检索结果-内蒙古大学图书馆

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Zhao, Jiayu Wei, Fei-Fei Liang, Anqi Mei, Kuizhi College of Artificial Intelligence Xi’an Jiaotong University Xi’an China National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center of Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China

ISBN: (纸本)9789819601219

This paper introduces BFVTModel, an efficient 3D semantic segmentation Model. Multi-modal segmentators, which employ LiDAR and Camera sensors as input, have gained popularity owing to their capacity to leverage the semantic information in image data and complementary details in point cloud data. However, the segmentation model using multi-modal input faces some problems, such as the modal consistency problem and the model complexity problem. In this paper, we propose utilizing the idea of an Occupancy-based multi-view feature combination method to obtain the 3D information of the features of the two modalities independently. We also design a projection structure to obtain the three-axis features in different modalities according to the information, including the main view, side view, and top view features. We construct a module called Feature View Transform (FVT) that combines three-axis plane features with bias. The CNN neural network is used to replace attention mechanisms, reducing the dimensionality of the original three-dimensional space matrix, thereby reducing the parameter count and increasing the model’s speed. We used a bilinear mapping structure to fuse LiDAR and Camera features and complete the 3D semantic segmentation task. We validate the model on the NuScenes dataset and obtain competitive accuracy results while leading the way in efficiency evaluation metrics. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

On the Stability of Random Access with Congestion Control 14th

On the Stability of Random Access with Congestion Control

引用

14th EAI International Conference on Wireless and Satellite Systems, WiSATS 2024

作者： Xu, Yu Cui, Chen Wang, Zhenyong Guo, Qing School of Electronics and Information Engineering Harbin Institute of Technology Harbin150001 China National Engineering Research Center of Visual Technology School of Computer Science Peking University Beijing100871 China Songjiang Laboratory Harbin Institute of Technology Harbin150001 China

ISBN: (纸本)9783031861956

The random access protocol is a critical technique widely used in various wireless networks. A significant challenge is analyzing the stability of the random access system when a large number of users transmit packets independently. Although the congestion control policy can enhance the stability of the system, there is currently a lack of quantitative analysis on the stability of random access with congestion control. In this paper, we analyze the random access system with congestion control and quantify its stability. Specifically, we consider a congestion control scheme to enhance the stability of the random access system and present the graphical analytical model. Based on this graphical model, we qualitatively discuss the behavioral variations of the system as it works and quantify its stability. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering 2025.

关键词： Congestion control (communication)

来源：评论

学校读者我要写书评

暂无评论

Multi-Keypoint Affordance Representation for Functional Dexterous Grasping

arXiv

引用

arXiv 2025年

作者： Yang, Fan Luo, Dongsheng Chen, Wenrui Lin, Jiacheng Cai, Junjie Yang, Kailun Li, Zhiyong Wang, Yaonan School of Robotics Hunan University China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China College of Computer Science and Electronic Engineering Hunan University Changsha China

Functional dexterous grasping requires precise hand-object interaction, going beyond simple gripping. Existing affordance-based methods primarily predict coarse interaction regions and cannot directly constrain the grasping posture, leading to a disconnection between visual perception and manipulation. To address this issue, we propose a multi-keypoint affordance representation for functional dexterous grasping, which directly encodes task-driven grasp configurations by localizing functional contact points. Our method introduces Contact-guided Multi-Keypoint Affordance (CMKA), leveraging human grasping experience images for weak supervision combined with Large Vision Models for fine affordance feature extraction, achieving generalization while avoiding manual keypoint annotations. Additionally, we present a Keypoint-based Grasp matrix Transformation (KGT) method, ensuring spatial consistency between hand keypoints and object contact points, thus providing a direct link between visual perception and dexterous grasping actions. Experiments on public real-world FAH datasets, IsaacGym simulation, and challenging robotic tasks demonstrate that our method significantly improves affordance localization accuracy, grasp consistency, and generalization to unseen tools and tasks, bridging the gap between visual affordance learning and dexterous robotic manipulation. The source code and demo videos will be publicly available at https://***/PopeyePxx/MKA. Copyright © 2025, The Authors. All rights reserved.

