no code implementations • 10 Apr 2024 • Matthew Kent Myers, Nick Wright, A. Stephen McGough, Nicholas Martin
In order to facilitate online action segmentation on a stream of incoming video data, we introduce two methods for improved training and inference of backbone action recognition models, allowing them to be deployed directly for online frame level classification.
no code implementations • 24 Nov 2022 • Matthew Kent Myers, Nick Wright, Stephen McGough, Nicholas Martin
Due to the rapid temporal and fine-grained nature of complex human assembly atomic actions, traditional action segmentation approaches requiring the spatial (and often temporal) down sampling of video frames often loose vital fine-grained spatial and temporal information required for accurate classification within the manufacturing domain.