检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhang, Ling Ma, Yidong Jiang, Zhi He, Weilei Bao, Zhongyun Fu, Gang Xu, Wenju Xiao, Chunxia School of Computer Science and Technology Hubei Key Laboratory of Intelligent Information Processing and Realtime Industrial Systems Wuhan University of Science and Technology Wuhan China School of Computer Science Wuhan University Wuhan China Department of Computing Hong Kong Polytechnic University Hong Kong Amazon Palo Alto United States

ISBN: (纸本)9798400706868

Recently, learning-based methods have made significant progress for image specular highlight removal. However, many of these approaches treat all the image pixels uniformly, overlooking the negative impact of invalid pixels on feature reconstruction. This oversight often leads to undesirable outcomes, such as color distortion or residual highlights. In this paper, we propose a novel image specular highlight removal network called HighlightRNet, which utilizes valid pixels as references to reconstruct the highlight-free image. To achieve this, we introduce a context-aware fusion block (CFBlock) that aggregates information in four directions, effectively capturing global contextual information. Additionally, we introduce a location-aware feature transformation module (LFTModule) to adaptively learn the valid pixels for feature reconstruction, thereby avoiding information errors caused by invalid pixels. With these modules, our method can produce high-quality highlight-free results without color distortion and highlight residual. Furthermore, we develop a multiple light image-capturing system to construct a large-scale highlight dataset called NSH, which exhibits minimal misalignment in image pairs and minimal brightness variation in non-highlight regions. Experimental results on various datasets demonstrate the superiority of our method over state-of-the-art methods, both qualitatively and quantitatively. © 2024 ACM.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Memory-Augmented Transformer for Efficient End-to-End Video Grounding

Memory-Augmented Transformer for Efficient End-to-End Video ...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yuanwu Xu Mohan Chen Yuejie Zhang Rui Feng Tao Zhang Shang Gao School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University School of Information Management and Engineering Shanghai Key Laboratory of Financial Information Technology Shanghai University of Finance and Economics School of Information Technology Deakin University

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Video grounding aims to localize a specific segment corresponding to a text query in an untrimmed video. Due to the tremendous computational cost required to process the video frames, the de facto paradigm of video grounding is to extract video features using pretrained video encoders. The parameters of the video encoders are fixed during training, which limits the performance of the localization model. To solve this problem, we propose a Memory-Augmented Transformer (MAT) model. Specifically, each video is split into non-overlapping clips, and our MAT processes videos in a clip-by-clip manner while caching video features into FIFO cached memory queues. By enabling early return, our MAT outperforms previous methods with only less than 60% frames seen. Extensive experimental results on three public benchmark datasets demonstrate that our MAT can achieve competitive performance while being much more efficient than currently prevailing two-stage methods. Code is available at https://***/xuyw1997/MAT.

关键词： Training Location awareness Codes Grounding Computational modeling Streaming media Predictive models

来源：评论

学校读者我要写书评

暂无评论

Food computing for Nutrition and Health

Food Computing for Nutrition and Health

引用

International Conference on Data Engineering Workshops

作者： Shuqiang Jiang Institute of Computing Technology Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Beijing University of Chinese Academy of Sciences Beijing

ISBN: (数字)9798350384031

ISBN: (纸本)9798350384048

Dietary intake is the main source of human nutrition and thus an important material foundation for maintaining human health. Food computing applies computational approaches to intelligently obtain dietary categories, ingredients, and nutrient intake from dietary data, and then provides dietary recommendations to users based on various dietary factors. Therefore, it can achieve intelligent dietary management to assist in solving human health issues. For its significant impact on human health, it has received more attention from both academia and industry, and has made rapid development, especially with the booming Artificial Intelligence (AI). This talk will first introduce the definition, methods, tasks and applications of food computing. Then we will discuss its various tasks, ranging from vision-based multi-granularity food analysis, multimodal recipe analysis, food knowledge graph construction and dietary recommendation. Finally, we will point out future research directions on food computing, such as large food language/multimodal models and the emerging interdisciplinary field AI4Food from the synergy between AI and food science. We expect that this talk will provide the researchers with a more comprehensive understanding of the field, and provide perspectives for the next wave of development in this rapidly growing field.

