检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Feng, Jiawei Wu, Ancong 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 Key Laboratory of Information Security Technology China

Due to the modality gap between visible and infrared images with high visual ambiguity, learning diverse modality-shared semantic concepts for visible-infrared person re-identification (VI-ReID) remains a challenging problem. Body shape is one of the significant modality-shared cues for VI-ReID. To dig more diverse modality-shared cues, we expect that erasing body-shape-related semantic concepts in the learned features can force the ReID model to extract more and other modality-shared features for identification. To this end, we propose shape-erased feature learning paradigm that decorrelates modality-shared features in two orthogonal subspaces. Jointly learning shape-related feature in one subspace and shape-erased features in the orthogonal complement achieves a conditional mutual information maximization between shape-erased feature and identity discarding body shape information, thus enhancing the diversity of the learned representation explicitly. Extensive experiments on SYSU-MM01, RegDB, and HITSZ-VCM datasets demonstrate the effectiveness of our method.1 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

Shape-Erased Feature Learning for Visible-Infrared Person Re-Identification

Shape-Erased Feature Learning for Visible-Infrared Person Re...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Jiawei Feng Ancong Wu 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 Key Laboratory of Information Security Technology China

关键词：

来源：评论

学校读者我要写书评

暂无评论

Variation of sEMG with Muscle Fatigue for Lower Limb Stroke Patient During Walking

Variation of sEMG with Muscle Fatigue for Lower Limb Stroke ...

引用

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Shang, Wenze Huang, Ruisen Liao, Wei-Hsin Wu, Xinyu Gao, Fei Southern University of Science and Technology Shenzhen518005 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen518055 China The Chinese University of Hong Kong Department of Mechanical and Automation Engineering Hong Kong999077 Hong Kong

ISBN: (纸本)9781665481090

SEMG signal is widely used and explored in control strategies of powered assistive human-robot interaction systems due to its non-invasive nature and ability to estimate motion intention well. However, prolonged use of the sEMG-based systems leads to muscle fatigue, contributing to unstable sEMG signals and regarding the performance of sEMG-based control strategies. In this study, three subjects, including two healthy subjects and one stroke subject, participated in our experiment, and the time domain, frequency domain, and complex features extracted from their sEMG signals were utilized to evaluate muscle fatigue. The results indicate that sEMG from the stroke side of the stroke subject contains more non-linear and chaotic parts, and the statistical differences between different trials are more significant, indicating that stroke has a more significant impact on the stroke side of the stroke subject. This study suggests that RMS in the stroke side of stroke subjects is less than that in others, whereas FuzzyEn in the stroke side of stroke subjects is greater than that in others, indicating that stroke leads to different motion patterns and more susceptibility to muscle fatigue. © 2024 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Genetic and phenotypic relationships between coronary atherosclerotic heart disease and electrocardiographic traits

Genetic and phenotypic relationships between coronary athero...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Wang, Xinfeng Zhang, Haoyang Xiu, Xuehao Qi, Mengling Yang, Yuedong Zhao, Huiying Sun Yat-sen University Key Laboratory of Machine Intelligence and Advanced Computing of Moe School of Computer Science and Engineering Guangzhou China Sun Yat-sen Memorial Hospital Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation Department of Medical Research Center Guangzhou China

ISBN: (纸本)9781665468190

Observational studies have revealed that Coronary Atherosclerotic Heart Disease (CAHD) is associated with abnormal electrocardiogram (ECG) traits. However, it remains unclear whether there are genetic correlations between ECG and CAHD. Here, we explored genetic correlations and putative causal relationships between CAHD and ECG by performing Mendelian randomization (MR) and Polygenic risk score (PRS) analyses on the summary statistics from a large-scale genome-wide association study (GWAS) for CAHD (FinnGen: Ncase 23363, Ncontrol 187840) and ECG traits (UK Biobank: Ncase=1137, Ncontrol=40823). Results showed a causal genetic relationship between CAHD and six ECG traits in the lead V6. These ECG traits combining with age and gender have predicted CAHD risk with an AUC of 0.76. Further summary data-based Mendelian randomization (SMR) analysis identified 11 risk genes associated with the causality between CAHD and ECG. Thus, the revealed putative causal effects of CAHD on ECG traits provide genetic evidence to support the importance of monitoring CAHD risk through the ECG. © 2022 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Dynamic Residual Classifier for Class Incremental Learning

