检索结果-内蒙古大学图书馆

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

作者： Jingqi Li Yuzhen Zhang Hongming Shan Junping Zhang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai China

This work presents a novel hybrid convolution-transformer framework for gait recognition, termed GaitCoTr. The developed framework captures the appearance and short-term temporal features by convolution and extracts the long-term temporal features by transformer architecture, achieving a comprehensive spatial-temporal representation of gait. To unleash the potential of this hybrid framework for extracting richness and generalized temporal features, we propose a new variant of transformer tailored for gait, including temporally shifted tokenization, length-flexible position embedding, and inter-frame encoder. In addition, we introduce an auxiliary task—view label prediction—aiming to disentangle view from ID information. Extensive experimental results on two well-known gait benchmark datasets, CASIA-B and GREW, demonstrate the superior performance of the proposed Gait-CoTr.

关键词： Convolution Speech recognition Benchmark testing Feature extraction Transformers Tokenization Acoustics

来源：评论

学校读者我要写书评

暂无评论

Motion Matters: A Novel Motion Modeling for Cross-View Gait Feature Learning

Motion Matters: A Novel Motion Modeling for Cross-View Gait ...

引用

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

作者： Jingqi Li Jiaqi Gao Yuzhen Zhang Hongming Shan Junping Zhang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Institute of Science and Technology for Brain-inspired Intelligence Fudan University Shanghai China

As a unique biometric that can be perceived at a distance, gait has broad applications in person authentication, social security and so on. Existing gait recognition methods suffer from changes in viewpoint and clothing and barely consider extracting diverse motion features, a fundamental characteristic in gaits, from gait sequences. This paper proposes a novel motion modeling method to extract the discriminative and robust representation. Specifically, we first extract the motion features from the encoded motion sequences in the shallow layer. Then we continuously enhance the motion feature in deep layers. This motion modeling approach is independent of mainstream work in building network architectures. As a result, one can apply this motion modeling method to any backbone to improve gait recognition performance. In this paper, we combine motion modeling with one commonly used backbone (GaitGL) as GaitGL-M to illustrate motion modeling. Extensive experimental results on two commonly-used crossview gait datasets demonstrate the superior performance of GaitGL-M over existing state-of-the-art methods.

关键词： Representation learning Clothing Buildings Signal processing Network architecture Feature extraction Robustness

来源：评论

学校读者我要写书评

暂无评论

MDDMamba: A Model for Multi-Modal Depression Detection with a Memory-Saving Cross-Modal Attention Mechanism Based on Mamba

MDDMamba: A Model for Multi-Modal Depression Detection with ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Mingzhou Liu Zheyu Wang Feng Liu School of Education Science and Technology Nanjing University of Posts and Telecommunications Nanjing China School of Computer and Artificial Intelligence Nanjing University of Science and Technology ZiJin College Nanjing China Jiangsu Key Laboratory of Intelligent Information Processing and Communication Technology Nanjing China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Depression is a severe mental health disorder that constitutes a significant global health challenge, necessitating efficient and accurate automated diagnostic tools. Traditional approaches to automated depression assessment using multi-modal data often face three significant difficulties: small sample sizes in available datasets, high computational cost, and difficulties in effectively integrating different modalities. In this paper, we first mitigate the problem of dataset quality by utilizing an estimated imputation strategy for missing values based on a known data augmentation method. Additionally, we introduce a multi-modal depression detection model named MDDMamba, designed to address the latter two challenges by integrating features from pre-trained emotion models with the memory-efficient selective state space model named Mamba. The MDDMamba model combines features from pre-trained emotion models for both text and audio, enhancing the extraction of emotional information. The core of the MDDMamba model is the CrossMamba module, which replaces the traditional Transformer’s quadratic computational complexity with a linear complexity alternative, facilitating efficient multi-modal fusion. Experimental results on CMDC and EATD-Corpus datasets show that the MDDMamba model achieves better classification and regression performance and stronger generalization capabilities in depression detection. Notably, the MDDMamba model achieves an F1 score of 0.94 and a Pearson correlation coefficient of 0.86 on the CMDC dataset while maintaining lower memory cost, outperforming most advanced multi-modal depression detection methods across various experimental scenarios.

关键词： Emotion recognition Computational modeling Biological system modeling Depression Brain modeling Feature extraction Data models Imputation Data mining Computational complexity

来源：评论

学校读者我要写书评

暂无评论

An unsupervised discriminative random vector functional link network for efficient data clustering 4

An unsupervised discriminative random vector functional link...

