Exploration of Network Optimization Strategies Based On the TSN Model

Y Yuan, Z Ruan, Y Wei, T Jiang - Proceedings of the 2023 6th …, 2023 - dl.acm.org
With the widespread application of deep learning in the field of computer vision, deep
learning-based video behavior recognition models have become important tools for video …

Temporal pyramid pooling-based convolutional neural network for action recognition

P Wang, Y Cao, C Shen, L Liu… - IEEE Transactions on …, 2016 - ieeexplore.ieee.org
Encouraged by the success of convolutional neural networks (CNNs) in image classification,
recently much effort is spent on applying the CNNs to the video-based action recognition …

An improved action recognition network with temporal extraction and feature enhancement

J Jiang, Y Zhang - IEEE Access, 2022 - ieeexplore.ieee.org
Image classification and action recognition are both active research topics in the field of
computer vision. However, the development of action recognition is rather slow compared …

BQN: Busy-Quiet Net Enabled by Motion Band-Pass Module for Action Recognition

G Huang, AG Bors - IEEE Transactions on Image Processing, 2022 - ieeexplore.ieee.org
A rich video data representation can be realized by means of spatio-temporal frequency
analysis. In this research study we show that a video can be disentangled, following the …

Spatiotemporal distilled dense-connectivity network for video action recognition

W Hao, Z Zhang - Pattern Recognition, 2019 - Elsevier
Two-stream convolutional neural networks show great promise for action recognition tasks.
However, most two-stream based approaches train the appearance and motion …

Temporal transformer networks with self-supervision for action recognition

Y Zhang, J Li, N Jiang, G Wu, H Zhang… - IEEE Internet of …, 2023 - ieeexplore.ieee.org
In recent years, Internet of Things (IoT) has made rapid development, and IoT devices are
developing toward intelligence. IoT terminal devices represented by surveillance cameras …

Multi-Stream Single Network: Efficient Compressed Video Action Recognition With a Single Multi-Input Multi-Output Network

H Terao, W Noguchi, H Iizuka, M Yamamoto - IEEE Access, 2024 - ieeexplore.ieee.org
Compressed video action recognition classifies actions using multiple features stored in
compressed videos to omit the decoding process for RGB frames and shorten the …

If-ttn: Information fused temporal transformation network for video action recognition

K Yang, P Qiao, D Li, Y Dou - arXiv preprint arXiv:1902.09928, 2019 - arxiv.org
Effective spatiotemporal feature representation is crucial to the video-based action
recognition task. Focusing on discriminate spatiotemporal feature learning, we propose …

Hierarchical Hourglass Convolutional Network for Efficient Video Classification

Y Tan, Y Hao, H Zhang, S Wang, X He - Proceedings of the 30th ACM …, 2022 - dl.acm.org
Videos naturally contain dynamic variation over the temporal axis, which will result in the
same visual clues (eg, semantics, objects) changing their scale, position, and perspective …

[HTML][HTML] Knowledge Distillation in Video-Based Human Action Recognition: An Intuitive Approach to Efficient and Flexible Model Training

F Camarena, M Gonzalez-Mendoza, L Chang - Journal of Imaging, 2024 - mdpi.com
Training a model to recognize human actions in videos is computationally intensive. While
modern strategies employ transfer learning methods to make the process more efficient, they …