0 citations0 references

Ball Position Feature Embedded Group Activity Recognition Model for Team Sport Games

Frontiers in artificial intelligence and applications2022

Citations Over Time

Ankhzaya Jamsrandorj, Vanyi Chao, Yin May Oo, Kyung-Ryoul Mun, Jinwook Kim

Abstract

Most group activity recognition models focus mainly on spatio-temporal features from the players in sports games. Often they do not pay enough attention to the game object, which heavily affects not only individual action but also a group activity. We propose a new group activity recognition model for sports games that incorporates players’ motion information and game object positional information. The proposed method uses a transformer encoder for temporal feature extraction and a ’simple’ conventional convolutional neural network for extracting spatial features and fusing them with the relative ball position-embedded features. The experimental results show that our model achieved comparable results to state-of-the-art methods on the Volleyball dataset by using only one transformer encoder block and the ball position.

Related Papers

Design and Realization of RS Encoder Based on FPGA(2009)
→ An analysis on optimal rates of BDB encoders for RLL and MTR systems(2004)
→ Area and Energy Efficient QCA Based Compact Serial Concatenated Convolutional Code Encoder(2022)
→ A(2023)