检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Huang, Zhizhong Dai, Mingliang Zhang, Yi Zhang, Junping Shan, Hongming Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China School of Cyber Science and Engineering Sichuan University Chengdu610065 China Institute of Science and Technology for Brain-inspired Intelligence MOE Frontiers Center for Brain Science Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Fudan University Shanghai200433 China

Class-agnostic object counting aims to count all objects in an image with respect to example boxes or class names, a.k.a few-shot and zero-shot counting. In this paper, we propose a generalized framework for both few-shot and zero-shot object counting based on detection. Our framework combines the superior advantages of two foundation models without compromising their zero-shot capability: (i) SAM to segment all possible objects as mask proposals, and (ii) CLIP to classify proposals to obtain accurate object counts. However, this strategy meets the obstacles of efficiency overhead and the small crowded objects that cannot be localized and distinguished. To address these issues, our framework, termed PseCo, follows three steps: point, segment, and count. Specifically, we first propose a class-agnostic object localization to provide accurate but least point prompts for SAM, which consequently not only reduces computation costs but also avoids missing small objects. Furthermore, we propose a generalized object classification that leverages CLIP image/text embeddings as the classifier, following a hierarchical knowledge distillation to obtain discriminative classifications among hierarchical mask proposals. Extensive experimental results on FSC-147, COCO, and LVIS demonstrate that PseCo achieves state-of-the-art performance in both few-shot/zero-shot object counting/detection. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Problem Reduction for Large-Scale Uncapacitated Facility Location Problems

Learning-Based Problem Reduction for Large-Scale Uncapacitat...

引用

Congress on Evolutionary Computation

作者： Shuaixiang Zhang Yixuan Yang Hao Tong Xin Yao Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Shenzhen China Department of Computing and Decision Sciences Lingnan University Hong Kong SAR China

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

The uncapacitated facility location problem (UFLP) is a well-known combinational optimization problem, attracting numerous heuristic and meta-heuristic methods. However, these effective algorithms still encounter challenges when solving large-scale UFLP instances. To deal with the thousands of decision variables, one possible approach is to predict and remove unimportant facilities and thus decreases the dimensionality of problem instances. This paper explores the problem reduction of large-scale instances of UFLP. We propose suitable features of facilities to construct machine learning models for UFLP by learning from small instances. Based on this model, we introduce a novel problem reduction strategy-based optimization framework, and apply it to large instances. Through comprehen-sive experiments, we show that the proposed problem reduction strategy can effectively transform the UFLP instances to smaller ones. The performance of existing solution methods can be significantly enhanced, especially on large-scale instances. Under the proposed framework, we also show the generalization abilities of our models, which can be improved further.

关键词： Dimensionality reduction Metaheuristics Training data Transforms Evolutionary computation Benchmark testing Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Output Containment Control of Heterogeneous Multiagent Systems: A Hierarchical Scheme 63

Data-Driven Output Containment Control of Heterogeneous Mult...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Sader, Malika Li, Wenyu Yin, Yanhui Li, Zhongmei Huang, Dexian Liu, Zhongxin He, Xiao Shang, Chao Tsinghua University Department of Automation Beijing100084 China Nankai University Coll. of Artif. Intell. Tianjin Key Lab. of Interventional Brain-Comp. Interface and Intelligent Rehab. Tianjin300350 China North-East Electric Power University School of Automation Engineering Jilin132000 China East China University of Science and Technology Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education Shanghai200237 China Tsinghua University Department of Automation Beijing National Research Center for Information Science and Technology Beijing100084 China

ISBN: (纸本)9798350316339

In this article, we propose a data-driven solution to the output containment control problem of multiagent systems characterized by heterogeneous and unknown dynamics. The proposed data-driven scheme is hierarchical, which includes a network layer and a physical layer, bypassing the traditional modeling exercise and eliminating the need for explicit state-space models. In the network layer, a fully distributed observer without knowing the dynamics of leaders is designed to generate a containment trajectory. A data-driven approach based on data sampled from an auxiliary system is developed to overcome the dependence on the explicit state-space models for design of control gains. This paves the way for deriving a datadriven solution to the regulator equation, which is derived by employing the data informativity condition and relevant data in the physical layer. The results demonstrate that the closedloop system is asymptotically stable, and the regulated output containment converges to zero. Compared to generic modelbased hierarchical schemes, the assumptions that the system matrices are completely known and homogeneous on system dynamics can be relaxed. © 2024 IEEE.

