检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Tang, Song Yan, Shaxu Qi, Xiaozhi Gao, Jianxin Ye, Mao Zhang, Jianwei Zhu, Xiatian IMI Group School of Health Sciences and Engineering University of Shanghai for Science and Technology Shanghai China TAMS Group Department of Informatics Universität Hamburg Hamburg Germany School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Surrey Institute for People-Centred Artificial Intelligence Centre for Vision Speech and Signal Processing University of Surrey Guildford United Kingdom Shenzhen Key Laboratory of Minimally Invasive Surgical Robotics and System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China

Few-shot Semantic Segmentation (FSS) aims to adapt a pretrained model to new classes with as few as a single labelled training sample per class. Despite the prototype based approaches have achieved substantial success, existing models are limited to the imaging scenarios with considerably distinct objects and not highly complex background, e.g., natural images. This makes such models suboptimal for medical imaging with both conditions invalid. To address this problem, we propose a novel Detail Self-refined Prototype Network (DSPNet) to constructing high-fidelity prototypes representing the object foreground and the background more comprehensively. Specifically, to construct global semantics while maintaining the captured detail semantics, we learn the foreground prototypes by modelling the multi-modal structures with clustering and then fusing each in a channel-wise manner. Considering that the background often has no apparent semantic relation in the spatial dimensions, we integrate channel-specific structural information under sparse channel-aware regulation. Extensive experiments on three challenging medical image benchmarks show the superiority of DSPNet over previous state-of-the-art methods. The code and data are available at https://***/tntek/DSPNet. Copyright © 2024, 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

Attention-Driven Dynamic Graph Convolutional Network for Multi-label Image Recognition 16th

Attention-Driven Dynamic Graph Convolutional Network for Mul...

引用

16th European Conference on computer vision, ECCV 2020

作者： Ye, Jin He, Junjun Peng, Xiaojiang Wu, Wenhao Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China School of Biomedical Engineering the Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9783030585884

Recent studies often exploit Graph Convolutional Network (GCN) to model label dependencies to improve recognition accuracy for multi-label image recognition. However, constructing a graph by counting the label co-occurrence possibilities of the training data may degrade model generalizability, especially when there exist occasional co-occurrence objects in test images. Our goal is to eliminate such bias and enhance the robustness of the learnt features. To this end, we propose an Attention-Driven Dynamic Graph Convolutional Network (ADD-GCN) to dynamically generate a specific graph for each image. ADD-GCN adopts a Dynamic Graph Convolutional Network (D-GCN) to model the relation of content-aware category representations that are generated by a Semantic Attention Module (SAM). Extensive experiments on public multi-label benchmarks demonstrate the effectiveness of our method, which achieves mAPs of 85.2%, 96.0%, and 95.5% on MS-COCO, VOC2007, and VOC2012, respectively, and outperforms current state-of-the-art methods with a clear margin. © 2020, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Multi-Branch Network with High-Frequency Enhancement for Image Dehazing

SSRN

引用

SSRN 2023年

作者： Sun, Hang Luo, Zhiming Ren, Dong Du, Bo Chang, Laibin Wan, Jun Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges University Yichang443002 China College of Computer and Information Technology China Three Gorges University Yichang443002 China School of Computer Science Wuhan University Wuhan430072 China Shenzhen University China

Recently, CycleGAN-based methods have been widely applied to the unsupervised image dehazing and achieved significant results. However, most existing CycleGAN-based methods ignore that the input of the generator contains two different distributions of data which can often lead to confusion in the learning process of the generator, consequently limiting the final dehazing performance. Moreover, reconstructing clear images through model architecture design and loss functions is an indirect constraint, making it difficult to compensate for the missing high-frequency information, such as textures and structures in the extracted features from hazy images. To address these issues, in this paper, we propose an Unsupervised Multi-Branch with High-Frequency Enhancement Network (UME-Net) which contain an Multi-Branch Dehazing Network (MBDN) and a High-Frequency Components Enhancement Module (HFEM). Specifically, MBDN constructs a single unsupervised dehazing network with Shared Encoding Module (SEM) and Multi-Branch Decoding Module (MDM). SEM enhance the consistency of feature representation and MDM effectively addresses the confusion during the generator learning process in CycleGAN-based methods. Furthermore, based on a key observation that hazy images and their corresponding clear images exhibit only subtle differences in high-frequency information, the HFEM is designed to compensates for the missing high-frequency information in the network which further enhances the reconstruction capability of the UME-Net for restore edge and texture information in obscured by dense haze. Experimental results on challenging benchmark datasets demonstrate the superiority of our UME-Net over SOTA unsupervised image dehazing methods. The source code is available at https://***/thislzm/UME-Net. © 2023, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Ensemble diverse hypotheses and knowledge distillation for unsupervised cross-subject adaptation

