检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Hongwei Chu Meng Shen Jiawen Peng Andy J Ma School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Domain-Adaptive Semantic Segmentation (DASS) aims to transfer a segmentation model trained on a labeled source domain to an unlabeled target domain. Most existing methods overlook the errors in the source labels and directly utilize the erroneous source labels for training. This may result in wrong source domain knowledge being wrongly transferred to the target domain, which leads to similar classes cannot be separated well in the target domain. To this end, we propose a novel Confidence-guided Online REfinement (CORE) method, which introduces a refinement network trained on the target data to rectify erroneous source labels online. This can effectively avoid transferring erroneous knowledge from the source domain to the target domain. On the other hand, using the same threshold for all classes in the target domain may result in a severe class imbalance in self-training. Therefore, we propose Class-aware Adaptive Thresholding (CAT) to calculate different thresholds for different target classes, which adaptively filter target pixels with high confidence for better adaptation. Our proposed CORE-CAT method can be easily integrated with existing methods and achieves superior performance across various domain-adaptive semantic segmentation benchmarks.

关键词： Training Adaptation models Semantic segmentation Neural networks Adaptive filters Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Single-View Scene Point Cloud Human Grasp Generation

Single-View Scene Point Cloud Human Grasp Generation

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yan-Kang Wang Chengyi Xing Yi-Lin Wei Xiao-Ming Wu Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Stanford University Stanford CA Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

In this work, we explore a novel task of generating human grasps based on single-view scene point clouds, which more accurately mirrors the typical real-world situation of observing objects from a single viewpoint. Due to the incompleteness of object point clouds and the presence of numerous scene points, the generated hand is prone to penetrating into the invisible parts of the object and the model is easily affected by scene points. Thus, we introduce S2HGrasp, a framework composed of two key modules: the Global Perception module that globally perceives partial object point clouds, and the DiffuGrasp module designed to generate high-quality human grasps based on complex inputs that include scene points. Additionally, we introduce S2HGD dataset, which comprises approximately 99,000 single-object single-view scene point clouds of 1,668 unique objects, each annotated with one human grasp. Our extensive experiments demonstrate that S2HGrasp can not only generate natural human grasps regardless of scene points, but also effectively prevent penetration between the hand and invisible parts of the object. Moreover, our model showcases strong generalization capability when applied to unseen objects. Our code and dataset are available at https://***/iSEE-laboratory/S2HGrasp.

关键词： Point cloud compression Computer vision Codes Computational modeling Pattern recognition Mirrors Task analysis

来源：评论

学校读者我要写书评

暂无评论

Efficient and Effective Weakly-Supervised Action Segmentation via Action-Transition-Aware Boundary Alignment

Efficient and Effective Weakly-Supervised Action Segmentatio...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Angchi Xu Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Weakly-supervised action segmentation is a task of learning to partition a long video into several action segments, where training videos are only accompanied by transcripts (ordered list of actions). Most of existing methods need to infer pseudo segmentation for training by serial alignment between all frames and the transcript, which is time-consuming and hard to be parallelized while training. In this work, we aim to escape from this inefficient alignment with massive but redundant frames, and instead to directly localize a few action transitions for pseudo segmentation generation, where a transition refers to the change from an action segment to its next adjacent one in the transcript. As the true transitions are submerged in noisy boundaries due to intra-segment visual variation, we propose a novel Action-Transition-Aware Boundary Alignment (ATBA) framework to efficiently and effectively filter out noisy boundaries and detect transitions. In addition, to boost the semantic learning in the case that noise is inevitably present in the pseudo segmentation, we also introduce video-level losses to utilize the trusted video-level supervision. Extensive experiments show the effectiveness of our approach on both performance and training speed. 1 1 Code is available at https://***/iSEE-laboratory/CVPR24_ATBA.

关键词： Training Visualization Computer vision Semantics Noise Robustness Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A Spatial Feature Extraction Method for Enhancing Upper Limb Motion Intent Prediction in EMG-PR System 46

A Spatial Feature Extraction Method for Enhancing Upper Limb...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Peng, Boxing Zhang, Haoshi Li, Xiangxin Zheng, Yue Li, Guanglin Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China University of Chinese Academy of Sciences Shenzhen College of Advanced Technology Shenzhen518055 China Southern University of Science and Technology Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Shenzhen518055 China Siat Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518055 China

ISBN: (纸本)9798350371499

High-Density Surface Electromyography (HD-sEMG) enriches motion intention pattern recognition systems by providing more spatial information. Multichannel linear descriptors (MLD) could provide a comprehensive description of the overall state characteristics within the muscle regions. In this study, an MLD-based spatial feature extraction method was proposed to capture differences and correlations in various muscle regions during movement, ultimately enhancing the system's classification accuracy. The performance of the feature extraction method was compared with traditional time domain feature extraction method under various classifiers and different movement types. The results show that employing the proposed method with the spatial features improves the classification error rates of combined movements from 11.14% to 7.28%, and better adaptability for all classifiers utilized in this study, which shows the effect of utilization of spatial information in different muscle regions. © 2024 IEEE.

