Joint temporal pooling for improving skeleton-based action recognition

Enhancing skeleton-based action recognition with language descriptions from pre-trained large multimodal models

T He, Y Chen, X Gao, L Wang, T Hu… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Skeleton data has become popular in human action recognition because of its efficacy in
capturing human motion patterns while mitigating the influence of environmental noise …
Shrani Navedi Navedeno v 2 virih Sorodni članki

Asynchronous joint-based temporal pooling for skeleton-based action recognition

SR Gunasekara, W Li, J Yang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Deep neural networks for skeleton-based human action recognition (HAR) often utilize
traditional averaging or maximum temporal pooling to aggregate features by treating all …
Shrani Navedi Navedeno v 1 virih Sorodni članki