Table 1.

Video classification performance comparison.

		Resnet50 transfer learning				CLIP VIT B/32 Encoding + Gaussian Naive Bayes
Train set	GrayST	Accuracy	Recall	Precision	F1	Accuracy	Recall	Precision	F1
Model 1 (all frames)	No	0.66	0.54	0.72	0.61	0.69	0.59	0.74	0.66
Model 1 (all frames)	Yes	0.77	0.66	0.84	0.74	0.81	0.67	0.94	0.78
Model 2 (top frames)	Yes	0.83	0.83	0.83	0.83	0.87	0.87	0.87	0.87