arXiv

引用

arXiv 2022年

作者： Zhang, Kuangen Chen, Jiahong Wang, Jing Chen, Xinxing Leng, Yuquan de Silva, Clarence W. Fu, Chenglong Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems Department of Mechanical and Energy Engineering Southern University of Science and Technology Shenzhen518055 China Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and Technology Shenzhen518055 China Department of Mechanical Engineering The University of British Columbia VancouverBC Canada Department of Electrical and Computer Engineering The University of British Columbia VancouverBC Canada

Recognizing human locomotion intent and activities is important for controlling the wearable robots while walking in complex environments. However, human-robot interface signals are usually user-dependent, which causes that the classifier trained on source subjects performs poorly on new subjects. To address this issue, this paper designs the ensemble diverse hypotheses and knowledge distillation (EDHKD) method to realize unsupervised cross-subject adaptation. EDH mitigates the divergence between labeled data of source subjects and unlabeled data of target subjects to accurately classify the locomotion modes of target subjects without labeling data. Compared to previous domain adaptation methods based on the single learner, which may only learn a subset of features from input signals, EDH can learn di- Copyright © 2022, The Authors. All rights reserved.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Provably Convergent Federated Trilevel Learning

arXiv

引用

arXiv 2023年

作者： Jiao, Yang Yang, Kai Wu, Tiancheng Jian, Chengtao Huang, Jianwei Department of Computer Science and Technology Tongji University China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University China Shanghai Research Institute for Intelligent Autonomous Systems China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Trilevel learning, also called trilevel optimization (TLO), has been recognized as a powerful modelling tool for hierarchical decision process and widely applied in many machine learning applications, such as robust neural architecture search, hyperparameter optimization, and domain adaptation. Tackling TLO problems has presented a great challenge due to their nested decision-making structure. In addition, existing works on TLO face the following key challenges: 1) they all focus on the non-distributed setting, which may lead to privacy breach;2) they do not offer any non-asymptotic convergence analysis which characterizes how fast an algorithm converges. To address the aforementioned challenges, this paper proposes an asynchronous federated trilevel optimization method to solve TLO problems. The proposed method utilizes µ-cuts to construct a hyper-polyhedral approximation for the TLO problem and solve it in an asynchronous manner. We demonstrate that the proposed µ-cuts are applicable to not only convex functions but also a wide range of non-convex functions that meet the µ-weakly convex assumption. Furthermore, we theoretically analyze the non-asymptotic convergence rate for the proposed method by showing its iteration complexity to obtain ϵ-stationary point is upper bounded by (Formula Presented). Extensive experiments on real-world datasets have been conducted to elucidate the superiority of the proposed method, e.g., it has a faster convergence rate with a maximum acceleration of approximately 80%. Copyright © 2023, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Style Transfer Enabled Sim2Real Framework for Efficient Learning of Robotic Ultrasound Image Analysis Using Simulated Data

arXiv

引用

arXiv 2023年

作者： Li, keyu Mao, Xinyu Ye, Chengwei Li, Ang Xu, Yangxin Meng, Max Q.-H. The Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong Shenzhen Key Laboratory of Robotics Perception and Intelligence The Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China The Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong The Department of Electrical and Computer Engineering The University of Alberta Canada

