MediaEval 2019: LRCNs for Stroke Detection in Table Tennis

Recognizing actions in videos is one of the most widely researched tasks in video analytics. Sports action recognition is one such work that has been extensively researched in order to make strategic decisions in athletic training. We present a model to classify strokes made by table tennis players as a part of the 2019 MediaEval Challenge. Our approach extracts features into a spatio-temporal model trained on the MediaEval Sports Video Classification dataset to detect the move made.

[1]  Trevor Darrell,et al.  Long-term recurrent convolutional networks for visual recognition and description , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[3]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[4]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[5]  Ming Yang,et al.  3D Convolutional Neural Networks for Human Action Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Jenny Benois-Pineau,et al.  Sport Action Recognition with Siamese Spatio-Temporal CNNs: Application to Table Tennis , 2018, 2018 International Conference on Content-Based Multimedia Indexing (CBMI).

[7]  Boris Mansencal,et al.  Sports Video Annotation: Detection of Strokes in Table Tennis Task for MediaEval 2019 , 2019, MediaEval.