Imperial College London
Alternate

ProfessorWilliamKnottenbelt

Faculty of Engineering, Department of Computing

Professor of Applied Quantitative Analysis
 
 
 
//

Contact

 

+44 (0)20 7594 8331w.knottenbelt Website

 
 
//

Location

 

E363ACE ExtensionSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Mora:2017:10.1109/CVPRW.2017.27,
author = {Mora, SV and Knottenbelt, WJ},
doi = {10.1109/CVPRW.2017.27},
pages = {170--178},
publisher = {IEEE},
title = {Deep learning for domain-specific action recognition in tennis},
url = {http://dx.doi.org/10.1109/CVPRW.2017.27},
year = {2017}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Recent progress in sports analytics has been driven by the availability of spatio-temporal and high level data. Video-based action recognition in sports can significantly contribute to these advances. Good progress has been made in the field of action recognition but its application to sports mainly focuses in detecting which sport is being played. In order for action recognition to be useful in sports analytics a finer-grained action classification is needed. For this reason we focus on the fine-grained action recognition in tennis and explore the capabilities of deep neural networks for this task. In our model, videos are represented as sequences of features, extracted using the well-known Inception neural network, trained on an independent dataset. Then a 3-layered LSTM network is trained for the classification. Our main contribution is the proposed neural network architecture that achieves competitive results in the challenging THETIS dataset, comprising videos of tennis actions.
AU  - Mora,SV
AU  - Knottenbelt,WJ
DO  - 10.1109/CVPRW.2017.27
EP  - 178
PB  - IEEE
PY  - 2017///
SN  - 2160-7508
SP  - 170
TI  - Deep learning for domain-specific action recognition in tennis
UR  - http://dx.doi.org/10.1109/CVPRW.2017.27
UR  - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000426448300021&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR  - http://hdl.handle.net/10044/1/106118
ER  -
Download