Search

Traditional clustering algorithms are widely used for building bag-of-words (BOW) models to aggregate spatio-temporal feature points extracted from a video for human activity recognition problems. Their performances are restricted by the computational complexity which limits the number of feature points being used. In contrast, deep clustering yields good clustering performance without the limit of the number of feature points. Therefore, this work proposes a dual stacked autoencoders features embedded clustering (DSAFEC) and a BOW construction method based on the DSAFEC (B-DSAFEC) to reduce the computational complexity and to remove the selection restriction. The DSAFEC first transforms feature points extracted from a video to a learned feature space and then probabilities of cluster assignment of feature points are predicted to build BOWs for human activity recognition. A soft clustering is used by assigning each feature point to multiple clusters yielding the largest probabilities instead of only one in hard clustering. Experimental results on three benchmark human activity datasets show that the B-DSAFEC yields better performance compared to five reference methods which are developed based on either traditional clustering methods or deep clustering methods. [ABSTRACT FROM AUTHOR]

In the past decades, many studies have confirmed that specific personality traits correlate such that a general factor of personality (GFP) emerges. In order to test whether the characteristics of this general factor are universal, thorough tests in various cultures are required. Accordingly, we conducted a meta-analysis on the GFP in mainland China. After testing the sensitivity of the GFP, correction for attenuation, testing for samples' geographical distribution, types of samples, and types of questionnaires, we confirmed the GFP in the population of mainland China (N = 30,863, K = 53). To further examine the nature of the GFP, we tested whether it is indicative of general social effectiveness by studying the associations of the GFP with (1) leadership effectiveness and (2) abusive supervision. The results implied that high-GFP leaders indeed work more effectively (r = 0.17) and were less abusive (−0.20), as rated by their subordinates. This study among Chinese samples adds to the literature by showing the consistency of the GFP in a large Eastern country. • The General Factor of Personality (GFP) can be found in the Chinese population. • The GFP is stable across subpopulations in mainland China. • The GFP is positively related to leadership effectiveness. • The GFP is negatively related to abusive supervision. • In Chinese populations, the GFP also seems to indicate social effectiveness. [ABSTRACT FROM AUTHOR]