First detection and genetic characterization of a novel kirkovirus from a dead thoroughbred mare in northern Xinjiang, China, in 2018.

BACKGROUND: In May 2018, a 8 year old thoroughbred mare died at an equestrian club in Changji, Xinjiang, China. The horse had been imported from the United States in 2013. She became pregnant in December 2016 but, after foaling, gradually lost weight and died in May 2018. This study aim to identify the pathogen, who cause of horse death, using virome. RESULTS: We have identified an Equ1-like virus from the fecal virome of a dead thoroughbred mare in China. Full genomic sequencing and phylogenetic analysis of the virus, tentatively named "kirkovirus Cj-7-7", showed that it was closely related to kirkovirus Equ1 and clustered together with po-circo-like viruses 21, 22, 41, and 51, suggesting that it should be assigned to the proposed family "Kirkoviridae". An epidemiological investigation showed that kirkovirus Cj-7-7 circulates in horses of northern Xinjiang and may specifically infect intestinal cells. CONCLUSIONS: Our findings demonstrate the genetic diversity and geographic distribution of Kirkoviruses, and the prevalence of Kirkovirus Cj-7-7 in Xinjiang, China.

A hybrid neural network-based intelligent body posture estimation system in sports scenes.

Body posture estimation has been a hot branch in the field of computer vision. This work focuses on one of its typical applications: recognition of various body postures in sports scenes. Existing technical methods were mostly established on the basis of convolution neural network (CNN) structures, due to their strong visual information sensing ability. However, sports scenes are highly dynamic, and many valuable contextual features can be extracted from multimedia frame sequences. To handle the current challenge, this paper proposes a hybrid neural network-based intelligent body posture estimation system for sports scenes. Specifically, a CNN unit and a long short-term memory (LSTM) unit are employed as the backbone network in order to extract key-point information and temporal information from video frames, respectively. Then, a semi-supervised learning-based computing framework is developed to output estimation results. It can make training procedures using limited labeled samples. Finally, through extensive experiments, it is proved that the proposed body posture estimation method in this paper can achieve proper estimation effect in real-world frame samples of sports scenes.