关键词： Industries Conferences Computational modeling Knowledge graphs Data engineering Distance measurement Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

An Efficient Color and Geometric Feature Fusion Module for 6D Object Pose Estiamtion 12

An Efficient Color and Geometric Feature Fusion Module for 6...

引用

12th International Conference on CYBER technology in Automation, Control, and intelligent Systems, CYBER 2022

作者： Li, Jiangeng Liu, Hong Huang, Gao Zuo, Guoyu Faculty of Information Technology Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Computing Intelligence and Intelligent Systems Beijing100124 China Faculty of Information Beijing University of Technology Beijing100124 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing100081 China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

6D pose estimation is widely used in robot tasks such as sorting and grasping. RGB-D-based methods have recently attained brilliant success, but they are still susceptible to heavy occlusion. Our critical insight is that color and geometry information in RGBD images are two complementary data, and the crux of the pose estimation problem under occlusion is fully leveraging them. Towards this end, we propose a new color and geometry feature fusion module that can efficiently leverage two complementary data sources from RGB-D images. Unlike prior fusion methods, we conduct a two-stage fusion strategy to do color-depth fusion and local-global fusion successively. Specifically, we fuse the color features extracted from RGB images into the point cloud in the first stage. In the second stage, we extract local and global features from the fused point cloud using an ASSANet-like network and splice them together to obtain the final fusion features. We conducted experiments on the widely used LineMod and YCB-Video datasets, which shows that our method improves the prediction accuracy while reducing the training time. © 2022 IEEE.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Efficient Hierarchical Exploration with An Active Subgoal Generation Strategy

Efficient Hierarchical Exploration with An Active Subgoal Ge...

引用

2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022

作者： Xu, Xin Zuo, Guoyu Li, Jiangeng Huang, Gao The Faculty of Information Technology Beijing University of Technology Beijing100124 China The Beijing Key Laboratory of Computing Intelligence and Intelligent Systems Beijing100124 China Faculty of Information Beijing University of Technology Beijing100124 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing100081 China

ISBN: (纸本)9781665481090

Goal-conditioned hierarchical reinforcement learning (HRL) is a promising approach in long-horizon and complex tasks. It has been successfully used by decomposing tasks via subgoals. However, the existing goal-conditioned HRL methods often suffer from training inefficiency in the long-horizon tasks with sparse external rewards. For this problem, this paper proposes a novel framework that can train high-level policy efficiently with an effective sub goal generation method. The key component of the framework is an active subgoal generation strategy which consists of (a) an efficient high-level policy learning mechanism and (b) two measures of novelty and coverage for filtering effective subgoals. We also introduce the HER mechanism to the framework to solve the problem of sparse reward in the environment. Building upon the proposed framework, this paper develops an active hierarchical exploration strategy with an efficient subgoal generation method. We test our method on a variety of continuous control tasks. Experimental results demonstrate that the strategy outperforms the state-of-the-art HRL approaches. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Brief Overview of ChatGPT:The History,Status Quo and Potential Future Development

引用

IEEE/CAA Journal of Automatica Sinica 2023年第5期10卷 1122-1136页

作者： Tianyu Wu Shizhu He Jingping Liu Siqi Sun Kang Liu Qing-Long Han Yang Tang the Key Laboratory of Smart Manufacturing in Energy Chemical Process East China University of Science and TechnologyShanghai 200237China the Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 the School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China the School of Information Science and Engineering East China University of Science and TechnologyShanghai 200237China the Research Institute of Intelligent Complex Systems Fudan UniversityShanghai 200437China the School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourne VIC 3122Australia

