SkateboardAI: The Coolest Video Action Recognition for Skateboarding
This work addresses the need for an AI referee in skateboarding competitions, but it is incremental as it applies existing methods to a new dataset.
The authors tackled the problem of video action recognition for skateboarding tricks by curating the 'SkateboardAI' dataset and implementing various uni-modal and multi-modal methods, achieving accurate recognition results as detailed in their performance comparisons.
Impressed by the coolest skateboarding sports program from 2021 Tokyo Olympic Games, we are the first to curate the original real-world video datasets "SkateboardAI" in the wild, even self-design and implement diverse uni-modal and multi-modal video action recognition approaches to recognize different tricks accurately. For uni-modal methods, we separately apply (1) CNN and LSTM; (2) CNN and BiLSTM; (3) CNN and BiLSTM with effective attention mechanisms; (4) Transformer-based action recognition pipeline. Transferred to the multi-modal conditions, we investigated the two-stream Inflated-3D architecture on "SkateboardAI" datasets to compare its performance with uni-modal cases. In sum, our objective is developing an excellent AI sport referee for the coolest skateboarding competitions.