检索结果-内蒙古大学图书馆

8th International Conference on Automation, Control and Robotics Engineering, CACRE 2023

作者： Wang, Liangliang Huang, Chengxi Chen, Xinwei Wuhan University of Technology School of Computer Science and Artificial Intelligence Luoshi Road 122 Wuhan430070 China -HIT Research Institute of Engineering and Technology Building 9 Software Park Quanzhou362008 China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou350121 China

ISBN: (纸本)9798350302776

Existing action detection approaches do not take spatio-temporal structural relationships of action clips into account, which leads to a low applicability in real-world scenarios and can benefit detecting if exploited. To this end, this paper proposes to formulate the action detection problem as a reinforcement learning process which is rewarded by observing both the clip sampling and classification results via adjusting the detection schemes. In particular, our framework consists of a heterogeneous graph convolutional network to represent the spatio-temporal features capturing the inherent relation, a policy network which determines the probabilities of a predefined action sampling spaces, and a classification network for action clip recognition. We accomplish the network joint learning by considering the temporal intersection over union and Euclidean distance between detected clips and ground-truth. Experiments on ActivityNet v1.3 and THUMOS14 demonstrate our method. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Recognizing Human-object Interactions for a Home Assistive Robot 8

Recognizing Human-object Interactions for a Home Assistive R...

引用

8th International Conference on Automation, Control and Robotics Engineering, CACRE 2023

作者： Wang, Liangliang Huo, Guanglei Chen, Xinwei Huang, Chengxi Wuhan University of Technology School of Computer Science and Artificial Intelligence Luoshi Road 122 Wuhan430070 China -HIT Research Institute of Engineering and Technology Building 9 Software Park Quanzhou362008 China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou350121 China

ISBN: (纸本)9798350302776

To enable robots to understand a specific assistive task during human-robot interactions under complex home scenes, at the center is the problem of human-object interaction (HOI) recognition. In particular, aiming at identifying efficiently, this paper proposes a graph convolutional network (GCN) by considering the similarity and proximity of human and object nodes, based on which the geometric positions and morphological relationships are explored. Also, a supplementary convolutional neural network (CNN) is fused to GCN to extract the global semantic features, which also ensures the recognition applicability for the cases where detectors fall into failure. Experiments on V-COCO demonstrate our approach, and results in real-world scenes on our assistive robot - Xiaozhi II verify its robustness. © 2023 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

An Efficient Particle YOLO Detector for Urine Sediment Detection 4th

An Efficient Particle YOLO Detector for Urine Sediment Dete...

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Chen, Zejian Hu, Rong Chen, Fukun Fan, Haoyi Ching, Fum Yew Li, Zuoyong Su, Shimei Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fujian University of Technology Fujian Fuzhou350118 China School of Computer and Artificial Intelligence Zhengzhou University Henan Zhengzhou450001 China School of Computer Sciences Universiti Sains Malaysia Penang11800 Malaysia Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fujian Fuzhou350121 China School of Electrical Engineering Zhengzhou University Henan Zhengzhou450001 China

ISBN: (纸本)9783031201011

Urine sediment detection is an essential aid in assessing kidney health. Traditional machine learning approaches treat urine sediment particle detection as an image classification task, segmenting particles for detection based on information such as edges or thresholds. However, the segmentation of sediment particles is complex due to the low contrast and weak edge characteristics of urine sediment images. In this paper, we consider urine sediment particle detection as a object detection task and propose the YOLOv5s-CBL, a detector dedicated to particle detection. Specifically, to mitigate the impact of background noise on detection accuracy, we inherit CBAM on the YOLOv5s model to help the network filter useless noise information and find regions of interest to extract target features. Then, we expand the original three-scale feature layer to improve the sensitivity of the model to larger-scale target sediment particles. Finally, we use the BiFPN structure instead of the original PANet combined with the FPN structure, which can more effectively fuse multiple different scales of information to improve the detection performance of the model. We compared state-of-the-art methods on two real-world datasets, and the experimental results demonstrated the effectiveness of YOLOv5s-CBL. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Mamba-VA: A Mamba-based Approach for Continuous Emotion Recognition in Valence-Arousal Space

