Skip to main content

Symmetric Dilated Convolution for Surgical Gesture Recognition.

Zhang, J., Nie, Y., Lyu, Y., Li, H., Chang, J., Yang, X. and Zhang, J. J., 2020. Symmetric Dilated Convolution for Surgical Gesture Recognition. In: MICCAI 2020: International Conference on Medical Image Computing and Computer-Assisted Intervention, 4-8 October 2020, Lima, Peru, 409 - 418.

Full text available as:

paper1685.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial.


DOI: 10.1007/978-3-030-59716-0_39


Automatic surgical gesture recognition is a prerequisite of intra-operative computer assistance and objective surgical skill assessment. Prior works either require additional sensors to collect kinematics data or have limitations on capturing temporal information from long and untrimmed surgical videos. To tackle these challenges, we propose a novel temporal convolutional architecture to automatically detect and segment surgical gestures with corresponding boundaries only using RGB videos. We devise our method with a symmetric dilation structure bridged by a self-attention module to encode and decode the long-term temporal patterns and establish the frame-to-frame relationship accordingly. We validate the effectiveness of our approach on a fundamental robotic suturing task from the JIGSAWS dataset. The experiment results demonstrate the ability of our method on capturing long-term frame dependencies, which largely outperform the state-of-the-art methods on the frame-wise accuracy up to ∼ 6 points and the F1@50 score ∼ 6 points.

Item Type:Conference or Workshop Item (Paper)
Group:Faculty of Media & Communication
ID Code:34774
Deposited By: Symplectic RT2
Deposited On:04 Nov 2020 17:08
Last Modified:14 Mar 2022 14:24


Downloads per month over past year

More statistics for this item...
Repository Staff Only -