Motion-Based Weak Supervision for Video Parsing with Application to Colonoscopy
arXiv:2210.10594v13 citationsh-index: 46
Originality Synthesis-oriented
AI Analysis
This work addresses phase detection in colonoscopy videos, which is an incremental improvement for medical video analysis.
The paper tackles the problem of parsing colonoscopy videos into phases by proposing a two-stage unsupervised approach that uses motion cues for coarse segmentation and then weakly supervises an appearance-based classifier with noisy labels.
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.