Fine-Grained Action Detection with RGB and Pose Information using Two Stream Convolutional Networks

by   Leonard Hacker, et al.

As participants of the MediaEval 2022 Sport Task, we propose a two-stream network approach for the classification and detection of table tennis strokes. Each stream is a succession of 3D Convolutional Neural Network (CNN) blocks using attention mechanisms. Each stream processes different 4D inputs. Our method utilizes raw RGB data and pose information computed from MMPose toolbox. The pose information is treated as an image by applying the pose either on a black background or on the original RGB frame it has been computed from. Best performance is obtained by feeding raw RGB data to one stream, Pose + RGB (PRGB) information to the other stream and applying late fusion on the features. The approaches were evaluated on the provided TTStroke-21 data sets. We can report an improvement in stroke classification, reaching 87.3 accuracy, while the detection does not outperform the baseline but still reaches an IoU of 0.349 and mAP of 0.110.


page 2

page 3


Two Stream Network for Stroke Detection in Table Tennis

This paper presents a table tennis stroke detection method from videos. ...

Two-stream convolutional neural network for accurate RGB-D fingertip detection using depth and edge information

Accurate detection of fingertips in depth image is critical for human-co...

Three-Stream 3D/1D CNN for Fine-Grained Action Classification and Segmentation in Table Tennis

This paper proposes a fusion method of modalities extracted from video t...

VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living

Many attempts have been made towards combining RGB and 3D poses for the ...

Image-based Localization using Hourglass Networks

In this paper, we propose an encoder-decoder convolutional neural networ...

Please sign up or login with your details

Forgot password? Click here to reset