检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Chaolei Tan Jianhuang Lai Wei-Shi Zheng Jian-Fang Hu School of Computer Science and Engineering Sun Yat-sen University 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)9798350353006

ISBN: (纸本)9798350353013

Video Paragraph Grounding (VPG) is an emerging task in video-language understanding, which aims at localizing multiple sentences with semantic relations and temporal or-der from an untrimmed video. However, existing VPG approaches are heavily reliant on a considerable number of temporal labels that are laborious and time-consuming to acquire. In this work, we introduce and explore Weakly-Supervised Video Paragraph Grounding (WSVPG) to elim-inate the need of temporal annotations. Different from pre-vious weakly-supervised grounding frameworks based on multiple instance learning or reconstruction learning for two-stage candidate ranking, we propose a novel siamese learning framework that jointly learns the cross-modal feature alignment and temporal coordinate regression without timestamp labels to achieve concise one-stage localization for WSVPG. Specifically, we devise a Siamese Grounding TRansformer (SiamGTR) consisting of two weight-sharing branches for learning complementary supervision. An Aug-mentation Branch is utilized for directly regressing the tem-poral boundaries of a complete paragraph within a pseudo video, and an Inference Branch is designed to capture the order-guided feature correspondence for localizing multi-ple sentences in a normal video. We demonstrate by exten-sive experiments that our paradigm has superior practica-bility and flexibility to achieve efficient weakly-supervised or semi-supervised learning, outperforming state-of-the-art methods trained with the same or stronger supervision.

关键词： Location awareness Computer vision Grounding Annotations Semantics Semisupervised learning Transformers

来源：评论

学校读者我要写书评

暂无评论

Inequality-Type Zhang Equivalency of Great-Than-or-Equal-to (GTOET) Sign in Matrix-Vector,Matrix,and Integral Situations Applied to Obstacle Avoidance 41

Inequality-Type Zhang Equivalency of Great-Than-or-Equal-to ...

引用

第41届中国控制会议

作者： Yunong Zhang Jianzhen Xiao School of Computer Science and Engineering Sun Yat-sen University Research Institute of Sun Yat-sen University in Shenzhen Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In this paper,the concept of Zhang equivalency(ZE) and equality-type ZE are *** the basis of equalitytype ZE,we introduce the inequality-type ZE of great-than-or-equal-to(GTOET) sign and thus propose the order-1,order-2,and order-3 general formulas of the inequality-type ZE of GTOET ***,we investigate the inequality-type ZE of GTOET sign in three different and appealing situations,including matrix-vector situation,matrix situation,and integral ***,the corresponding formulas are *** distance between a certain object and an obstacle can be considered as the point-to-point distance,and thus the obstacle avoidance scheme is described as an *** by that thought,we apply the inequality-type ZE of GTOET sign to the matrix-form obstacle avoidance.

关键词： Zhang equivalency Great-than-or-equal-to(GTOET) sign Inequalities Obstacle avoidance

来源：评论

学校读者我要写书评

暂无评论

Salient Foreground-Aware Network for Person Search 16th

Salient Foreground-Aware Network for Person Search

引用

16th Chinese Conference on Biometric Recognition, CCBR 2022

作者： Chen, Hongxu Zhang, Quan Lai, Jianhuang The School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China The Guangdong Key Laboratory of Information Security Technology Guangzhou510006 China The Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangzhou510006 China

ISBN: (纸本)9783031202322

Person search aims to simultaneously localize and identify a query person from realistic and uncropped images, which consists of person detection and re-identification. In existing methods, the extracted features come from the low-quality proposals generated by the structure like Region Proposal Network (RPN), and convolution is used to learn local features in the process of extracting features while the receptive field cannot grasp the global structural information. We propose an end-to-end network embedded with our Salient Foreground-Aware Module (SFAM). Self-attention mechanism in SFAM allows for better capture of global information. Our network incorporates our embedding method for person detection and person re-identification, which can effectively optimize the process of extracting features and improve feature expression capabilities. We merge the above modules into our Salient Foreground-Aware Network (SFAN). Extensive experiments have shown that our SFAN significantly improves the performance of end-to-end models with acceptable time-consuming and achieves state-of-the-art results. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Accurate Prediction of Knee Joint Angles Using a Hybrid CNN-LSTM-Attention Network from Surface Electromyography

Accurate Prediction of Knee Joint Angles Using a Hybrid CNN-...