Robotic ultrasound (US) systems have shown great potential to make US examinations easier and more accurate. Recently, various machine learning techniques have been proposed to realize automatic US image interpretation for robotic US acquisition tasks. However, obtaining large amounts of real US imaging data for training is usually expensive or even unfeasible in some clinical applications. An alternative is to build a simulator to generate synthetic US data for training, but the differences between simulated and real US images may result in poor model performance. This work presents a Sim2Real framework to efficiently learn robotic US image analysis tasks based only on simulated data for real-world deployment. A style transfer module is proposed based on unsupervised contrastive learning and used as a preprocessing step to convert the real US images into the simulation style. Thereafter, a task-relevant model is designed to combine CNNs with vision transformers to generate the task-dependent prediction with improved generalization ability. We demonstrate the effectiveness of our method in an image regression task to predict the probe position based on US images in robotic transesophageal echocardiography (TEE). Our results show that using only simulated US data and a small amount of unlabelled real data for training, our method can achieve comparable performance to semi-supervised and fully supervised learning methods. Moreover, the effectiveness of our previously proposed CT-based US image simulation method is also indirectly confirmed. Copyright © 2023, The Authors. All rights reserved.

关键词： Echocardiography

来源：评论

学校读者我要写书评

暂无评论

LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents

arXiv

引用

arXiv 2025年

作者： Chen, Boyu Yue, Zhengrong Chen, Siran Wang, Zikang Liu, Yang Li, Peng Wang, Yali Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Tsinghua University Beijing China Dept. of Comp. Sci. & Tech. Institute for AI Tsinghua University Beijing China Shanghai Artificial Intelligence Laboratory China Shanghai Jiao Tong University China

Existing Multimodal Large Language Models (MLLMs) encounter significant challenges in modeling the temporal context within long videos. Currently, mainstream Agent-based methods use external tools (e.g., search engine, memory banks, OCR, retrieval models) to assist a single MLLM in answering long video questions. Despite such tool-based support, a solitary MLLM still offers only a partial understanding of long videos, resulting in limited performance. In order to better address long video tasks, we introduce LVAgent, the first framework enabling multi-round dynamic collaboration of MLLM agents in long video understanding. Our methodology consists of four key steps: 1) Selection: We pre-select appropriate agents from the model library to form optimal agent teams based on different tasks. 2) Perception: We design an effective retrieval scheme for long videos, improving the coverage of critical temporal segments while maintaining computational efficiency. 3) Action: Agents answer long video-related questions and exchange reasons. 4) Reflection: We evaluate each agent’s performance in each round of discussion and optimize the agent team for dynamic collaboration. The agents iteratively refine their answers by multi-round dynamical collaboration of MLLM agents. LVAgent is the first agent system method that outperforms all closed-source models (including GPT-4o) and open-source models (including InternVL-2.5 and Qwen2-VL) in the long video understanding tasks. Our LVAgent achieves an accuracy of 80% on four mainstream long video understanding tasks. Notably, on the LongVideoBench dataset, LVAgent improves accuracy by up to 14.3% compared with SOTA. © 2025, CC BY-NC-SA.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

ReactFace: Online Multiple Appropriate Facial Reaction Generation in Dyadic Interactions

arXiv

引用

arXiv 2023年

作者： Luo, Cheng Song, Siyang Xie, Weicheng Spitale, Micol Ge, Zongyuan Shen, Linlin Gunes, Hatice Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China Department of Computer Science University of Nottingham Ningbo China Ningbo315100 China Computer Sciences University of Exeter ExeterEX4 4PY United Kingdom Department of Computer Science and Technology University of Cambridge CambridgeCB3 0FT United Kingdom Airdoc-Monash Research Centre Monash University Faculty of IT Monash University Melbourne Australia