引用

4th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2021

作者： Zhang, Yikai Zhu, Qi Peng, Yong Kong, Wanzeng School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China Provincial Key Lab. for Computer Information Processing Technology Soochow University Suzhou215123 China

ISBN: (纸本)9781665413220

Random Vector Functional Link (RVFL) is a single hidden layer feed forward network which can be trained with non-iterative learning methods. Concretely, the input weights and hidden biases in RVFL can be randomly generated and then the calculation of the output weights can be reduced to solve a regularized least squares regression formula. Though RVFL network obtained promising performance in diverse applications, most of its current variants work mainly for supervised tasks such as classification and regression while less effort was made to utilize the unlabeled data. In this paper, we propose an unsupervised RVFL model by simultaneously considering the local manifold structure and the global discriminative information of data. The newly formulated unsupervised discriminative RVFL (UDRVFL) model can be efficiently solved by handling an eigen-value decomposition operation. We conduct experiments by comparing UDRVFL with several state-of-the-arts on representative benchmark data sets and the results demonstrate that it has very competitive performance in data clustering. © 2021 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

FloodSFCP: Quality and Latency Balanced Service Function Chain Placement for Remote Sensing in LEO Satellite Network

FloodSFCP: Quality and Latency Balanced Service Function Cha...

引用

IEEE Communications Society Conference on Sensor and Ad Hoc Communications and Networks (SECON)

作者： Ruoyi Zhang Chao Zhu Xiao Chen Qingyuan Gong Xinlei Xie Xiangyuan Bu School of Cyberspace Science and Technology Beijing Institute of Technology China School of Computer Science and Shanghai Key Lab of Intelligent Information Processing Fudan University China School of Information and Electronics Beijing Institute of Technology China

Prompted by the significant advancements in image processing technologies and their diverse range of applications, remote sensing satellites are poised for rapid expansion. Nonetheless, offloading the vast amount of remote sensing satellite images to the ground gateway station is inefficient due to the exorbitant costs induced by satellite links, while the limited resources of individual satellites hinder local task processing. With the advancement of the network function virtualization (NFV) technology, a new paradigm for service function chain (SFC) has emerged, which can significantly improve the flexibility and resource utilization of network services and alleviate resource conflicts by dividing large services into smaller ones organized in the form of SFCs. As mega-constellations (e.g., Starlink) developed, the number of low earth orbit (LEO) satellites is increasing. By dividing services into small sub-services and organizing them into SFCs throughout the LEO network, services that cannot be completed by a single satellite can be accomplished through multi-satellite cooperation. However, the quality of the remote sensing service is positively correlated with its latency, and the rapidly changing topology of LEO networks also adds complexity to the SFC placement. Hence, how to select appropriate satellites to place the SFC and modulate service levels, in order to obtain better remote sensing results within an acceptable latency, remains a question. To address these issues, this paper proposes the FloodSFCP, an SFC placement method that aims to increase service quality and decrease latency through offline training and online optimization via deep reinforcement learning, taking into account the variation in LEO network topology. By introducing NoisyNet, Dueling, and N-step learning, we improve the model’s generalization ability and reduce the state space, thus enhancing convergence speed while reducing decision and training time. Experimental results demonstrate

关键词：

来源：评论

学校读者我要写书评

暂无评论

LCGen: mining in low-certainty generation for view-consistent text-to-3D 24

LCGen: mining in low-certainty generation for view-consisten...

引用

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Zeng Tao Tong Yang Junxiong Lin Xinji Mai Haoran Wang Beining Wang Enyu Zhou Yan Wang Wenqiang Zhang Shanghai Engineering Research Center of AI & Robotics Academy for Engineering & Technology Fudan University Shanghai China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China School of Computer Science Fudan University Shanghai China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China and Engineering Research Center of AI & Robotics Ministry of Education Academy for Engineering & Technology Fudan University Shanghai China

ISBN: (纸本)9798331314385

The Janus Problem is a common issue in SDS-based text-to-3D methods. Due to view encoding approach and 2D diffusion prior guidance, the 3D representation model tends to learn content with higher certainty from each perspective, leading to view inconsistency. In this work, we first model and analyze the problem, visualizing the specific causes of the Janus Problem, which are associated with discrete view encoding and shared priors in 2D lifting. Based on this, we further propose the LCGen method, which guides text-to-3D to obtain different priors with different certainty from various viewpoints, aiding in view-consistent generation. Experiments have proven that our LCGen method can be directly applied to different SDS-based text-to-3D methods, alleviating the Janus Problem without introducing additional information, increasing excessive training burden, or compromising the generation effect. Project page is https://***/zeng-tao/LCGen.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Student Behavior Analysis via YOLOv5 with Coordinate Attention 9th

Real-Time Student Behavior Analysis via YOLOv5 with Coordina...

引用

9th International Symposium on Artificial Intelligence and Robotics, ISAIR 2024

作者： Ma, Shuai Chang, Heyou Yang, Xinru Chen, Quan Han, Jian Key Laboratory of Intelligent Information Processing Nanjing XiaoZhuang University Nanjing China School of Information and Engineering Nanjing XiaoZhuang University Nanjing China School of Computer Science Nanjing University of Information Science and Technology Nanjing China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9789819629138