关键词： Vision

来源：评论

学校读者我要写书评

暂无评论

Towards Real-World Aerial Vision Guidance with Categorical 6D Pose Tracker

引用

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

作者： Sun, Jingtao Wang, Yaonan Wang, Danwei Hunan University College of Electrical and Information Engineering National Engineering Research Centre for Robot Visual Perception and Control Changsha410082 China Nanyang Technological University School of Electrical and Electronic Engineering SG 639798 Singapore

Tracking the object 6-DoF pose is crucial for various downstream robot tasks and real-world applications. In this paper, we investigate the real-world robot task of aerial vision guidance for aerial robotics manipulation, utilizing category-level 6-DoF pose tracking. Aerial conditions inevitably introduce special challenges, such as rapid viewpoint changes in pitch and roll and inter-frame differences. To support these challenges in task, we firstly introduce a robust category-level 6-DoF pose tracker (Robust6DoF). This tracker leverages shape and temporal prior knowledge to explore optimal inter-frame keypoint pairs, generated under a priori structural adaptive supervision in a coarse-to-fine manner. Notably, our Robust6DoF employs a Spatial-Temporal Augmentation module to deal with the problems of the inter-frame differences and intra-class shape variations through both temporal dynamic filtering and shape-similarity filtering. We further present a Pose-Aware Discrete Servo strategy (PAD-Servo), serving as a decoupling approach to implement the final aerial vision guidance task. It contains two servo action policies to better accommodate the structural properties of aerial robotics manipulation. Exhaustive experiments on four well-known public benchmarks demonstrate the superiority of our Robust6DoF. Real-world tests directly verify that our Robust6DoF along with PAD-Servo can be readily used in real-world aerial robotic applications. The project homepage is released at Robust6DoF. © 1979-2012 IEEE.

关键词： visual servoing

来源：评论

学校读者我要写书评

暂无评论

EgoEvGesture: Gesture Recognition Based on Egocentric Event Camera

arXiv

引用

arXiv 2025年

作者： Wang, Luming Shi, Hao Yin, Xiaoting Yang, Kailun Wang, Kaiwei State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University Hangzhou310027 China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China

Egocentric gesture recognition is a pivotal technology for enhancing natural human-computer interaction, yet traditional RGB-based solutions suffer from motion blur and illumination variations in dynamic scenarios. While event cameras show distinct advantages in handling high dynamic range with ultra-low power consumption, existing RGB-based architectures face inherent limitations in processing asynchronous event streams due to their synchronous frame-based nature. Moreover, from an egocentric perspective, event cameras record data that include events generated by both head movements and hand gestures, thereby increasing the complexity of gesture recognition. To address this, we propose a novel network architecture specifically designed for event data processing, incorporating (1) a lightweight CNN with asymmetric depthwise convolutions to reduce parameters while preserving spatiotemporal features, (2) a plug-and-play state-space model as context block that decouples head movement noise from gesture dynamics, and (3) a parameter-free Bins-Temporal Shift Module (BSTM) that shifts features along bins and temporal dimensions to fuse sparse events efficiently. We further build the EgoEvGesture dataset, the first large-scale dataset for egocentric gesture recognition using event cameras. Experimental results demonstrate that our method achieves 62.7% accuracy in heterogeneous testing with only 7M parameters, 3.1% higher than state-of-the-art approaches. Notable misclassifications in freestyle motions stem from high inter-personal variability and unseen test patterns differing from training data. Moreover, our approach achieved a remarkable accuracy of 96.97% on DVS128 Gesture [1], demonstrating strong cross-dataset generalization capability. The dataset and models are made publicly available at https://***/3190105222/EgoEv_Gesture. Copyright © 2025, The Authors. All rights reserved.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Potential of Segment Anything Model 2 for RGB-Thermal Semantic Segmentation with Language Guidance

arXiv

引用

arXiv 2025年

作者： Zhao, Jiayi Teng, Fei Luo, Kai Zhao, Guoqiang Li, Zhiyong Zheng, Xu Yang, Kailun The School of Robotics Hunan University China The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China The AI Thrust Hong Kong University of Science and Technology Guangzhou China