关键词： Hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

Tuning In to Neural Encoding: Linking Human brain and Artificial Supervised Representations of Language

arXiv

引用

arXiv 2023年

作者： Sun, Jingyuan Zhang, Xiaohan Moens, Marie-Francine Department of Computer Science KU Leuven Belgium Institute of Neuroscience Key Laboratory of Primate Neurobiology CAS Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences China

To understand the algorithm that supports the human brain’s language representation, previous research has attempted to predict neural responses to linguistic stimuli using embeddings generated by artificial neural networks (ANNs), a process known as neural encoding. However, most of these studies have focused on probing neural representations of Germanic languages, such as English, with unsupervised ANNs. In this paper, we propose to bridge the gap between human brain and supervised ANN representations of the Chinese language. Specifically, we investigate how task tuning influences a pretained Transformer for neural encoding and which tasks lead to the best encoding performances. We generate supervised representations on eight Natural Language Understanding (NLU) tasks using prompt-tuning, a technique that is seldom explored in neural encoding for language. We demonstrate that prompt-tuning yields representations that better predict neural responses to Chinese stimuli than traditional fine-tuning on four tasks. Furthermore, we discover that tasks that require a fine-grained processing of concepts and entities lead to representations that are most predictive of brain activation patterns. Additionally, we reveal that the proportion of tuned parameters highly influences the neural encoding performance of fine-tuned models. Overall, our experimental findings could help us better understand the relationship between supervised artificial and brain language representations. Copyright © 2023, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal brain Network Fusion for Intelligent Diagnostic Devices

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Li, Shengrong Zhu, Qi Sun, Liang Ma, Kai Ji, Yixin Qi, Shile Zhang, Daoqiang Nanjing University of Aeronautics and Astronautics College of Artificial Intelligence Nanjing211106 China University of Aeronautics and Astronautics Key Laboratory of Brain-Machine Intelligence Technology Ministry of Education Nanjing211106 China Jiangsu University of Science and Technology School of Computer Jiangsu Province Zhenjiang212100 China

Embedding multi-modal brain network analysis technology into consumer electronics, such as smart wearables, helps enable early intelligent diagnosis of brain diseases. Recent studies confirm that the functional-structural coupling in certain regions is more tightly correlated than in others. However, existing multi-modal methods often directly fuse functional brain networks (FBN) and structural brain networks (SBN), ignoring the regional heterogeneity between them. Additionally, identity information encoded in brain networks may interfere with disease diagnosis. In this paper, we develop a multi-modal brain network fusion method with regional heterogeneity constraints, and design a feature decoupling module to alleviate disease-irrelevant information. Specifically, we first divide FBN and SBN into multiple subnetworks, and introduce penalty weights to reduce the communication cost between cross-modal brain regions within the subnetwork while increasing the cost between different subnetworks. Then, under the regional heterogeneity constraints, we adopt optimal transport to simulate the transfer of brain region hubness from FBN to SBN, thereby effectively integrating the complex cross-modal interactions. Furthermore, we design a feature decoupling module to suppress ineffective features and enhance the discrimination between modality-specific features and multi-modal features. Experimental results show that the proposed method has promising performance and can identify multi-modal biomarkers for brain disease diagnosis. © 1975-2011 IEEE.

关键词： Wearable technology

来源：评论

学校读者我要写书评

暂无评论

Video Corpus Moment Retrieval with Query-specific Context Learning and Progressive Localization

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Zhang, Long Song, Peipei Duan, Zhangling Wang, Shuo Chang, Xiaojun Yang, Xun School of Information Science and Technology Hefei230026 China Hefei Comprehensive National Science Center Institute of Artificial Intelligence Hefei230026 China University of Science and Technology of China School of Information Science and Technology Hefei230026 China Department of Computer Vision Abu Dhabi United Arab Emirates University of Science and Technology of China MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition China