ChatG PT,an artificial intelligence generated content (AIGC) model developed by OpenAI,has attracted worldwide attention for its capability of dealing with challenging language understanding and generation tasks in the form of *** paper briefly provides an overview on the history,status quo and potential future development of ChatGPT,helping to provide an entry point to think about ***,from the limited open-accessed resources,we conclude the core techniques of ChatGPT,mainly including large-scale language models,in-context learning,reinforcement learning from human feedback and the key technical steps for developing *** further analyze the pros and cons of ChatGPT and we rethink the duality of ChatGPT in various *** it has been widely acknowledged that ChatGPT brings plenty of opportunities for various fields,mankind should still treat and use ChatG PT properly to avoid the potential threat,e.g.,academic integrity and safety ***,we discuss several open problems as the potential development of ChatGPT.

关键词： AIGC ChatGPT GPT-3 GPT-4 human feedback large language models

来源：评论

学校读者我要写书评

暂无评论

Time-independent Spiking Neuron via Membrane Potential Estimation for Efficient Spiking Neural Networks

Time-independent Spiking Neuron via Membrane Potential Estim...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Hanqi Chen Lixing Yu Shaojie Zhan Penghui Yao Jiankun Shao Yunnan Key Laboratory of Intelligent Systems and Computing School of Information Science and Engineering Yunnan University China State Key Laboratory of Explosion Science and Technology Beijing Institute of Technology Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The computational inefficiency of spiking neural networks (SNNs) is primarily due to the sequential updates of membrane potential, which becomes more pronounced during extended encoding periods compared to artificial neural networks (ANNs). This highlights the need to parallelize SNN computations effectively to leverage available hardware parallelism. To address this, we propose Membrane Potential Estimation Parallel Spiking Neurons (MPE-PSN), a parallel computation method for spiking neurons that enhances computational efficiency by enabling parallel processing while preserving the intrinsic dynamic characteristics of SNNs. Our approach exhibits promise for enhancing computational efficiency, particularly under conditions of elevated neuron density. Empirical experiments demonstrate that our method achieves state-of-the-art (SOTA) accuracy and efficiency on neuromorphic datasets. Codes are available at https://***/chrazqee/MPE-PSN.

关键词： Neuromorphics Computational modeling Neurons Membrane potentials Estimation Spiking neural networks Parallel processing Signal processing Computational efficiency Speech processing

来源：评论

学校读者我要写书评

暂无评论

GACL-Net:Hybrid Deep Learning Framework for Accurate Motor Imagery Classification in Stroke Rehabilitation

引用

Computers, Materials & Continua 2025年第4期83卷 517-536页

作者： Chayut Bunterngchit Laith H.Baniata Mohammad H.Baniata Ashraf ALDabbas Mohannad A.Khair Thanaphon Chearanai Sangwoo Kang State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing100190China School of Computing Gachon UniversitySeongnam13120Republic of Korea Computer Science Department Faculty of Information TechnologyThe World Islamic Sciences and Education UniversityAmman11947Jordan Intelligent Systems Department Faculty of Artificial IntelligenceAl-Balqa Applied UniversityAl-Salt19117Jordan IT Infrastructure Department Qatrana Cement CompanyAmman11821Jordan Division of Industrial and Logistics Engineering Technology Faculty of Engineering and TechnologyKing Mongkut’s University of Technology North BangkokRayong CampusRayong21120Thailand

Stroke is a leading cause of death and disability worldwide,significantly impairing motor and cognitive *** rehabilitation is often hindered by the heterogeneity of stroke lesions,variability in recovery patterns,and the complexity of electroencephalography(EEG)signals,which are often contaminated by *** classification of motor imagery(MI)tasks,involving the mental simulation of movements,is crucial for assessing rehabilitation strategies but is challenged by overlapping neural signatures and patient-specific *** address these challenges,this study introduces a graph-attentive convolutional long short-term memory(LSTM)network(GACL-Net),a novel hybrid deep learning model designed to improve MI classification accuracy and ***-Net incorporates multi-scale convolutional blocks for spatial feature extraction,attention fusion layers for adaptive feature prioritization,graph convolutional layers to model inter-channel dependencies,and bidi-rectional LSTM layers with attention to capture temporal *** on an open-source EEG dataset of 50 acute stroke patients performing left and right MI tasks,GACL-Net achieved 99.52%classification accuracy and 97.43%generalization accuracy under leave-one-subject-out cross-validation,outperforming existing state-of-the-art ***,its real-time processing capability,with prediction times of 33–56 ms on a T4 GPU,underscores its clinical potential for real-time neurofeedback and adaptive *** findings highlight the model’s potential for clinical applications in assessing rehabilitation effectiveness and optimizing therapy plans through precise MI classification.

