Home > Research > Publications & Outputs > System-Status-Aware Adaptive Network for Online...

Links

Text available via DOI:

View graph of relations

System-Status-Aware Adaptive Network for Online Streaming Video Understanding

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

System-Status-Aware Adaptive Network for Online Streaming Video Understanding. / Foo, Lin Geng; Gong, Jia; Fan, Zhipeng et al.
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society Press, 2023. p. 10514-10523 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2023-June).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Foo, LG, Gong, J, Fan, Z & Liu, J 2023, System-Status-Aware Adaptive Network for Online Streaming Video Understanding. in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2023-June, IEEE Computer Society Press, pp. 10514-10523, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, Canada, 18/06/23. https://doi.org/10.1109/CVPR52729.2023.01013

APA

Foo, L. G., Gong, J., Fan, Z., & Liu, J. (2023). System-Status-Aware Adaptive Network for Online Streaming Video Understanding. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 10514-10523). (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2023-June). IEEE Computer Society Press. https://doi.org/10.1109/CVPR52729.2023.01013

Vancouver

Foo LG, Gong J, Fan Z, Liu J. System-Status-Aware Adaptive Network for Online Streaming Video Understanding. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society Press. 2023. p. 10514-10523. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). Epub 2023 Jun 17. doi: 10.1109/CVPR52729.2023.01013

Author

Foo, Lin Geng ; Gong, Jia ; Fan, Zhipeng et al. / System-Status-Aware Adaptive Network for Online Streaming Video Understanding. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society Press, 2023. pp. 10514-10523 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

Bibtex

@inproceedings{f660068a6f2a45808f623ae08a42d11b,
title = "System-Status-Aware Adaptive Network for Online Streaming Video Understanding",
abstract = "Recent years have witnessed great progress in deep neural networks for real-time applications. However, most existing works do not explicitly consider the general case where the device's state and the available resources fluctuate over time, and none of them investigate or address the impact of varying computational resources for online video understanding tasks. This paper proposes a System-status-aware Adaptive Network (SAN) that considers the device's real-time state to provide high-quality predictions with low delay. Usage of our agent's policy improves efficiency and robustness to fluctuations of the system status. On two widely used video understanding tasks, SAN obtains state-of-the-art performance while constantly keeping processing delays low. Moreover, training such an agent on various types of hardware configurations is not easy as the labeled training data might not be available, or can be computationally prohibitive. To address this challenging problem, we propose a Meta Self-supervised Adaptation (MSA) method that adapts the agent's policy to new hardware configurations at test-time, allowing for easy deployment of the model onto other unseen hardware platforms.",
keywords = "Video: Action and event understanding",
author = "Foo, {Lin Geng} and Jia Gong and Zhipeng Fan and Jun Liu",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 ; Conference date: 18-06-2023 Through 22-06-2023",
year = "2023",
month = aug,
day = "22",
doi = "10.1109/CVPR52729.2023.01013",
language = "English",
isbn = "9798350301304",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society Press",
pages = "10514--10523",
booktitle = "2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)",

}

RIS

TY - GEN

T1 - System-Status-Aware Adaptive Network for Online Streaming Video Understanding

AU - Foo, Lin Geng

AU - Gong, Jia

AU - Fan, Zhipeng

AU - Liu, Jun

N1 - Publisher Copyright: © 2023 IEEE.

PY - 2023/8/22

Y1 - 2023/8/22

N2 - Recent years have witnessed great progress in deep neural networks for real-time applications. However, most existing works do not explicitly consider the general case where the device's state and the available resources fluctuate over time, and none of them investigate or address the impact of varying computational resources for online video understanding tasks. This paper proposes a System-status-aware Adaptive Network (SAN) that considers the device's real-time state to provide high-quality predictions with low delay. Usage of our agent's policy improves efficiency and robustness to fluctuations of the system status. On two widely used video understanding tasks, SAN obtains state-of-the-art performance while constantly keeping processing delays low. Moreover, training such an agent on various types of hardware configurations is not easy as the labeled training data might not be available, or can be computationally prohibitive. To address this challenging problem, we propose a Meta Self-supervised Adaptation (MSA) method that adapts the agent's policy to new hardware configurations at test-time, allowing for easy deployment of the model onto other unseen hardware platforms.

AB - Recent years have witnessed great progress in deep neural networks for real-time applications. However, most existing works do not explicitly consider the general case where the device's state and the available resources fluctuate over time, and none of them investigate or address the impact of varying computational resources for online video understanding tasks. This paper proposes a System-status-aware Adaptive Network (SAN) that considers the device's real-time state to provide high-quality predictions with low delay. Usage of our agent's policy improves efficiency and robustness to fluctuations of the system status. On two widely used video understanding tasks, SAN obtains state-of-the-art performance while constantly keeping processing delays low. Moreover, training such an agent on various types of hardware configurations is not easy as the labeled training data might not be available, or can be computationally prohibitive. To address this challenging problem, we propose a Meta Self-supervised Adaptation (MSA) method that adapts the agent's policy to new hardware configurations at test-time, allowing for easy deployment of the model onto other unseen hardware platforms.

KW - Video: Action and event understanding

U2 - 10.1109/CVPR52729.2023.01013

DO - 10.1109/CVPR52729.2023.01013

M3 - Conference contribution/Paper

AN - SCOPUS:85152915163

SN - 9798350301304

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 10514

EP - 10523

BT - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

PB - IEEE Computer Society Press

T2 - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023

Y2 - 18 June 2023 through 22 June 2023

ER -