Video corpus moment retrieval (VCMR) aims to retrieve a moment from a large corpus of untrimmed videos corresponding to a given language query. However, existing methods often fall short due to their reliance on simple cross-modal attention mechanisms and one-stop localization, which fail to handle the complex multimodal information and large search space effectively. To address these challenges, we propose a novel VCMR method with Query-specific Context Learning and Progressive Localization (QCLPL). First, we construct query-specific multimodal contexts that capture complementary and consistent semantics across subtitles and frames, ensuring informative and efficient context building. We further introduce a semantic contrastive loss to refine these multimodal contexts, filtering out query-irrelevant information. Additionally, we introduce a progressive localization strategy that transforms the moment localization task into a two-stage process. By classifying frames into foreground and background regions, we present a simplified binary classification problem before boundary prediction, constrained by a region-aware loss. This progressive approach leverages region priors to improve subsequent moment localization. Extensive experiments on the TVR and DiDeMo datasets demonstrate that our method significantly outperforms existing approaches, setting a new state of the art for VCMR. © 1991-2012 IEEE.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Neuron-astrocyte coupling in lateral habenula mediates depressive-like behaviors

引用

Cell 2025年

作者： Xin, Qianqian Wang, Junying Zheng, Jinkun Tan, Yi Jia, Xiaoning Ni, Zheyi Xu, Zijie Feng, Jiesi Wu, Zhaofa Li, Yulong Li, Xiao-Ming Ma, Huan Hu, Hailan Department of Neurobiology Affiliated Mental Health Center & Hangzhou Seventh People's Hospital Zhejiang University School of Medicine Hangzhou 310058 China Nanhu Brain-Computer Interface Institute Liangzhu Laboratory MOE Frontier Science Center for Brain Science and Brain-Machine Integration State Key Laboratory of Brain-Machine Intelligence New Cornerstone Science Laboratory Zhejiang University Hangzhou 311121 China Department of Psychiatry and International Institutes of Medicine The Fourth Affiliated Hospital Zhejiang University School of Medicine Yiwu 322000 China State Key Laboratory of Membrane Biology Peking University School of Life Sciences Beijing 100871 China

The lateral habenula (LHb) neurons and astrocytes have been strongly implicated in depression etiology, but it was not clear how the two dynamically interact during depression onset. Here, using multi-brain-region calcium photometry recording in freely moving mice, we discover that stress induces a most rapid astrocytic calcium rise and a bimodal neuronal response in the LHb. LHb astrocytic calcium requires the α_1A-adrenergic receptor and depends on a recurrent neural network between the LHb and locus coeruleus (LC). Through the gliotransmitter glutamate and ATP/adenosine, LHb astrocytes mediate the second-wave LHb neuronal activation and norepinephrine (NE) release. Activation or inhibition of LHb astrocytic calcium signaling facilitates or prevents stress-induced depressive-like behaviors, respectively. These results identify a stress-induced positive feedback loop in the LHb-LC axis, with astrocytes being a critical signaling relay. The identification of this prominent neuron-glia interaction may shed light on stress management and depression prevention. © 2025 Elsevier Inc.

关键词： astrocytes depression lateral habenula locus coeruleus norepinephrine phasic and tonic NE reboxetine SNRI stress α1A-adrenergic receptor

来源：评论

学校读者我要写书评

暂无评论

State entropy reveals the reconfiguration of brain complexity in Parkinson’s disease

Brain Network Disorders

引用

brain Network Disorders 2025年第1期1卷 57-64页

作者： Xuyang Wang Ting Zou Huafu Chen Chen Chen Chunyan Zhang Jingliang Cheng Rong Li The Center of Psychosomatic Medicine Sichuan Provincial Center for Mental Health Sichuan Provincial People’s Hospital University of Electronic Science and Technology of China Chengdu Sichuan 611731 China School of Life Science and Technology University of Electronic Science and Technology of China Chengdu Sichuan 611731 China MOE Key Laboratory for Neuroinformation High-Field Magnetic Resonance Brain Imaging Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Chengdu Sichuan 611731 China Department of Magnetic Resonance The First Affiliated Hospital of Zhengzhou University Zhengzhou Henan 450052 China

Background The brain is a complex dynamic system comprising multiple information-processing units. The characterization of brain systems and understanding of their organization and reconfiguration in different states remains an ongoing challenge. This study aims to explore the organization of brain complexity in Parkinson’s disease (PD). Methods In this study, we developed a framework to measure the complexity of each unit and explore aberrant patterns in PD. The resting-state blood oxygen level-dependent signals were converted into a state series with spatiotemporal coding of the whole brain system, and subsequently calculated the Shannon entropy of the state series (referred to as state entropy). Results In a total of 152 participants (PD patients n = 73, normal controls n = 79), we revealed a descent entropy gradient from the neocortex, particularly the default mode network (DMN), to subcortical systems. Subsequent application of a two-sample t -test and multiple comparison correction revealed that the state entropy of the visual, sensorimotor, and limbic networks was significantly increased in the PD group. Additionally, we obtained the person-based similarity index (PBSI) of state entropy within each network to measure individual variability, finding that patients with PD have decreased PBSI scores on the visual, sensorimotor, and limbic networks, and increased PBSI of entropy on the DMN. Notably, when testing the classification performance of state entropy and PBSI metrics, we found that individual variability was more effective in recognizing patients with PD. Conclusions Our study reveals the organization of brain complexity across healthy and PD states, and suggests that personalized measures of brain reconfiguration have the potential to help develop clinical assistant diagnostic systems.