The perception capability of robotic systems relies on the richness of the dataset. Although Segment Anything Model 2 (SAM2), trained on large datasets, demonstrates strong perception potential in perception tasks, its inherent training paradigm prevents it from being suitable for RGB-T tasks. To address these challenges, we propose SHIFNet, a novel SAM2-driven Hybrid Interaction Paradigm that unlocks the potential of SAM2 with linguistic guidance for efficient RGB-Thermal perception. Our framework consists of two key components: (1) Semantic-Aware Cross-modal Fusion (SACF) module that dynamically balances modality contributions through text-guided affinity learning, overcoming SAM2’s inherent RGB bias;(2) Heterogeneous Prompting Decoder (HPD) that enhances global semantic information through a semantic enhancement module and then combined with category embeddings to amplify cross-modal semantic consistency. With 32.27M trainable parameters, SHIFNet achieves state-of-the-art segmentation performance on public benchmarks, reaching 89.8% on PST900 and 67.8% on FMB, respectively. The framework facilitates the adaptation of pre-trained large models to RGB-T segmentation tasks, effectively mitigating the high costs associated with data collection while endowing robotic systems with comprehensive perception capabilities. The source code will be made publicly available at https://***/iAsakiT3T/SHIFNet. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

RAMPGrasp: Retentive Attention-based Multiscale Perception Grasp Detection Network

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Huang, Jianan Liu, Xuebing Zhu, Qing Wang, Yaonan Feng, Mingtao Zhou, Jiaming Zhou, Zhen Chen, Lin Wang, Danwei Hunan University The National Engineering Research Center for Robot Visual Perception and Control College of Electrical and Information Engineering Changsha410082 China Xidian University School of Artificial Intelligence Xi'an710071 China Nanyang Technological University School of Electrical and Electrical Engineering Nanyang Avenue 639798 Singapore

In robotic grasp detection, challenges such as uncertainty in object type, size, and placement within the scene diminish grasping accuracy. However, the inability to effectively locate the graspable area and incomplete feature extraction for grasp detection are two key factors that hinder grasp detection accuracy and are not considered in current methods. This paper presents a novel retentive attention-based multiscale perception grasp detection network (RAMPGrasp) to address this constraint. First, we introduce retentive attention in the feature extraction module, which significantly improves the efficiency of attention score computation for long sequences in visual tasks. Second, we propose a multiscale spatial pyramid attention module, which can effectively adjust the importance of multiscale feature sequences and feature channels, while enhancing the correlation of multiscale features. Third, we design the prediction module as a coarse-to-fine framework, improving feature representation for grasp detection by considering the distribution trend of grasp poses. As a result, RAMPGrasp achieves state-of-the-art grasp detection accuracy, with 98.4% and 95.6% on the Cornell and Jacquard datasets, respectively. © 1991-2012 IEEE.

关键词： robotics

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

引用

IEEE Transactions on Image Processing 2025年 PP卷 PP页

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

Deep learning-based person re-identification (reid) 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 crossmodel&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. © 1992-2012 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Adversarial Mixup-Based Contrast Learning for Data-Driven Predictive Maintenance in Long-Tailed Recognition

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Peng, Ru Chen, Xingyu Lan, Xuguang National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Application Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China

