Crossmark

MLKD-CLIP: Multi-layer Feature Knowledge Distillation of CLIP for Open-vocabulary Action Recognition

Published Online: 2025-05-16

Published Print: 2025-08

Authors

Wang, Jingjing

Ye, Junyong

Liu, Xinyuan

Li, Youwei

Xu, Guangyi

Zheng, Chaoming
Funding

Funding for this research was provided by:

National Key Research and Development Program of China (2020YFC1522900)

National Key Research and Development Program of China (2020YFC1522900)

National Key Research and Development Program of China (2020YFC1522900)

National Key Research and Development Program of China (2020YFC1522900)

National Key Research and Development Program of China (2020YFC1522900)

National Key Research and Development Program of China (2020YFC1522900)

Chongqing Technological Innovation and Application Development Project (cstc2021jscx-gksbX0056)

Chongqing Technological Innovation and Application Development Project (cstc2021jscx-gksbX0056)

Chongqing Technological Innovation and Application Development Project (cstc2021jscx-gksbX0056)

Chongqing Technological Innovation and Application Development Project (cstc2021jscx-gksbX0056)

Chongqing Technological Innovation and Application Development Project (cstc2021jscx-gksbX0056)

Chongqing Technological Innovation and Application Development Project (cstc2021jscx-gksbX0056)
License Information

Text and Data Mining valid from 2025-05-16

Version of Record valid from 2025-05-16
More Information

Article History

Received: 25 October 2024

Accepted: 28 April 2025

First Online: 16 May 2025

Declarations

:

: The authors declare no competing interests.

Document is current