3D CNNs achieve over 84% frame-wise accuracy recognizing surgical gestures from video on the JIGSAWS dataset, outperforming spatial-only and hybrid temporal models.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Using 3D Convolutional Neural Networks to Learn Spatiotemporal Features for Automatic Surgical Gesture Recognition in Video
3D CNNs achieve over 84% frame-wise accuracy recognizing surgical gestures from video on the JIGSAWS dataset, outperforming spatial-only and hybrid temporal models.