Table 3 UAR and UF1 performance of different approach under LOSO protocol on different datasets.

Approach	MMEW		CASME II		SMIC		SAMM
Approach	UAR	UF1	UAR	UF1	UAR	UF1	UAR	UF1
LBP-TOP¹⁰	0.5628	0.5794	0.7429	0.7026	0.5280	0.2000	0.4102	0.3954
LBP-SIP¹³	0.5208	0.5174	0.5281	0.5369	0.5142	0.4452	0.4169	0.4412
Bi-WOOF¹⁷	–	–	0.5382	0.7805	–	0.5727	–	0.5211
HOOF¹⁸	0.5814	0.5982	0.5782	0.5874	0.5696	0.5574	0.5877	0.5639
CapsuleNet⁴³	0.7296	0.7115	0.7018	0.7068	0.5877	0.5820	0.5927	0.6520
CNN-LSTM²²	–	–	0.4125	0.4113	0.4276	0.4150	0.3086	0.3020
NMER⁴⁴	0.3414	0.4253	0.6929	0.7624	0.5555	0.5607	04,894	0.6389
RCN-Best³²	–	–	0.6600	0.6584	0.8131	0.8653	0.6771	0.7647
TSCNN²¹	–	–	0.6009	0.6124	0.5924	0.5839	0.6103	0.6083
MobileNetV2⁴²	–	–	0.6328	0.6125	0.6368	0.6589	0.6236	0.6614
DeiT³⁹	0.6921	0.6882	0.6814	0.6994	0.6881	0.6970	0.7052	0.7028
Proposed method	0.6981	0.7318	0.6997	0.7251	0.7356	0.7141	0.6781	0.7428

Quick links

Search