Sports Video Classification Framework Using Enhanced Threshold Based Keyframe Selection Algorithm and Customized CNN on UCF101 and Sports1-M Dataset

Table 6

Comparison of various deep learning architectures with the proposed model for the UCF101 dataset.

Reference	Architectures	Activation function	Optimizer	Batch size	Epochs	Learning rate	Training accuracy (%)	Testing accuracy (%)
[26]	AlexNet	Softmax	SGDM	10	15	0.0001	90.87	92.68
[26]	GoogleNet	Softmax	SGDM	15	15	0.0001	90.29	91.67
[18]	VGG16	ReLu	SGDM	128	60	0.001	100	93.52
[27]	VGG19	ReLu	SGDM	128	60	0.001	100	93.33
[27]	CNN	Softmax	Adam	128	50	0.001	93.09	93.56
Proposed model	Customized CNN	Softmax	SGDM	128	60	0.0001	92.77	93.59