检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Ma, Chenxiang Chen, Xinyi Li, Yanchen Yang, Qu Wu, Yujie Li, Guoqi Pan, Gang Tang, Huajin Tan, Kay Chen Wu, Jibin Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong Department of Computing The Hong Kong Polytechnic University Hong Kong Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore Institute of Automation Chinese Academy of Sciences Beijing100045 China State Key Laboratory of Brain-Machine Intelligence College of Computer Science and Technology MOE Frontier Science Center for Brain Science and Brain-Machine Integration Zhejiang University Hangzhou310027 China

Temporal processing is fundamental for both biological and artificial intelligence systems, as it enables the comprehension of dynamic environments and facilitates timely responses. Spiking Neural Networks (SNNs) excel in handling such data with high efficiency, owing to their rich neuronal dynamics and sparse activity patterns. Given the recent surge in the development of SNNs, there is an urgent need for a comprehensive evaluation of their temporal processing capabilities. In this paper, we first conduct an in-depth assessment of commonly used neuromorphic benchmarks, revealing critical limitations in their ability to evaluate the temporal processing capabilities of SNNs. To bridge this gap, we further introduce a benchmark suite consisting of three temporal processing tasks characterized by rich temporal dynamics across multiple timescales. Utilizing this benchmark suite, we perform a thorough evaluation of recently introduced SNN approaches to elucidate the current status of SNNs in temporal processing. Our findings indicate significant advancements in recently developed spiking neuron models and neural architectures regarding their temporal processing capabilities, while also highlighting a performance gap in handling long-range dependencies when compared to state-of-the-art non-spiking models. Finally, we discuss the key challenges and outline potential avenues for future research. Copyright © 2025, The Authors. All rights reserved.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Hybrid Modeling Approaches in Energy Internet: Bridging Cyber, Physical, and Social Realms

Hybrid Modeling Approaches in Energy Internet: Bridging Cybe...

引用

2024 International Conference on Communication, computer sciences and Engineering, IC3SE 2024

作者： Chaturvedi, Prateek Thethi, H. Pal Reddy, N. V. Uma Kalaiarasi, M. Al-Rubaye, Taqi Mohammed Khattab Anusha, K. Amity University Greater Noida Department Of Mechanical Engineering India Lovely Professional University Phagwara India New Horizon College Of Engineering Department Of Artificial Intelligence And Machine Learning Bangalore India Institute Of Aeronautical Engineering Department Of Computer Science And Engineering Telangana Hyderabad India College Of Medical Technologies The Islamic University Department Of Medical Laboratory Technology Najaf Iraq Mlr Institute Of Technology Department Of CSE-AI&ML Telangana Hyderabad India

ISBN: (纸本)9798350366846

Effective modeling approaches are required for the management and operation of the Energy Internet due to the system's complexity and mobility. New hybrid models that link the Energy Internet's digital, real-world, and social components are the primary focus of this article. We propose a novel approach that integrates adaptive reinforcement learning, social behavior analysis, and multi-agent coordination optimization to enhance the system's performance, robustness, and long-term sustainability. We intend to address issues that arise when several factors, such as evolving technology, user behavior, and social interactions, converge by employing these mixed modeling approaches. Because of this, the Energy Internet setting will run more efficiently and effectively. Through extensive simulations and case studies, we demonstrate that our proposed method outperforms conventional ones. Our main focus is on how technology can enhance energy management, better allocate resources, and back user-centered and socially inclusive policies. To ensure the seamless operation of the Energy Internet environment's cyber, physical, and social components, the results highlight the significance of mixed modeling methodologies. © 2024 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Skeletal Human Action Recognition using Hybrid Attention based Graph Convolutional Network

arXiv

引用

arXiv 2022年

作者： Xing, Hao Burschka, Darius Technical University of Munich Machine Vision and Perception Group Munich Institute of Robotics and Machine Intelligence Department of Computer Science Parkring 13 Munich85748 Germany

In skeleton-based action recognition, Graph Convolutional Networks model human skeletal joints as vertices and connect them through an adjacency matrix, which can be seen as a local attention mask. However, in most existing Graph Convolutional Networks, the local attention mask is defined based on natural connections of human skeleton joints and ignores the dynamic relations for example between head, hands and feet joints. In addition, the attention mechanism has been proven effective in Natural Language Processing and image description, which is rarely investigated in existing methods. In this work, we proposed a new adaptive spatial attention layer that extends local attention map to global based on relative distance and relative angle information. Moreover, we design a new initial graph adjacency matrix that connects head, hands and feet, which shows visible improvement in terms of action recognition accuracy. The proposed model is evaluated on two large-scale and challenging datasets in the field of human activities in daily life: NTU-RGB+D and Kinetics skeleton. The results demonstrate that our model has strong performance on both dataset. © 2022, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition from Eye Movements Using Multi-way Autoregressive Model

