# Motion-Based Weak Supervision for Video Parsing with Application to Colonoscopy

arXiv: https://arxiv.org/abs/2210.10594 · HTML: https://mlsanity.com/paper/2210.10594/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 7 references that are in the map.
- First posted on arXiv 16 Oct 2022.

## Builds on (most cited first, 3 of 3)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [Fast Optical Flow using Dense Inverse Search](https://mlsanity.com/paper/1603.03590/) (2016)

## Built on by (most cited first, 3 of 3)

- [Semantic Parsing of Colonoscopy Videos with Multi-Label Temporal Networks](https://mlsanity.com/paper/2306.06960/) (2023)
- [Colonoscopy Coverage Revisited: Identifying Scanning Gaps in Real-Time](https://mlsanity.com/paper/2305.10026/) (2023)
- [Semi-supervised Quality Evaluation of Colonoscopy Procedures](https://mlsanity.com/paper/2305.10090/) (2023)

## Abstract (arXiv)

We propose a two-stage unsupervised approach for parsing videos into phases. We use motion cues to divide the video into coarse segments. Noisy segment labels are then used to weakly supervise an appearance-based classifier. We show the effectiveness of the method for phase detection in colonoscopy videos.