Spatio-Temporal Self-Attention Weighted VLAD Neural Network for Action Recognition

Cheng, Shilei; Xie, Mei; Ma, Zheng; Li, Siqi; Gu, Song; Yang, Feng

doi:10.1587/transinf.2020edl0002

Cited by 4 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The HMDB51 dataset contains a total of 6,849 videos, demonstrating a total of 51 actions, each action contains at least 51 videos, and the resolution of these videos is 320 ∗ 240 [ 27 ]. The data in HMDB51 is mainly from YouTube, Google Video, and other websites.…”

Section: Design Of Lightweight Smart Home System For Middle-aged and ...mentioning

confidence: 99%

The Design of the Lightweight Smart Home System and Interaction Experience of Products for Middle-Aged and Elderly Users in Smart Cities

Ji¹

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The research aims to improve the comfort and safety of the smart home by adding a motion recognition algorithm to the smart home system. First, the research status of motion recognition is introduced. Second, based on the requirements of the smart home system, a smart home system is designed for middle-aged and elderly users. The software system in this system includes intelligent control subsystems, intelligent monitoring subsystems, and intelligent protection subsystems. Finally, to increase the security of the smart home, the intelligent monitoring subsystem is improved, and an intelligent security subsystem is proposed based on a small-scale motion detection algorithm. The system uses three three-dimensional (3D) convolutional neural networks (CNNs) to extract three image features, so that the data information in the video can be fully extracted. The performance of the proposed intelligent security subsystem based on a small-scale motion detection algorithm is compared and analyzed. The research results show that the accuracy of the system on the University of Central Florida (UCF101) dataset is 94.64%, and the accuracy on the HMDB51 dataset is 90.11%, which is similar to other advanced algorithms. Observing whether there are dangers such as falling inside and outside the family through motion recognition technology has very important application significance for protecting people’s personal safety, life, and health.

show abstract

Section: Design Of Lightweight Smart Home System For Middle-aged and ...mentioning

confidence: 99%

The Design of the Lightweight Smart Home System and Interaction Experience of Products for Middle-Aged and Elderly Users in Smart Cities

Ji¹

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Pose MoTion (PoTion) [10], Pose-Action 3D Machine (PA3D) [34], and Pose-Guided Inflated 3D ConvNet (PI3D) [35] achieve better performance by fusing the pose network and I3D. ST-SAWVLAD [36] proposes a spatio-temporal self-attention weighted VLAD model that follows spatio-temporal selfattention operations to improve network performance. Zheng et al [37] obtained the state-of-the-art performance by fusing global and local detailed information of action.…”

Section: Two-stream Networkmentioning

confidence: 99%

SRI3D: Two‐stream inflated 3D ConvNet based on sparse regularization for action recognition

Yang

Zhang

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

Although most state‐of‐the‐art action recognition models have adopted a two‐stream 3D convolutional structure as a backbone network, few works have studied the impact of loss functions on action recognition models. In addition, sparsity is used as a key prior knowledge in many fields. However, as far as is known, no one has studied the influence of the sparsity of network output on the output of deep learning‐based action recognition models. Therefore, this paper proposes a novel two‐stream inflated 3D ConvNet based on the sparse regularization (SRI3D) model for action recognition. In order to allow the network to learn the sparsity of output, the ℓ1 norm is embedded in the loss function in regularization form in a plug‐and‐play manner. It can make the classification result after the fusion of the two‐stream network only be the category with the highest confidence in one of the streams and not the other cases. The proposed loss function based on sparse regularization makes the output vector of the neural network as sparse as possible so that the classification results will not be ambiguous. Experimental results show that compared with other state‐of‐the‐art models, this SRI3D has a competitive advantage on Kinetics‐400, Something‐Something V2, UCF‐101 and HMDB‐51.

show abstract

Temporal Knowledge Graph Embedding for Link Prediction

Zhang

Deng

Meng³

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Spatio-Temporal Self-Attention Weighted VLAD Neural Network for Action Recognition

Cited by 4 publications

References 13 publications

The Design of the Lightweight Smart Home System and Interaction Experience of Products for Middle-Aged and Elderly Users in Smart Cities

The Design of the Lightweight Smart Home System and Interaction Experience of Products for Middle-Aged and Elderly Users in Smart Cities

SRI3D: Two‐stream inflated 3D ConvNet based on sparse regularization for action recognition

Temporal Knowledge Graph Embedding for Link Prediction

Contact Info

Product

Resources

About