Dynamic Residual Classifier for Class Incremental Learning

引用

International Conference on Computer Vision (ICCV)

作者： Xiuwei Chen Xiaobin Chang School of Artificial Intelligence Sun Yat-sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou P.R.China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

The rehearsal strategy is widely used to alleviate the catastrophic forgetting problem in class incremental learning (CIL) by preserving limited exemplars from previous tasks. With imbalanced sample numbers between old and new classes, the classifier learning can be biased. Existing CIL methods exploit the long-tailed (LT) recognition techniques, e.g., the adjusted losses and the data re-sampling methods, to handle the data imbalance issue within each increment task. In this work, the dynamic nature of data imbalance in CIL is shown and a novel Dynamic Residual Classifier (DRC) is proposed to handle this challenging scenario. Specifically, DRC is built upon a recent advance residual classifier with the branch layer merging to handle the model-growing problem. Moreover, DRC is compatible with different CIL pipelines and substantially improves them. Combining DRC with the model adaptation and fusion (MAF) pipeline, this method achieves state-of-the-art results on both the conventional CIL and the LT-CIL benchmarks. Extensive experiments are also conducted for a detailed analysis. The code is publicly available 1 .

关键词：

来源：评论

学校读者我要写书评

暂无评论

MaintaAvatar: A Maintainable Avatar Based on Neural Radiance Fields by Continual Learning 39

MaintaAvatar: A Maintainable Avatar Based on Neural Radiance...

引用

39th Annual AAAI Conference on Artificial intelligence, AAAI 2025

作者： Gu, Shengbo Qiu, Yu-Kun Tang, Yu-Ming Wu, Ancong Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Peng Cheng Laboratory Shenzhen China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (纸本)157735897X

The generation of a virtual digital avatar is a crucial research topic in the field of computer vision. Many existing works utilize Neural Radiance Fields (NeRF) to address this issue and have achieved impressive results. However, previous works assume the images of the training person are available and fixed while the appearances and poses of a subject could constantly change and increase in real-world scenarios. How to update the human avatar but also maintain the ability to render the old appearance of the person is a practical challenge. One trivial solution is to combine the existing virtual avatar models based on NeRF with continual learning methods. However, there are some critical issues in this approach: learning new appearances and poses can cause the model to forget past information, which in turn leads to a degradation in the rendering quality of past appearances, especially color bleeding issues, and incorrect human body poses. In this work, we propose a maintainable avatar (MaintaAvatar) based on neural radiance fields by continual learning, which resolves the issues by utilizing a Global-Local Joint Storage Module and a Pose Distillation Module. Overall, our model requires only limited data collection to quickly fine-tune the model while avoiding catastrophic forgetting, thus achieving a maintainable virtual avatar. The experimental results validate the effectiveness of our MaintaAvatar model. © 2025, Association for the Advancement of Artificial intelligence (***). All rights reserved.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

MaintaAvatar: A Maintainable Avatar Based on Neural Radiance Fields by Continual Learning

arXiv

引用

arXiv 2025年

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Rotation Exploration Transformer for Aerial Person Re-identification

Rotation Exploration Transformer for Aerial Person Re-identi...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Lei Wang Quan Zhang Junyang Qiu Jianhuang Lai 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 Pazhou Lab (HuangPu) Guangzhou China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Aerial person re-identification (AReID) focuses on accurately matching target person images within a UAV camera network. Challenges arise due to the broad field of view and arbitrary movement of UAVs, leading to foreground target rotation and background style variation. Existing AReID methods have provided limited solutions for the former, while the latter remains largely unexplored. This paper propose a Rotation Exploration Vision Transformer (RoExViT) to tackle the aforementioned dual challenges. Specifically, we design Multiple Rotation Tokens (MRT) to explore diverse rotational representations at the feature level, addressing foreground target rotation. To handle background style variation, we propose Cross-Camera Similarity (CCS) loss to effectively minimize the view gap among different cameras. Furthermore, we propose Iteratively Adaptive Batch Construction (IABC) strategy to mitigate overfitting on small datasets. Extensive experiments show that our method outperforms the state-of-the-art methods on PRAI-1581 and UAV-Human while also exhibting outstanding performance on Market1501.

