Human action recognition has been applied in many fields, such as video surveillance and human computer interaction, where it helps to improve performance. Numerous reviews of the literature have been done, but rarely have these reviews concentrated on skeleton-graph-based approaches. Connecting the skeleton joints as in the physical appearance can naturally generate a graph. This paper provides an up-to-date review for readers on skeleton graph-neural-network-based human action recognition. After analyzing previous related studies, a new taxonomy for skeleton-GNN-based methods is proposed according to their designs, and their merits and demerits are analyzed. In addition, the datasets and codes are discussed. Finally, future research directions are suggested.
Eucommia ulmoides Oliver is a dioecious, pharmaceutically and economically important, and precious relict tree species endemic to China, and has been listed as a key protected tree species of national level II. Phenotypic variation in ten natural populations in some key traits is still obscure. In order to study the relationship between population variation in phenotypic traits and geoclimatic factors, 15 traits were analyzed in 117 female sampled tree from ten natural populations. The results showed that the coefficients of variation for all of the 15 traits widely ranged from 9.7% (fruit vertical diameter) to 49.0% (leaf thickness), with an average of 19.7%. The nested ANOVA revealed plentiful phenotypic variations within and among populations. The variation within population was the main source, with an average proportion of 42.8%, greater than that among the population (16.6%). The 15 traits were reduced to four principal components, which collectively accounted for 70.1% of phenotypic variation among trees. The ten populations were mainly divided into two groups: Group A included eight populations throughout the Wuling Mountains occurring in relatively close proximity to each other, and Group B which comprises two geographically distant populations in mountains further northern. There were significant level correlations between phenotypic differentiation among population of E. ulmoides and both geographic (r = 0.65, p < 0.05) and climatic (r = 0.73, p < 0.01) distance. Step-wise regression indicates average annual temperature and rainfall accounted for most of the phenotypic variation among populations, and mainly associated with differences in leaf, fruit and seed size. These results can have an important implication for genetic improvement, diversity conservation and resource management of the species in the future.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.