The detection and recognition of student behavior play a pivotal role in the context of smart classrooms. However, conventional methods often encounter performance degradation due to challenges such as occlusion, data diversity, and complexity. To effectively addresses these issues, we propose a method that integrates YOLOv5 with coordinate attention mechanism and GhostConv for analyzing students' behavior. Specifically, the coordinate attention module enhances the localization ability of the proposed method by addressing problems related to target scale variations and uneven distribution. Additionally, we employ GhostConv to replace conventional convolutional layers in YOLOv5, reducing parameters while improving computational efficiency. To verify the validity of our method, a self-built challenging dataset for real teaching scenarios and Citypersons dataset are selected for the experiment. In comparison to the original YOLOv5, our method has achieved a 14.8% and 5.7% increase in mean average precision rates, with a 19.0% improvement in frames per second. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Delving into Decision-based Black-box Attacks on Semantic Segmentation

arXiv

引用

arXiv 2024年

作者： Chen, Zhaoyu Shan, Zhengyang Chang, Jingwen Jiang, Kaixun Yang, Dingkang Cheng, Yiting Zhang, Wenqiang Shanghai Engineering Research Center of AI & Robotics Academy for Engineering & Technology Fudan University China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China

Semantic segmentation is a fundamental visual task that finds extensive deployment in applications with security-sensitive considerations. Nonetheless, recent work illustrates the adversarial vulnerability of semantic segmentation models to white-box attacks. However, its adversarial robustness against black-box attacks has not been fully explored. In this paper, we present the first exploration of black-box decision-based attacks on semantic segmentation. First, we analyze the challenges that semantic segmentation brings to decision-based attacks through the case study. Then, to address these challenges, we first propose a decision-based attack on semantic segmentation, called Discrete Linear Attack (DLA). Based on random search and proxy index, we utilize the discrete linear noises for perturbation exploration and calibration to achieve efficient attack efficiency. We conduct adversarial robustness evaluation on 5 models from Cityscapes and ADE20K under 8 attacks. DLA shows its formidable power on Cityscapes by dramatically reducing PSPNet’s mIoU from an impressive 77.83% to a mere 2.14% with just 50 queries. 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

Motion Deep Association for spatio-temporal object tracking

引用

Pattern Recognition 2025年 168卷

作者： Guo, Husheng Du, Xihao Wang, Wenjian School of Computer and Information Technology Shanxi University Shanxi Taiyuan030006 China Key Lab of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Shanxi Taiyuan030006 China

Most approaches regard visual object tracking as a template matching problem, heavily relying on complex mechanisms to utilize temporal information between consecutive video frames, while neglecting the object's motion information, which in turn affects tracking accuracy. To address this, we propose MDATrack, a Transformer-based approach that includes a spatio-aware fusion encoder, a temporal motion association encoder, and a spatio-temporal decoder for robust tracking. Firstly, the spatio-aware fusion encoder captures multi-level features of template and search images through global interaction and adaptively fuses these features using a cross-attention mechanism, providing a comprehensive feature representation for the model. Secondly, the temporal motion association encoder establishes motion associations for the object's positions in historical frames using temporal attention, capturing dynamic changes in object location. Finally, the spatio-temporal decoder establishes feature associations of the object in the temporal and spatial dimensions to generate accurate object positions. Our experiments demonstrate that MDATrack significantly outperforms existing methods, achieving state-of-the-art results in real-time tracking scenarios. © 2025 Elsevier Ltd

关键词： Template matching

来源：评论

学校读者我要写书评

暂无评论

Character-Level Street View Text Spotting Based on Deep Multisegmentation Network for Smarter Autonomous Driving

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2022年第2期3卷 297-308页

作者： Zhang, Chongsheng Tao, Yuefeng Du, Kai Ding, Weiping Wang, Bin Liu, Ji Wang, Wei Henan Provincial Key Laboratory of Big Data Analysis and Processing Laboratory of the Yellow River Cultural Heritage Henan University Kaifeng475001 China School of Information Science and Technology Nantong University Nantong226019 China School of Electrical Engineering Zhejiang University Hangzhou310058 China Big Data Lab Baidu Inc. Beijing100044 China School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China

Urban scenes are full of street entities with sign boards. Therefore, in autonomous driving, street view text spotting techniques will play a significant role in the precise understanding of surrounding scenes during driving, because texts contained in the images usually provide important clues for accurate image understanding, while it is often ambiguous for existing computer vision algorithms to understand scene images without texts. In this work, we propose a Multi-Segmentation network for character-level scene Text Detection (MSTD). The MSTD introduces a densely connected atrous spatial pyramid pooling module to enlarge the receptive field of the feature extraction layer, so as to localize long as well as large-sized text instances. Moreover, it devises a double segmentation subnetwork to utilize two independent but inherently complementary losses to co-optimize the network and increase the reliability of the confidence scores in predicting the text/nontext areas. With the character instances detected by the MSTD, one can easily perform scene text spotting with classic object recognition networks such as ResNet and DenseNet. We carried out extensive experiments on nine scene text datasets to demonstrate the outstanding performance of the MSTD on character-level and line-level text instance localization and scene text recognition, where the MSTD significantly outperforms the state-of-the-art scene text detection methods and the sequence-to-sequence-learning-based scene text recognizers. © 2020 IEEE.

关键词： Character recognition

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：