# Automated Surgical Activity Recognition with One Labeled Sequence

## TL;DR

This paper explores automated surgical activity recognition using minimal labeled data, demonstrating that unsupervised learning can significantly improve performance even with only one annotated sequence.

## Contribution

It introduces a novel approach for activity recognition with scarce annotations, leveraging unsupervised learning to enhance accuracy in robot-assisted surgery.

## Key findings

- Feasibility of recognition with only one labeled sequence
- Unsupervised pre-training improves performance substantially
- Highlights the challenge of limited annotation regimes

## Abstract

Prior work has demonstrated the feasibility of automated activity recognition in robot-assisted surgery from motion data. However, these efforts have assumed the availability of a large number of densely-annotated sequences, which must be provided manually by experts. This process is tedious, expensive, and error-prone. In this paper, we present the first analysis under the assumption of scarce annotations, where as little as one annotated sequence is available for training. We demonstrate feasibility of automated recognition in this challenging setting, and we show that learning representations in an unsupervised fashion, before the recognition phase, leads to significant gains in performance. In addition, our paper poses a new challenge to the community: how much further can we push performance in this important yet relatively unexplored regime?