关键词： Electromyography

来源：评论

学校读者我要写书评

暂无评论

Blockchain Privacy Protection Based on Post Quantum Threshold Algorithm

引用

Computers, Materials & Continua 2023年第7期76卷 957-973页

作者： Faguo Wu Bo Zhou Jie Jiang Tianyu Lei Jiale Song Institute of Artificial Intelligence Beihang UniversityBeijing100191China Zhongguancun Laboratory Beijing100094China Key Laboratory of Mathematics Informatics and Behavioral Semantics(LMIB)Beihang UniversityBeijing100191China Bejing Advanced Innovation Center for Future Blockchain and Privacy Computing Beihang UniversityBeijing100191China LMIB and School of Mathematical Sciences Beihang UniversityBeijing100191China

With the rapid increase in demand for data trustworthiness and data security,distributed data storage technology represented by blockchain has received unprecedented *** technologies have been suggested for various uses because of their remarkable ability to offer decentralization,high autonomy,full process traceability,and tamper *** enables the exchange of information and value in an untrusted *** has been a significant increase in attention to the confidentiality and privacy preservation of blockchain *** data privacy is a critical concern in cryptography,and one of the most important protocols used to achieve this is the secret-sharing *** dividing the secret into shares and distributing them among multiple parties,no one can access the secret without the cooperation of the other ***,Attackers with quantum computers in the future can execute Grover’s and Shor’s algorithms on quantum computers that can break or reduce the currently widely used ***,centralized management of keys increases the risk of key *** paper proposed a post-quantum threshold algo-rithm to reduce the risk of data privacy leakage in blockchain *** algorithm uses distributed key management technology to reduce the risk of individual node private key leakage and provide post-quantum *** proposed privacy-preserving cryptographic algorithm provides a post-quantum threshold architecture for managing data,which involves defining users and interaction processes within the *** paper applies a linear secret-sharing solution to partition the private key of the Number Theory Research Unit(NTRU)algorithm into n *** constructs a t–n threshold that allows recovery of the plaintext only when more than t nodes participate in *** characteristic of a threshold makes the scheme resistant to collusion attacks from members whose combined credibility is less than the

关键词： Blockchain post-quantum cryptography threshold cryptography privacy protection

来源：评论

学校读者我要写书评

暂无评论

Grasp as You Say: Language-guided Dexterous Grasp Generation

arXiv

引用

arXiv 2024年

作者： Wei, Yi-Lin Jiang, Jian-Jian Xing, Chengyi Tan, Xian-Tuo Wu, Xiao-Ming Li, Hao Cutkosky, Mark Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Stanford University United States Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

This paper explores a novel task "Dexterous Grasp as You Say" (DexGYS), enabling robots to perform dexterous grasping based on human commands expressed in natural language. However, the development of this field is hindered by the lack of datasets with natural human guidance;thus, we propose a language-guided dexterous grasp dataset, named DexGYSNet, offering high-quality dexterous grasp annotations along with flexible and fine-grained human language guidance. Our dataset construction is cost-efficient, with the carefully-design hand-object interaction retargeting strategy, and the LLM-assisted language guidance annotation system. Equipped with this dataset, we introduce the DexGYSGrasp framework for generating dexterous grasps based on human language instructions, with the capability of producing grasps that are intent-aligned, high quality and diversity. To achieve this capability, our framework decomposes the complex learning process into two manageable progressive objectives and introduce two components to realize them. The first component learns the grasp distribution focusing on intention alignment and generation diversity. And the second component refines the grasp quality while maintaining intention consistency. Extensive experiments are conducted on DexGYSNet and real world environments for validation. Copyright © 2024, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Nerve function restoration following targeted muscle reinnervation after varying delayed periods

引用

Neural Regeneration Research 2023年第12期18卷 2762-2766页

作者： Yuanheng Li Jiangping Huang Yuling Chen Shanshan Zhu Zhen Huang Lin Yang Guanglin Li Key Laboratory of Human-Machine Intelligence-Synergy Systems and Branch of Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen Institutes of Advanced TechnologyChinese Academy of SciencesShenzhenGuangdong ProvinceChina Department of Rehabilitation Medicine Guangzhou University of Chinese MedicineGuangzhouGuangdong ProvinceChina Department of Rehabilitation Medicine Yibin Hospital of Traditional Chinese MedicineYibinSichuan ProvinceChina