In dyadic interaction, predicting the listener’s facial reactions is challenging as different reactions could be appropriate in response to the same speaker’s behaviour. Previous approaches predominantly treated this task as an interpolation or fitting problem, emphasizing deterministic outcomes but ignoring the diversity and uncertainty of human facial reactions. Furthermore, these methods often failed to model short-range and long-range dependencies within the interaction context, leading to issues in the synchrony and appropriateness of the generated facial reactions. To address these limitations, this paper reformulates the task as an extrapolation or prediction problem, and proposes an novel framework (called ReactFace) to generate multiple different but appropriate facial reactions from a speaker behaviour rather than merely replicating the corresponding listener facial behaviours. Our ReactFace generates multiple different but appropriate photo-realistic human facial reactions by: (i) learning an appropriate facial reaction distribution representing multiple different but appropriate facial reactions;and (ii) synchronizing the generated facial reactions with the speaker verbal and non-verbal behaviours at each time stamp, resulting in realistic 2D facial reaction sequences. Experimental results demonstrate the effectiveness of our approach in generating multiple diverse, synchronized, and appropriate facial reactions from each speaker’s behaviour. The quality of the generated facial reactions is intimately tied to the speaker’s speech and facial expressions, achieved through our novel speaker-listener interaction modules. Our code is made publicly available at https://***/lingjivoo/ReactFace. Copyright © 2023, The Authors. All rights reserved.

关键词： Extrapolation

来源：评论

学校读者我要写书评

暂无评论

Blueprint Separable Residual Network for Efficient Image Super-Resolution

arXiv

引用

arXiv 2022年

作者： Li, Zheyuan Liu, Yingqi Chen, Xiangyu Cai, Haoming Gu, Jinjin Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China University of Macau China Shanghai AI Laboratory Shanghai China The University of Sydney Australia

Recent advances in single image super-resolution (SISR) have achieved extraordinary performance, but the computational cost is too heavy to apply in edge devices. To alleviate this problem, many novel and effective solutions have been proposed. Convolutional neural network (CNN) with the attention mechanism has attracted increasing attention due to its efficiency and effectiveness. However, there is still redundancy in the convolution operation. In this paper, we propose Blueprint Separable Residual Network (BSRN) containing two efficient designs. One is the usage of blueprint separable convolution (BSConv), which takes place of the redundant convolution operation. The other is to enhance the model ability by introducing more effective attention modules. The experimental results show that BSRN achieves state-of-the-art performance among existing efficient SR methods. Moreover, a smaller variant of our model BSRN-S won the first place in model complexity track of NTIRE 2022 Efficient SR Challenge. The code is available at https://***/xiaom233/BSRN. Copyright © 2022, The Authors. All rights reserved.

关键词： Blueprints

来源：评论

学校读者我要写书评

暂无评论

SATO: Stable Text-to-Motion Framework

arXiv

引用

arXiv 2024年

作者： Chen, Wenshuo Xiao, Hongru Zhang, Erhang Hu, Lijie Wang, Lei Liu, Mengyuan Chen, Chen Shandong University Qingdao China Tongji University Shanghai China King Abdullah University of Science and Technology Jeddah Saudi Arabia Australian National University & Data61/CSIRO Canberra Australia State Key Laboratory of General Artificial Intelligence Peking University Shenzhen Graduate School Shenzhen China Center for Research in Computer Vision University of Central Florida Orlando United States

Is the Text to Motion model robust? Recent advancements in Text to Motion models primarily stem from more accurate predictions of specific actions. However, the text modality typically relies solely on pre-trained Contrastive Language-Image Pretraining (CLIP) models. Our research has uncovered a significant issue with the text-to-motion model: its predictions often exhibit inconsistent outputs, resulting in vastly different or even incorrect poses when presented with semantically similar or identical text inputs. In this paper, we undertake an analysis to elucidate the underlying causes of this instability, establishing a clear link between the unpredictability of model outputs and the erratic attention patterns of the text encoder module. Consequently, we introduce a formal framework aimed at addressing this issue, which we term the Stable Text-to-Motion Framework (SATO). SATO consists of three modules, each dedicated to stable attention, stable prediction, and maintaining a balance between accuracy and robustness trade-off. We present a methodology for constructing an SATO that satisfies the stability of attention and prediction. To verify the stability of the model, we introduced a new textual synonym perturbation dataset based on HumanML3D and KIT-ML. Results show that SATO is significantly more stable against synonyms and other slight perturbations while keeping its high accuracy performance. Codes and models are released at https://***/sato-team/Stable-Text-to-Motion-Framework Copyright © 2024, 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

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：