关键词： Computer vision Transformers Cameras Autonomous aerial vehicles Identification of persons

来源：评论

学校读者我要写书评

暂无评论

Hard-normal Example-aware Template Mutual Matching for Industrial Anomaly Detection

arXiv

引用

arXiv 2023年

作者： Chen, Zixuan Xie, Xiaohua Yang, Lingxiao Lai, Jian-Huang School of Computer Science and Engineering Sun Yat-sen University Guangdong Guangzhou510006 China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Anomaly detectors are widely used in industrial manufacturing to detect and localize unknown defects in query images. These detectors are trained on anomaly-free samples and have successfully distinguished anomalies from most normal samples. However, hard-normal examples are scattered and far apart from most normal samples, and thus they are often mistaken for anomalies by existing methods. To address this issue, we propose Hard-normal Example-aware Template Mutual Matching (HETMM), an efficient framework to build a robust prototype-based decision boundary. Specifically, HETMM employs the proposed Affine-invariant Template Mutual Matching (ATMM) to mitigate the affection brought by the affine transformations and easy-normal examples. By mutually matching the pixel-level prototypes within the patch-level search spaces between query and template set, ATMM can accurately distinguish between hard-normal examples and anomalies, achieving low false-positive and missed-detection rates. In addition, we also propose PTS to compress the original template set for speed-up. PTS selects cluster centres and hard-normal examples to preserve the original decision boundary, allowing this tiny set to achieve comparable performance to the original one. Extensive experiments demonstrate that HETMM outperforms state-of-the-art methods, while using a 60-sheet tiny set can achieve competitive performance and real-time inference speed (around 26.1 FPS) on a Quadro 8000 RTX GPU. HETMM is training-free and can be hot-updated by directly inserting novel samples into the template set, which can promptly address some incremental learning issues in industrial manufacturing. Copyright © 2023, The Authors. All rights reserved.

关键词： Affine transforms

来源：评论

学校读者我要写书评

暂无评论

Inserting anybody in diffusion models via celeb basis 23

Inserting anybody in diffusion models via celeb basis

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Ge Yuan Xiaodong Cun Yong Zhang Maomao Li Chenyang Qi Xintao Wang Ying Shan Huicheng Zheng School of Computer Science and Engineering Sun Yat-sen University and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China and Guangdong Key Laboratory of Information Security Technology and Tencent AI Lab Tencent AI Lab The Hong Kong University of Science and Technology School of Computer Science and Engineering Sun Yat-sen University and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China and Guangdong Key Laboratory of Information Security Technology

Exquisite demand exists for customizing the pretrained large text-to-image model, e.g. Stable Diffusion, to generate innovative concepts, such as the users themselves. However, the newly-added concept from previous customization methods often shows weaker combination abilities than the original ones even given several images during training. We thus propose a new personalization method that allows for the seamless integration of a unique individual into the pre-trained diffusion model using just one facial photograph and only 1024 learnable parameters under 3 minutes. So we can effortlessly generate stunning images of this person in any pose or position, interacting with anyone and doing anything imaginable from text prompts. To achieve this, we first analyze and build a well-defined celeb basis from the embedding space of the pre-trained large text encoder. Then, given one facial photo as the target identity, we generate its own embedding by optimizing the weight of this basis and locking all other parameters. Empowered by the proposed celeb basis, the new identity in our customized model showcases a better concept combination ability than previous personalization methods. Besides, our model can also learn several new identities at once and interact with each other where the previous customization model fails to. Project page is at: http://***. Code is at: https://***/ygtxr1997/CelebBasis.

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：