Deep neural networks have achieved remarkable success in various computer vision tasks. However, in real-world applications, such as the Internet of Things (IoT), these models often struggle due to the long-tailed data distributions. For instance, in scenarios such as Holographic Counterpart Integration in IoT-based predictive maintenance for home systems or smart repair services, common operational states are prevalent in the dataset. In contrast, rare failures, such as hardware malfunctions or system breakdowns, are represented by only a few samples. This imbalance severely impacts models, making it difficult to accurately predict rare failures, leading to costly downtime or unanticipated equipment failure. Current contrastive learning-based methods are effective at optimizing feature distributions but often overlook inter-class relationships and are highly sensitive to class imbalance, which limits their generalization ability. To address these challenges, we propose the Adversarial Mixup-based supervised contrast learning (AMCL) framework, which integrates Mixup-based data augmentation with contrastive learning and incorporates an adversarial-inspired sample policy generator. AMCL generates boundary samples via a dynamically optimized Mixup strategy to enhance inter-class relationship modeling and improve predictions on ambiguous boundaries. Furthermore, we introduce a new MixCo loss function to account for the non-one-hot distribution of Mixup-generated targets, ensuring better alignment with augmented data and improving optimization efficiency. AMCL is easy to implement and achieves a performance superior to recent approaches for long-tailed recognition across various datasets such as ImageNet-LT, iNaturalist18, CIFAR-10-LT, and CIFAR-100-LT. © 1975-2011 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Subretinal fibrosis secondary to neovascular age-related macular degeneration:mechanisms and potential therapeutic targets

引用

Neural Regeneration research 2025年第2期20卷 378-393页

作者： Jingxiang Zhang Xia Sheng Quanju Ding Yujun Wang Jiwei Zhao Jingfa Zhang Department of Ophthalmology People’s Hospital of Huangdao DistrictQingdaoShandong ProvinceChina Department of Urology People’s Hospital of Huangdao DistrictQingdaoShandong ProvinceChina Department of Ophthalmology Shanghai General Hospital(Shanghai First People’s Hospital)Shanghai Jiao Tong University School of MedicineShanghaiChina National Clinical Research Center for Eye Diseases Shanghai Key Laboratory of Ocular Fundus DiseasesShanghai Engineering Center for Visual Science and PhotomedicineShanghai Engineering Center for Precise Diagnosis and Treatment of Eye DiseasesShanghaiChina

Subretinal fibrosis is the end-stage sequelae of neovascular age-related macular *** causes local damage to photoreceptors,retinal pigment epithelium,and choroidal vessels,which leads to permanent central vision loss of patients with neovascular age-related macular *** pathogenesis of subretinal fibrosis is complex,and the underlying mechanisms are largely ***,there are no effective treatment options.A thorough understanding of the pathogenesis of subretinal fibrosis and its related mechanisms is important to elucidate its complications and explore potential *** current article reviews several aspects of subretinal fibrosis,including the current understanding on the relationship between neovascular age-related macular degeneration and subretinal fibrosis;multimodal imaging techniques for subretinal fibrosis;animal models for studying subretinal fibrosis;cellular and non-cellular constituents of subretinal fibrosis;pathophysiological mechanisms involved in subretinal fibrosis,such as aging,infiltration of macrophages,different sources of mesenchymal transition to myofibroblast,and activation of complement system and immune cells;and several key molecules and signaling pathways participating in the pathogenesis of subretinal fibrosis,such as vascular endothelial growth factor,connective tissue growth factor,fibroblast growth factor 2,platelet-derived growth factor and platelet-derived growth factor receptor-β,transforming growth factor-βsignaling pathway,Wnt signaling pathway,and the axis of heat shock protein 70-Toll-like receptors 2/*** review will improve the understanding of the pathogenesis of subretinal fibrosis,allow the discovery of molecular targets,and explore potential treatments for the management of subretinal fibrosis.

关键词： choroidal neovascularization epithelial-mesenchymal transition mesenchymal transition myofibroblast neovascular age-related macular degeneration submacular fibrosis subretinal fibrosis therapeutic targets transforming growth factor-β vascular endothelial growth factor

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：