Emotion Recognition from Eye Movements Using Multi-way Autor...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Tian-Fang Ma Xuan-Hao Liu Wei-Long Zheng Bao-Liang Lu Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

The application of physiological signals in emotion recognition is a popular research topic in human-computer interactions. Eye movement, as an important physiological signal, plays an essential role in medicine, psychology, cognitive science, and other scientific research fields. Previous studies have successfully identified human emotions by combining various eye-related measurements, selecting features, and utilizing machine learning techniques. However, the exploration of eye movement signals in emotion recognition remains insufficient. In this study, we utilize eye tracking heatmap and eye movement trajectory data for emotion recognition for the first time. Based on the two types of eye movement data, we develop a multi-way autoregressive model capable of processing multi-view eye movement data. Compared to traditional deep learning baseline models, our model better adapts to the structure of eye movement data and significantly improves the classification performance. Furthermore, we integrate heatmap and trajectory data with commonly used eye-related measurement features, which further enhance the performance of emotion recognition beyond previous methods.

关键词： Heating systems Emotion recognition Adaptation models Accuracy Psychology Gaze tracking Biomedical measurement Data models Physiology Trajectory

来源：评论

学校读者我要写书评

暂无评论

Disentangling Long-Short Term State Under Unknown Interventions for Online Time Series Forecasting

arXiv

引用

arXiv 2025年

作者： Cai, Ruichu Huang, Haiqin Jiang, Zhifan Li, Zijian Zhou, Changze Liu, Yuequn Liu, Yuming Hao, Zhifeng School of Computer Science Guangdong University of Technology China Peng Cheng Laboratory Shenzhen China Machine Learning Department Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Shantou University China

Current methods for time series forecasting struggle in the online scenario, since it is difficult to preserve long-term dependency while adapting short-term changes when data are arriving sequentially. Although some recent methods solve this problem by controlling the updates of latent states, they cannot disentangle the long/short-term states, leading to the inability to effectively adapt to nonstationary. To tackle this challenge, we propose a general framework to disentangle long/short-term states for online time series forecasting. Our idea is inspired by the observations where short-term changes can be led by unknown interventions like abrupt policies in the stock market. Based on this insight, we formalize a data generation process with unknown interventions on short-term states. Under mild assumptions, we further leverage the independence of short-term states led by unknown interventions to establish the identification theory to achieve the disentanglement of long/short-term states. Built on this theory, we develop a Long Short-Term Disentanglement model (LSTD) to extract the long/short-term states with long/short term encoders, respectively. Furthermore, the LSTD model incorporates a smooth constraint to preserve the long-term dependencies and an interrupted dependency constraint to enforce the forgetting of short-term dependencies, together boosting the disentanglement of long/short-term states. Experimental results on several benchmark datasets show that our LSTD model outperforms existing methods for online time series forecasting, validating its efficacy in real-world applications. Copyright © 2025, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Disentangling Long-Short Term State Under Unknown Interventions for Online Time Series Forecasting 39

Disentangling Long-Short Term State Under Unknown Interventi...

引用

39th Annual AAAI Conference on Artificial intelligence, AAAI 2025

ISBN: (纸本)157735897X

关键词：

来源：评论

学校读者我要写书评

暂无评论

vision Transformer Based Automated Model for Enhancing Lung Cancer Classification

Vision Transformer Based Automated Model for Enhancing Lung ...

引用

IEEE International Workshop on Imaging Systems and Techniques (IST)

作者： Akbar Sheikh Akbari Arvind Kumar B Ramachandra Reddy Koushlendra Kumar Singh Masahiro Takei Leeds Beckett University UK Machine Vision and Intelligence Lab National Institute of Technology Jamshedpur Jharkhand India Computer Science and Engineering National Institute of Technology Jamshedpur Jharkhand India Department of Mechanical Engineering Chiba University Chiba Japan

ISBN: (数字)9798350378214

ISBN: (纸本)9798350378221

Lung cancer is one of the leading causes of cancer related mortality. The early detection and classification of the cancers tissues will reduce the mortalities rate. The present research focus on the development of automated classification model for lung and colon cancers tissues based on the histopathology images. The present work encompasses a vision transformer (ViT) based model to enhance diagnostic accuracy of lung cancers tissues. The proposed model utilizes the self-attention mechanism of ViT to focus on essential features present in histopathologicals images. The proposed model has been validated using two different dataset namely LC25000 & IQ-OTH/NCCD with 25000 & 1096 images respectively. The performance of proposed model is compared with traditional convolutional neural network (CNN) model and it has been observed the based model outforms better in terms of accuracy which - 98.80% & 99.09% respectively for datasets.