关键词： Motor imagery EEG stroke rehabilitation deep learning brain-computer interface

来源：评论

学校读者我要写书评

暂无评论

Synchronization of Hyper-Lorenz System Based on DNA Strand Displacement

引用

IEEE/ACM Transactions on Computational Biology and Bioinformatics 2022年第3期19卷 1897-1908页

作者： Zou, Chengye Zhang, Qiang Wei, Xiaopeng School of Mathematics and Statistics of Anyang Normal University Anyang455000 China Dalian University Ministry of Education Key Laboratory of Advanced and Intelligent Computing Dalian116622 China Dalian University of Technology Faculty of Electronic Information and Electrical Engineering Dalian116024 China

Lorenz system is depicted by chemical reaction equations of an ideal formal chemical reaction network, and a series of reversible reactions are added into chemical reaction network in order to construct a cluster of hyper-Lorenz system. DNA as a universal substrate for chemical dynamics can approximate arbitrary dynamical characteristics of ideal formal chemical reaction network through auxiliary DNA strands and displacement reactions. Based on Lyapunov's stableness theory, a novel synchronization strategy is proposed. A 6-dimensional hyper-Lorenz system is taken as examples for simulation and shows that DNA strands displacement reactions can implement the synchronization of ideal formal chemical reaction networks. Numerical simulations indicate that synchronization based on DNA strand displacement is robust to the detection of DNA strand concentration, control of reaction rate, and noise. © 2004-2012 IEEE.

关键词： Substrates

来源：评论

学校读者我要写书评

暂无评论

FDAC: Federated Domain Adaptation via Dual Contrastive Learning

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Yi, Chang'an Chen, Haotian Zhang, Yifan Xu, Yonghui Zhou, Yan Cui, Lizhen Yu, Han Foshan University Guangdong Provincial Key Laboratory of Industrial Intelligent Inspection Technology School of Electronic and Information Engineering Foshan China Jinan China School of Computing Singapore Singapore College of Computing and Data Science Singapore Singapore

Federated domain adaptation (FDA) aims to transfer knowledge collaboratively from multiple source domains to related but different unlabelled target domains. The data of each domain are locally maintained, and various domain gaps exist among them, resulting in extreme challenges in simultaneously mitigating diverse distribution shifts and preserving discriminative knowledge without accessing the source data. Many existing works have failed to fully explore different source models to measure domain shifts and leverage semantic knowledge, resulting in skewed alignment and partial preservation of discriminative information. In this paper, we propose a novel approach named FDAC to address Federated Domain Adaptation by thoroughly investigating source models via dual Contrastive mechanisms. FDAC contrastively increases the data diversity to align features across domains in a fine-grained manner by manipulating the latent deep architecture and compensating for knowledge from each source domain;simultaneously, it contrastively utilizes the comprehensive semantic knowledge of different source domains to guide the adaptation process. Extensive experiments on several real datasets demonstrate that FDAC outperforms all comparative methods under most conditions. Furthermore, FDAC only needs approximately half of the communication rounds compared with the state-of-the-art methods, indicating that FDAC can significantly improve communication efficiency, which is another key factor in the federated setting. The source code is publicly available at https://***/ycarobot/FDAC. © 1991-2012 IEEE.

关键词： Contrastive learning Domain adaptation Federated learning Vision transformer

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：