关键词： Resting-state functional magnetic resonance imaging State entropy Parkinson disease Classification modeling

来源：评论

学校读者我要写书评

暂无评论

Exploring Humanoid Robot Face Preference Using brain Functional Connectivity and Graph Neural Network 12

Exploring Humanoid Robot Face Preference Using Brain Functio...

引用

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

作者： Wang, Pengchao Mu, Wei Zhan, Gege Wang, Aiping Song, Zuoting Fang, Tao Zhang, Xueze Wang, Junkongshuai Niu, Lan Bin, Jianxiong Zhang, Lihua Jia, Jie Kang, Xiaoyang State Key Laboratory of Medical Neurobiology Institute of Ai and Robotics Academy for Engineering and Technology Fudan University Laboratory for Neural Interface and Brain Computer Interface Engineering Research Center of Ai and Robotics Ministry of Education Shanghai Engineering Research Center of Ai and Robotics Moe Frontiers Center for Brain Science Shanghai200433 China Ji Hua Laboratory Guangdong Province Foshan528200 China Huashan Hospital Fudan University Department of Rehabilitation Medicine Shanghai200040 China Yiwu Research Institute of Fudan University Zhejiang Yiwu City322000 China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou311121 China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

Graph neural networks (GNN) have been applied in EEG signal analysis. However, it is not clear how to describe the connection relationships between electrodes, and a reasonable representation of the adjacency matrix cannot be neglected for the study of GNN based on EEG signals. In this paper, we use brain functional connectivity to analyze the face preferences of a humanoid robot and explore the feasibility of using the matrix obtained based on brain functional connectivity measurements as a GNN connectivity matrix. The results show that it is feasible and an average accuracy of 73.47% is achieved. In addition, the results of the brain functional connectivity analysis also show that there is a difference between preferences and non-preferences. © 2022 IEEE.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

Route Control of Four-rotor UAV based on brain-computer interface in Virtual Reality 12

Route Control of Four-rotor UAV based on Brain-Computer Inte...

引用

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

作者： Niu, Lan Bin, Jianxiong Wang, Junkongshuai Zhan, Gege Jiang, Haifeng Dong, Zhiyan Zhang, Lihua Kang, Xiaoyang Moe Frontiers Center for Brain Science State Key Laboratory of Medical Neurobiology Institute of Ai and Robotics Academy for Engineering and Technology Fudan University Laboratory for Neural Interface and Brain Computer Interface Engineering Research Center of Ai and Robotics Ministry of Education Shanghai Engineering Research Center of Ai and Robotics Shanghai200433 China Ji Hua Laboratory Guangdong Province Foshan China Shanghai Mental Center Shanghai Jiao Tong University School of Medicine Shanghai China Yiwu Research Institute of Fudan University Chengbei Road Zhejiang Province Yiwu City China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

This article presented an experiment to determine the effect of dynamic 3D vision-evoked modules on the performance of the system we designed to steer a four-rotor unmanned aerial vehicle (UAV). Nowadays, UAV system is widely used in various industries, and UAV control has always been a focus of research. The brain-computer interface (BCI) system was based on the well-known steady-state visually evoked potentials (SSVEP). The specificity of the interface was the integration of dynamic 3D paradigms in virtual reality. In order to achieve a more immersive and interactive scene, VR scenes were moving synchronously with the UAV. Users can achieve remote control of four-rotor UAV through virtual scenarios. Ten subjects participated in the experiment and operated the UAV to complete a specific track. The dynamic paradigm based on the experimenter's feedback may indeed affect their attention, we proposed an effective solution to overcome this problem. The detailed results of these experiments were reported in this paper and we discussed the possible causes of performance loss under such conditions. © 2022 IEEE.

关键词： brain computer interface

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：