M2CAI Workflow Challenge: Convolutional Neural Networks with Time Smoothing and Hidden Markov Model for Video Frames Classification
This work addresses the domain-specific problem of surgical workflow analysis for medical professionals, but it is incremental as it combines existing methods like CNNs and HMMs without introducing new paradigms.
The paper tackled the problem of recognizing operation phases in endoscopic video frames for the M2CAI Workflow Challenge, achieving a result among the top three best approaches by fine-tuning a Residual Network-200 with temporal smoothing and a Hidden Markov Model.
Our approach is among the three best to tackle the M2CAI Workflow challenge. The latter consists in recognizing the operation phase for each frames of endoscopic videos. In this technical report, we compare several classification models and temporal smoothing methods. Our submitted solution is a fine tuned Residual Network-200 on 80% of the training set with temporal smoothing using simple temporal averaging of the predictions and a Hidden Markov Model modeling the sequence.