English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Conference Paper

Fine-grained action detection with RGB and pose information using two stream convolutional networks

MPS-Authors
/persons/resource/persons266715

Martin,  Pierre-Etienne       
Department of Comparative Cultural Psychology, Max Planck Institute for Evolutionary Anthropology, Max Planck Society;

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)

Hacker_Fine-Grained_MediaEval_2023.pdf
(Publisher version), 2MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Hacker, L., Bartels, F., & Martin, P.-E. (2023). Fine-grained action detection with RGB and pose information using two stream convolutional networks. In CEUR Workshop Proceedings: MediaEval 2022: Multimedia Evaluation Workshop. doi:10.48550/arXiv.2302.02755.


Cite as: https://hdl.handle.net/21.11116/0000-000E-1621-4
Abstract
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% of accuracy, while the detection does not outperform the baseline but still reaches an IoU of 0.349 and mAP of 0.110.