关键词： computer vision Analytical models Accuracy Lungs Lung cancer Imaging Transformers Convolutional neural networks Reliability Testing

来源：评论

学校读者我要写书评

暂无评论

LES-Talker: Fine-Grained Emotion Editing for Talking Head Generation in Linear Emotion Space

arXiv

引用

arXiv 2024年

作者： Feng, Guanwen Qian, Zhihao Li, Yunan Jin, Siyu Miao, Qiguang Pun, Chi-Man School of Computer Science and Technology Xidian University Xi’an710071 China Xi’an Key Laboratory of Big Data and Intelligent Vision Shaanxi Xi’an710071 China Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi’an710071 China Department of Computer and Information Science University of Macau 999078 China

While existing one-shot talking head generation models have achieved progress in coarse-grained emotion editing, there is still a lack of fine-grained emotion editing models with high interpretability. We argue that for an approach to be considered fine-grained, it needs to provide clear definitions and sufficiently detailed differentiation. We present LES-Talker, a novel one-shot talking head generation model with high interpretability, to achieve fine-grained emotion editing across emotion types, emotion levels, and facial units. We propose a Linear Emotion Space (LES) definition based on Facial Action Units to characterize emotion transformations as vector transformations. We design the Cross-Dimension Attention Net (CDAN) to deeply mine the correlation between LES representation and 3D model representation. Through mining multiple relationships across different feature and structure dimensions, we enable LES representation to guide the controllable deformation of 3D model. In order to adapt the multimodal data with deviations to the LES and enhance visual quality, we utilize specialized network design and training strategies. Experiments show that our method provides high visual quality along with multilevel and interpretable fine-grained emotion editing, outperforming mainstream methods. Project page: https://***/LES-Talker/ Copyright © 2024, The Authors. All rights reserved.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Protein codes promote selective subcellular compartmentalization

引用

science (New York, N.Y.) 2025年第6738期387卷 1095-1101页

作者： Kilgore, Henry R. Chinn, Itamar Mikhael, Peter G. Mitnikov, Ilan Van Dongen, Catherine Zylberberg, Guy Afeyan, Lena Banani, Salman F. Wilson-Hawken, Susana Lee, Tong Ihn Barzilay, Regina Young, Richard A. Whitehead Institute for Biomedical Research Cambridge MA United States Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology (MIT) Cambridge MA United States Abdul Latif Jameel Clinic for Machine Learning in Health MIT Cambridge MA United States Department of Biology MIT Cambridge MA United States Department of Pathology Brigham and Women's Hospital Harvard Medical School Boston MA United States Computational and Systems Biology Program MIT Cambridge MA United States

Cells have evolved mechanisms to distribute ~10 billion protein molecules to subcellular compartments where diverse proteins involved in shared functions must assemble. In this study, we demonstrate that proteins with shared functions share amino acid sequence codes that guide them to compartment destinations. We developed a protein language model, ProtGPS, that predicts with high performance the compartment localization of human proteins excluded from the training set. ProtGPS successfully guided generation of novel protein sequences that selectively assemble in the nucleolus. ProtGPS identified pathological mutations that change this code and lead to altered subcellular localization of proteins. Our results indicate that protein sequences contain not only a folding code but also a previously unrecognized code governing their distribution to diverse subcellular compartments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DuSSS: Dual Semantic Similarity-Supervised vision-Language Model for Semi-Supervised Medical Image Segmentation

arXiv

引用

arXiv 2024年

作者： Pan, Qingtao Qiao, Wenhao Lou, Jingjiao Ji, Bing Li, Shuo School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education China Department of Computer and Data Science Department of Biomedical Engineering Case Western Reserve University United States

Semi-supervised medical image segmentation (SSMIS) uses consistency learning to regularize model training, which alleviates the burden of pixel-wise manual annotations. However, it often suffers from error supervision from low-quality pseudo labels. vision-Language Model (VLM) has great potential to enhance pseudo labels by introducing text prompt guided multimodal supervision information. It nevertheless faces the cross-modal problem: the obtained messages tend to correspond to multiple targets. To address aforementioned problems, we propose a Dual Semantic Similarity-Supervised VLM (DuSSS) for SSMIS. Specifically, 1) a Dual Contrastive Learning (DCL) is designed to improve cross-modal semantic consistency by capturing intrinsic representations within each modality and semantic correlations across modalities. 2) To encourage the learning of multiple semantic correspondences, a Semantic Similarity-Supervision strategy (SSS) is proposed and injected into each contrastive learning process in DCL, supervising semantic similarity via the distribution-based uncertainty levels. Furthermore, a novel VLM-based SSMIS network is designed to compensate for the quality deficiencies of pseudo-labels. It utilizes the pretrained VLM to generate text prompt guided supervision information, refining the pseudo label for better consistency regularization. Experimental results demonstrate that our DuSSS achieves outstanding performance with Dice of 82.52%, 74.61% and 78.03% on three public datasets (QaTa-COV19, BM-Seg and MoNuSeg). Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

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：