引用

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Wang, Zhuo Chen, Hui Yang, Fangliang Wang, Xiangyang Wu, Xinyu Chen, Chunjie Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen518055 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9781665481090

In various fields such as robotics, rehabilitation, biomechanics, human-machine interfaces, and clinical research, human motion prediction has extensive applications. A hybrid networks model based on Convolutional Neural Network-Long Short-Term Memory-Attention (CNN-LSTM-Attention) was employed in this paper to extract features from the high-dimensional space and time series of surface electromyography (sEMG) data for continuous prediction of knee angles. Five able-bodied subjects participated in the study, walking at a self-selected pace while six surface electromyography (sEMG) signals from muscles involved in knee flexion and extension, along with knee angles, were synchronously recorded. The performance was assessed using the root mean square error (RMSE), Pearson Correlation Coefficient (r), and coefficient of determination (R2) between estimated and measured knee joint angles. Compared to the CNN, LSTM, and CNN-LSTM algorithms, the adopted method estimated knee angles more accurately, achieving an average RMSE, ρ, and R2 of 3.09± 0.90,\ 0.9911 ± 0.0052, and 0.9817± 0.0108, respectively. As the advance time increased, the accuracy of knee joint angle estimation decreased, particularly when the advance time reached 100 ms, at which point the RMSE is 4.83 degress. In addition, the computing time of the prediction model was less than 1 ms, which was shorter than the advance time 100 ms it could predict, thereby facilitating real-time computation in practical environments. Compared to previous studies, the proposed method excelled at extracting features directly from raw signals, avoiding the need for handcrafted feature extraction. Consequently, the model effectively achieved continuous and accurate predictions of joint motion angles and demonstrated potential to reduce latency in the human-machine interface. © 2024 IEEE.

关键词： Clinical research

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

Confidence-guided Source Label Refinement and Class-aware Pseudo-Label Thresholding for Domain-Adaptive Semantic Segmentation

Confidence-guided Source Label Refinement and Class-aware Ps...

引用

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

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

arXiv

引用

arXiv 2024年

作者： Xu, Angchi 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 Guangdong Province Key Laboratory of Information Security Technology Guangzhou China

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. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment

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

CLIP-RestoreX: Restore Image Structure and Perception in Exposure Correction 39

CLIP-RestoreX: Restore Image Structure and Perception in Exp...

引用

39th Annual AAAI Conference on Artificial intelligence, AAAI 2025

作者： Huang, Xiang Zhang, Qing Hu, Jian-Fang 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

ISBN: (纸本)157735897X

Exposure correction aims to adjust the exposure of an under- and over-exposed image to enhance its overall visual quality. The core challenge of this task lies in that it requires to faithfully restore both the structure and perception information. In this work, we present a novel exposure correction method, referred to as CLIP-RestoreX, that leverages structural and perceptual priors from CLIP to tackle exposure correction. Specifically, we in CLIP-RestoreX propose to perform exposure correction by aligning CLIP-based structural and perceptual feature of the impaired image with its ground-truth image. To better restore the damaged structural information and perceptual information, we further design a frequency-domain based feature enhancement diffusion model, where we utilize the globality of Fourier transform to help reveal potential the relationship within the features. We conduct extensive experiments on several benchmark datasets. The results demonstrate that the proposed CLIP-RestoreX outperforms state-of-the-art exposure correction methods. Copyright © 2025, Association for the Advancement of Artificial intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ViT-based Terrain Recognition System for wearable soft exosuit

引用

Biomimetic intelligence & Robotics 2023年第1期3卷 57-64页

作者： Fangliang Yang Chunjie Chen Zhuo Wang Hui Chen Yao Liu Gang Li Xinyu Wua Shenzhen Institute of Advanced Technology Chinese Academy of SciencesShenzhen 518055China Shenzhen College of Advanced Technology University of Chinese Academy of SciencesShenzhen 518055China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China Guangdong-Hong Kong-Macao Joint Laboratory of Human–Machine Intelligence-Synergy Systems Shenzhen 518055China SIASUN Robot and Automation CO. LtdShenyang 110169China

Terrain classification and force assistance strategies in complex environments have always piqued the interest of many *** wearable soft exosuits,inaccurate terrain recognition can easily introduce undesired assist forces that can easily injure the *** of these problems,we introduced a depth camera into the exosuit system,perform classification of terrain based on a Vision Transformer(ViT),and optimized the control algorithm,which is known as a ViT-Based Terrain Recognition System(TTRS).First,we used the Transformer algorithm to achieve a considerable classification effect in terrain *** also introduced terrain recognition as prior knowledge into the force assistance strategy of the exosuit,providing different force assistance to the exosuit in different ***,we performed human experiments with seven able-bodied people(six males and one female).The promising results demonstrate that our classification accuracy can reach 99.2%under six different terrains and that it can smoothly switch the force–assist curve in different terrains to better adapt to the complex terrain and improve the walking *** aforementioned terrain recognition algorithms and force–assist strategies may positively influence the study of soft exosuit,powered prostheses,and orthotics.

关键词： Vision Transformer(ViT) Depth camera Wearable soft exosuit Force assistance strategy Terrain recognition

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：