arXiv

引用

arXiv 2025年

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

Continuous Emotion Recognition (CER) plays a crucial role in intelligent human-computer interaction, mental health monitoring, and autonomous driving. Emotion modeling based on the Valence-Arousal (VA) space enables a more nuanced representation of emotional states. However, existing methods still face challenges in handling long-term dependencies and capturing complex temporal dynamics. To address these issues, this paper proposes a novel emotion recognition model, Mamba-VA, which leverages the Mamba architecture to efficiently model sequential emotional variations in video frames. First, the model employs a Masked Autoencoder (MAE) to extract deep visual features from video frames, enhancing the robustness of temporal information. Then, a Temporal Convolutional Network (TCN) is utilized for temporal modeling to capture local temporal dependencies. Subsequently, Mamba is applied for long-sequence modeling, enabling the learning of global emotional trends. Finally, a fully connected (FC) layer performs regression analysis to predict continuous valence and arousal values. Experimental results on the Valence-Arousal (VA) Estimation task of the 8th competition on Affective Behavior Analysis in-the-wild (ABAW) demonstrate that the proposed model achieves valence and arousal scores of 0.5362 (0.5036) and 0.4310 (0.4119) on the validation (test) set, respectively, outperforming the baseline. The source code is available on GitHub: https://***/FreedomPuppy77/Charon. Copyright © 2025, The Authors. All rights reserved.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-...

引用

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

作者： Kaijun Deng Dezhi Zheng Jindong Xie Jinbao Wang Weicheng Xie Linlin Shen Siyang Song Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Department of Computer Science University of Exeter

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code is available at https://***/CVI-SZU/DEGSTalk.

关键词： Hair Training Three-dimensional displays Dynamics Signal processing Rendering (computer graphics) Noise measurement Speech processing Faces Videos

来源：评论

学校读者我要写书评

暂无评论

STGE-Former: Spatial-Temporal Graph-Enhanced Transformer for EEG-Based Major Depressive Disorder Detection

STGE-Former: Spatial-Temporal Graph-Enhanced Transformer for...

引用

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

作者： Yu Chen Chunfeng Yang School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Southeast University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Applying deep learning techniques to Electroencephalogram (EEG) data has shown great potential in the field of depression detection. However, existing EEG-based depression detection models face challenges: they struggle to capture the complex spatiotemporal dependencies and the complementary nature of spatiotemporal information in EEG data; functional connectivity between brain regions is not sufficiently considered. To address these issues, we propose a new Spatial-Temporal Graph-Enhanced Transformer, named STGE-Former. Raw EEG signals are first mapped to Spatial-Temporal Shared Embeddings, then processed by the Spatial Attention Stream and the Temporal Graph-Enhanced Attention Stream to extract spatiotemporal complementary information, and finally classified through a classification head. Experimental results on the MODMA dataset show that our model outperforms existing methods in the task of EEG-Based MDD Detection. STGE-Former provides a promising approach for automatic depression detection. The code is available at https://***/RockyChen0205/STGE-Former.

关键词： Deep learning Electric potential Signal processing Depression Transformers Brain modeling Electroencephalography Spatiotemporal phenomena Speech processing Faces

来源：评论

学校读者我要写书评

暂无评论

Leveraging Tumor Heterogeneity: Heterogeneous Graph Representation Learning for Cancer Survival Prediction in Whole Slide Images 38

Leveraging Tumor Heterogeneity: Heterogeneous Graph Represen...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Wu, Junxian Ke, Xinyi Jiang, Xiaoming Wu, Huanwen Kong, Youyong Shao, Lizhi School of Internet Anhui University China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University China Department of Pathology State Key Laboratory of Complex Severe and Rare Disease Molecular Pathology Research Center Peking Union Medical College Hospital Chinese Academy of Medical Sciences Peking Union Medical College Beijing China School of Bioinformatics Chongqing University of Post and Telecommunications China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education China

Survival prediction is a significant challenge in cancer management. Tumor microenvironment is a highly sophisticated ecosystem consisting of cancer cells, immune cells, endothelial cells, fibroblasts, nerves and extracellular matrix. The intratumor heterogeneity and the interaction across multiple tissue types profoundly impact the prognosis. However, current methods often neglect the fact that the contribution to prognosis differs with tissue types. In this paper, we propose ProtoSurv, a novel heterogeneous graph model for WSI survival prediction. The learning process of ProtoSurv is not only driven by data but also incorporates pathological domain knowledge, including the awareness of tissue heterogeneity, the emphasis on prior knowledge of prognostic-related tissues, and the depiction of spatial interaction across multiple tissues. We validate ProtoSurv across five different cancer types from TCGA (i.e., BRCA, LGG, LUAD, COAD and PAAD), and demonstrate the superiority of our method over the state-of-the-art methods. Source code is available at https://***/wjx-error/ProtoSurv. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Big-Moe: Bypassing Isolated Gating For Generalized Multimodal Face Anti-Spoofing

Big-Moe: Bypassing Isolated Gating For Generalized Multimoda...

