EURASIP Journal on Image and Video Processing

Table 4 Comparisons of feature selection algorithms on HMDB13 ←EID in terms of average accuracy using three classifiers when the ratio of labeled video data are set to 5%

From: A feature selection framework for video semantic recognition via integrated cross-media analysis and embedded learning

Classifiers	FF	FSFS	FSNM	LSR₂₁	SVM₂₁	EnFS	JELSR	JCAEL
LMCSVM	0.3032	0.3187	0.3137	0.3117	0.3137	0.3182	*0.3387*	0.3526
LSR	0.1763	0.2138	0.1898	0.1903	0.1873	0.2003	*0.2233*	0.2318
MCkNN	0.1898	0.2647	0.2517	0.2582	0.2093	0.2697	*0.2737*	0.2877

Back to article page