Targeted muscle reinnervation has been proposed for reconstruction of neuromuscular function in ***,it is unknown whether performing delayed targeted muscle reinnervation after nerve injury will affect restoration of *** this rat nerve injury study,the median and musculocutaneous nerves of the forelimb were *** proximal median nerve stump was sutured to the distal musculocutaneous nerve stump immediately and 2 and 4 weeks after surgery to reinnervate the biceps *** targeted muscle reinnervation,intramuscular myoelectric signals from the biceps brachii were *** amplitude gradually increased with *** brachii myoelectric signals and muscle fiber morphology and grooming behavior did not significantly differ among rats subjected to delayed target muscle innervation for different *** muscle reinnervation delayed for 4 weeks can acquire the same nerve function restoration effect as that of immediate reinnervation.

关键词： biceps brachii delayed nerve repair delayed targeted muscle reinnervation functional reconstruction grooming test implanted electrode intramuscular myoelectric signals median nerve motor function nerve transfer

来源：评论

学校读者我要写书评

暂无评论

NECA: Neural Customizable Human Avatar

arXiv

引用

arXiv 2024年

作者： Xiao, Junjin Zhang, Qing Xu, Zhan Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Adobe Research United States Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Human avatar has become a novel type of 3D asset with various applications. Ideally, a human avatar should be fully customizable to accommodate different settings and environments. In this work, we introduce NECA, an approach capable of learning versatile human representation from monocular or sparse-view videos, enabling granular customization across aspects such as pose, shadow, shape, lighting and texture. The core of our approach is to represent humans in complementary dual spaces and predict disentangled neural fields of geometry, albedo, shadow, as well as an external lighting, from which we are able to derive realistic rendering with high-frequency details via volumetric rendering. Extensive experiments demonstrate the advantage of our method over the state-of-the-art methods in photorealistic rendering, as well as various editing tasks such as novel pose synthesis and relighting. The code is available at https://***/iSEE-laboratory/NECA. Copyright © 2024, The Authors. All rights reserved.

关键词： Lighting

来源：评论

学校读者我要写书评

暂无评论

Event-Guided Procedure Planning from Instructional Videos with Text Supervision

arXiv

引用

arXiv 2023年

作者： Wang, An-Lan Lin, Kun-Yu Du, Jia-Run Meng, Jingke Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

In this work, we focus on the task of procedure planning from instructional videos with text supervision, where a model aims to predict an action sequence to transform the initial visual state into the goal visual state. A critical challenge of this task is the large semantic gap between observed visual states and unobserved intermediate actions, which is ignored by previous works. Specifically, this semantic gap refers to that the contents in the observed visual states are semantically different from the elements of some action text labels in a procedure. To bridge this semantic gap, we propose a novel event-guided paradigm, which first infers events from the observed states and then plans out actions based on both the states and predicted events. Our inspiration comes from that planning a procedure from an instructional video is to complete a specific event and a specific event usually involves specific actions. Based on the proposed paradigm, we contribute an Event-guided Prompting-based Procedure Planning (E3P) model, which encodes event information into the sequential modeling process to support procedure planning. To further consider the strong action associations within each event, our E3P adopts a mask-and-predict approach for relation mining, incorporating a probabilistic masking scheme for regularization. Extensive experiments on three datasets demonstrate the effectiveness of our proposed model. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Generating Anomalies for Video Anomaly Detection with Prompt-based Feature Mapping

Generating Anomalies for Video Anomaly Detection with Prompt...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zuhao Liu Xiao-Ming Wu Dian Zheng Kun-Yu Lin Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Anomaly detection in surveillance videos is a challenging computer vision task where only normal videos are available during training. Recent work released the first virtual anomaly detection dataset to assist real-world detection. However, an anomaly gap exists because the anomalies are bounded in the virtual dataset but unbounded in the real world, so it reduces the generalization ability of the virtual dataset. There also exists a scene gap between virtual and real scenarios, including scene-specific anomalies (events that are abnormal in one scene but normal in another) and scene-specific attributes, such as the viewpoint of the surveillance camera. In this paper, we aim to solve the problem of the anomaly gap and scene gap by proposing a prompt-based feature mapping framework (PFMF). The PFMF contains a mapping network guided by an anomaly prompt to generate unseen anomalies with unbounded types in the real scenario, and a mapping adaptation branch to narrow the scene gap by applying domain classifier and anomaly classifier. The proposed framework outperforms the state-of-the-art on three benchmark datasets. Extensive ablation experiments also show the effectiveness of our framework design.

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：