1 code implementation • 16 Oct 2021 • Fangqiu Yi, Hongyu Wen, Tingting Jiang
However, there are several major concerns when directly applying the Transformer to the action segmentation task, such as the lack of inductive biases with small training sets, the deficit in processing long input sequence, and the limitation of the decoder architecture to utilize temporal relations among multiple action segments to refine the initial predictions.
Ranked #2 on Action Segmentation on Assembly101
2 code implementations • 10 Jul 2021 • Fangqiu Yi, Tingting Jiang
To address the problem, we propose a new non end-to-end training strategy and explore different designs of multi-stage architecture for surgical phase recognition task.