OperA: Attention-Regularized Transformers for Surgical Phase Recognition
Lists
Only you see this
Abstract
In this paper we introduce OperA, a transformer-based model that accurately predicts surgical phases from long video sequences. A novel attention regularization loss encourages the model to focus on high-quality frames during training. Moreover, the attention weights are utilized to identify characteristic high attention frames for each surgical phase, which could further be used for surgery summarization. OperA is thoroughly evaluated on two datasets of laparoscopic cholecystectomy videos, outperforming various state-of-the-art temporal refinement approaches.
BibTeX
@inproceedings{czempiel2021opera,
author = {Tobias Czempiel and Magdalini Paschali and Daniel Ostler and Seong-Tae Kim and Benjamin Busam and Nassir Navab},
title = {{OperA: Attention-Regularized Transformers for Surgical Phase Recognition}},
booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention},
year = {2021},
url = {https://openreview.net/forum?id=x5-iJQsq9WeC},
}Loading related content...