引用

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

作者： Yingjie Ma Zitong Yu Xun Lin Weicheng Xie Linlin Shen College of Computer Science and Software Engineering Shenzhen University Great Bay University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In the domain of facial recognition security, multimodal Face Anti-Spoofing (FAS) is essential for countering presentation attacks. However, existing technologies encounter challenges due to modality biases and imbalances, as well as domain shifts. Our research introduces a Mixture of Experts (MoE) model to address these issues effectively. We identified three limitations in traditional MoE approaches to multimodal FAS: (1) Coarse-grained experts’ inability to capture nuanced spoofing indicators; (2) Gated networks’ susceptibility to input noise affecting decision-making; (3) MoE’s sensitivity to prompt tokens leading to overfitting with conventional learning methods. To mitigate these, we propose the Bypass Isolated Gating MoE (BIG-MoE) framework, featuring: (1) Fine-grained experts for enhanced detection of subtle spoofing cues; (2) An isolation gating mechanism to counteract input noise; (3) A novel differential convolutional prompt bypass enriching the gating network with critical local features, thereby improving perceptual capabilities. Extensive experiments on four benchmark datasets demonstrate significant generalization performance improvement in multimodal FAS task. The code is released at https://***/murInJ/BIG-MoE.

关键词： Convolutional codes Sensitivity Convolution Face recognition Noise Logic gates Feature extraction Security Speech processing Overfitting

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Policies of Subgoals for Safe Deep Reinforcement Learning 2nd

Hierarchical Policies of Subgoals for Safe Deep Reinforcem...

引用

2nd International Conference on Ubiquitous Security, UbiSec 2022

作者： Yu, Fumin Gao, Feng Yuan, Yao Xing, Xiaofei Dai, Yinglong College of Information Science and Engineering Hunan Normal University Changsha410081 China School of Computer Science and Cyber Engineering Guangzhou University Guangzhou510006 China College of Liberal Arts and Sciences National University of Defense Technology Changsha410073 China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Changsha410081 China

ISBN: (纸本)9789819902712

Reinforcement learning is a machine learning method that relies on the agent to learn by trial and error to solve decision optimization problems. It is well known that an agent based on deep reinforcement learning in complex environments is difficult to train. Moreover, the agent will generate unsafe and strange actions due to the lack of sufficient reward feedback from the environment. To make the agent converge to a better policy and make its behavior safer and more controllable under sparse rewards, we propose a subgoal embedding method based on prior knowledge and hierarchical strategy that can make the training process converge faster. The subgoal embedding method can be combined with existing reinforcement learning methods. In this paper, we combine the subgoal embedding method with REINFORCE algorithm and PPO(Proximal Policy Optimization) algorithm to test the method in the MiniGrid-Doorkey game environment of the gym platform. The experiments demonstrate the effectiveness of the subgoal embedding method. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space

arXiv

引用

arXiv 2025年

作者： Pan, Linchao Gao, Can Zhou, Jie Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China

Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from known classes, called closed-set noise. However, in real-world scenarios, noisy labels from similar unknown classes, i.e., open-set noise, may occur during the training and inference stage. Such open-world noisy labels may significantly impact the performance of LNL methods. In this study, we propose a novel dual-space joint learning method to robustly handle the open-world noise. To mitigate model overfitting on closed-set and open-set noises, a dual representation space is constructed by two networks. One is a projection network that learns shared representations in the prototype space, while the other is a One-Vs-All (OVA) network that makes predictions using unique semantic representations in the class-independent space. Then, bi-level contrastive learning and consistency regularization are introduced in two spaces to enhance the detection capability for data with unknown classes. To benefit from the memorization effects across different types of samples, class-independent margin criteria are designed for sample identification, which selects clean samples, weights closed-set noise, and filters open-set noise effectively. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods and achieves an average accuracy improvement of 4.55% and an AUROC improvement of 6.17% on CIFAR80N. Copyright © 2025, 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：