Search Results for author:
Found 2 papers, 2 papers with code
ASFormer: Transformer for Action Segmentation
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
Not End-to-End: Explore Multi-Stage Architecture for Online Surgical Phase Recognition
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.
