相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Environmental Sciences
Kai Hu et al.
Summary: A multi-branch convolutional attention network (MCANet) is proposed for accurate segmentation of cloud/snow regions in remote sensing imagery. The network utilizes a double-branch structure to extract spatial and semantic information, improving feature extraction capability. A fusion module is suggested to correctly merge feature information from multiple branches, and a new decoder module is constructed to enhance information recovery and refine segmentation boundaries.
Article
Computer Science, Information Systems
Zhigang Tu et al.
Summary: In recent years, graph convolutional networks (GCNs) have become increasingly important in skeleton-based human action recognition. However, most existing GCN-based methods have limitations in terms of considering the correlation between joints and bones and reliance on labeled training data. To address these issues, we propose a novel semi-supervised skeleton-based action recognition method that incorporates a correlation-driven joint-bone fusion graph convolutional network (CD-JBF-GCN) as an encoder and a pose prediction head as a decoder. Our model achieves state-of-the-art performance on two popular datasets, demonstrating its effectiveness in semi-supervised action recognition.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Environmental Sciences
Kai Hu et al.
Summary: This study proposes a multi-scale feature aggregation network for water area segmentation. By designing a deep feature extraction module and a multi-branch aggregation module, it accurately identifies small tributaries in water area images and extracts deep semantic information, achieving improved segmentation accuracy.
Article
Chemistry, Multidisciplinary
Kai Hu et al.
Summary: This paper proposes a novel multi-scale time sampling module and a deep spatiotemporal feature extraction module to enhance the accuracy of human motion recognition network. Comparative experiments show that the proposed method achieves performance improvement on two datasets.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Tianshan Liu et al.
Summary: The article proposes a method for recognizing group activities based on visual-semantic graph neural network and pose-position attentive learning. The method improves the recognition performance of group activities by constructing a bi-modal visual graph and a semantic graph, and utilizing pose and position information for attention aggregation.
Article
Computer Science, Artificial Intelligence
Ce Li et al.
Summary: A new method named memory attention networks (MANs) is proposed to address the complex variations of skeleton joints in 3-D spatiotemporal space for action recognition. By using the temporal attention recalibration module (TARM) and spatiotemporal convolution module (STCM), and introducing the collaborative memory fusion module (CMFM), the performance is significantly improved.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Abdelrahman Mostafa et al.
Summary: This work introduces compact hyperbolic space ST-GCNs, which outperform their corresponding Euclidean counterparts, improve the performance of large Euclidean models, reduce the total number of model parameters and model size. Experimental results demonstrate the promising performance of these hyperbolic networks in human action recognition tasks.
2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Yue Zhao et al.
Summary: This paper introduces a simple and general approach called Bridge Attention to address the issue of heavy feature compression in attention mechanism research. By integrating features from previous layers and promoting information interchange, BA-Net effectively enhances the performance of neural networks. The study also discovered that bridging convolution outputs with BN inside each block can obtain better attention. Extensive evaluation on computer vision tasks demonstrates the superiority of the proposed approach in terms of accuracy and computing efficiency.
COMPUTER VISION, ECCV 2022, PT XXI
(2022)
Article
Computer Science, Artificial Intelligence
Jiaxu Zhang et al.
Summary: The authors propose a novel SATD-GCN for skeleton-based action recognition, which consists of SAP and TDGC components for selecting beneficial human body joints and extracting temporal features at different scales. Experimental results show that the method outperforms existing approaches.
CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Shang-Hua Gao et al.
Summary: This paper introduces a novel building block for CNNs, Res2Net, which represents multiscale features within one single residual block by constructing hierarchical residual-like connections. The Res2Net enhances the representation of multiscale features in various vision tasks and consistently outperforms baseline models in performance gains.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
Wei Peng et al.
Summary: Graph Convolutional Network (GCN) is successfully applied to skeleton-based action recognition, however, lacking pooling operations leads to flat architectures, Tripool offers a solution for this issue.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Artificial Intelligence
Wei Peng et al.
Summary: This article discusses the task of action recognition based on skeleton data and the mainstream framework ST-GCN, proposing a simple and effective strategy in experiments to capture global graph correlations, reducing model complexity, and achieving superior performance.
Article
Computer Science, Artificial Intelligence
Chiara Plizzari et al.
Summary: In this study, a novel Spatial-Temporal Transformer network (ST-TR) is proposed to model dependencies between joints using the Transformer self-attention operator. The ST-TR model utilizes a Spatial Self Attention module (SSA) to understand intra-frame interactions between different body parts, and a Temporal Self-Attention module (TSA) to model inter-frame correlations, achieving good performance in human activity recognition tasks.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Negar Heidari et al.
Summary: Graph convolutional networks have shown promising results in skeleton-based human action recognition by modeling skeletons as a spatio-temporal graph, with recent methods focusing on learning the graph structure using spatial attention. This paper proposes symmetric spatial attention to better capture the symmetric property of human body joints during actions, and introduces the spatio-temporal bilinear network (ST-BLN) as a more flexible alternative to predefined adjacency matrices. Experimental results demonstrate that all three models perform equally well, with the ST-BLN offering increased efficiency.
2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)
(2021)
Article
Engineering, Electrical & Electronic
Wei Peng et al.
Summary: This paper introduces a novel and flexible graph deconvolution technique, ST-GDN, to provide better message aggregation by removing the embedding redundancy of input graphs and alleviate the issues in spatial-temporal graph convolutional networks. Extensive experiments show that ST-GDN consistently improves performance and significantly reduces model size on the most challenging benchmarks.
IEEE SIGNAL PROCESSING LETTERS
(2021)
Article
Computer Science, Artificial Intelligence
Xikun Zhang et al.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2020)
Article
Computer Science, Artificial Intelligence
Pengfei Zhang et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Lei Shi et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Chenyang Si et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Article
Computer Science, Artificial Intelligence
Jun Liu et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2018)
Article
Computer Science, Artificial Intelligence
Pichao Wang et al.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Tae Soo Kim et al.
2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Jun Liu et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Proceedings Paper
Computer Science, Information Systems
Ionut C. Duta et al.
MULTIMEDIA MODELING (MMM 2017), PT I
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Harshala Gammulle et al.
2017 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2017)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Qiuhong Ke et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Article
Engineering, Biomedical
Andru P. Twinanda et al.
INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY
(2015)
Proceedings Paper
Computer Science, Artificial Intelligence
Relja Arandjelovic et al.
2013 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2013)
Article
Computer Science, Artificial Intelligence
Franco Scarselli et al.
IEEE TRANSACTIONS ON NEURAL NETWORKS
(2009)