring segmentation accuracy. Therefore it is easy to deploy to lightweight mobile devices and has good application prospects.

关键词：

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：