Human interaction recognition technology is a hot topic in the field of computer vision, and its application prospects are very extensive. At present, there are many difficulties in human interaction recognition such as the spatial complexity of human interaction, the differences in action characteristics at different time periods, and the complexity of interactive action features. The existence of these problems restricts the improvement of recognition accuracy. To investigate the differences in the action characteristics at different time periods, we propose an improved fusion time-phase feature of the Gaussian model to obtain video keyframes and remove the influence of a large amount of redundant information. Regarding the complexity of interactive action features, we propose a multi-feature fusion network algorithm based on parallel Inception and ResNet. This multi-feature fusion network not only reduces the network parameter quantity, but also improves the network performance; it alleviates the network degradation caused by the increase in network depth and obtains higher classification accuracy. For the spatial complexity of human interaction, we combined the whole video features with the individual video features, making full use of the feature information of the interactive video. A human interaction recognition algorithm based on whole–individual detection is proposed, where the whole video contains the global features of both sides of action, and the individual video contains the individual detail features of a single person. Making full use of the feature information of the whole video and individual videos is the main contribution of this paper to the field of human interaction recognition and the experimental results in the UT dataset (UT–interaction dataset) showed that the accuracy of this method was 91.7%.

No abstract

BackgroundPlant architecture, which is mostly determined by shoot branching, plays an important role in plant growth and development. Thus, it is essential to explore the regulatory molecular mechanism of branching patterns based on the economic and ecological importance. In our previous work, a multiple-branches birch mutant br was identified from 19 CINNAMOYL-COENZYME A REDUCTASE 1 (CCR1)-overexpressed transgenic lines, and the expression patterns of differentially expressed genes in br were analyzed. In this study, we further explored some other characteristics of br, including plant architecture, wood properties, photosynthetic characteristics, and IAA and Zeatin contents. Meanwhile, the T-DNA insertion sites caused by the insertion of exogenous BpCCR1 in br were identified to explain the causes of the mutation phenotypes.ResultsThe mutant br exhibited slower growth, more abundant and weaker branches, and lower wood basic density and lignin content than BpCCR1 transgenic line (OE2) and wild type (WT). Compared to WT and OE2, br had high stomatal conductance (Gs), transpiration rate (Tr), but a low non-photochemical quenching coefficient (NPQ) and chlorophyll content. In addition, br displayed an equal IAA and Zeatin content ratio of main branches’ apical buds to lateral branches’ apical buds and high ratio of Zeatin to IAA content. Two T-DNA insertion sites caused by the insertion of exogenous BpCCR1 in br genome were found. On one site, chromosome 2 (Chr2), no known gene was detected on the flanking sequence. The other site was on Chr5, with an insertion of 388 bp T-DNA sequence, resulting in deletion of 107 bp 5′ untranslated region (UTR) and 264 bp coding sequence (CDS) on CORONATINE INSENSITIVE 1 (BpCOII). In comparison with OE2 and WT, BpCOI1 was down-regulated in br, and the sensitivity of br to Methyl Jasmonate (MeJA) was abnormal.ConclusionsPlant architecture, wood properties, photosynthetic characteristics, and IAA and Zeatin contents in main and lateral branches’ apical buds changed in br over the study’s time period. One T-DNA insertion was identified on the first exon of BpCOI1, which resulted in the reduction of BpCOI1 expression and abnormal perception to MeJA in br. These mutation phenotypes might be associated with a partial loss of BpCOI1 in birch.

Leaves are one of the vegetative organs of plants that are essential for plant growth and development. PIN-FORMED (PINs) gene is an indoleacetic acid (IAA) transporter that plays a critical role in leaf development. To determine the function of BpPIN3 in leaf polarity formation in Betula pendula, the transgenic lines with BpPIN3 overexpression (OE) and BpPIN3-reduced expression (RE) were analyzed using the Agrobacterium-mediated method. The RE lines displayed the characteristics of leaf margin adaxial upward curling, with lower expression of BpPIN3 resulting in greater rolling. Tissue localization of IAA in the auxin GUS reporter system proved that auxin in the RE was mainly distributed in the secondary veins, palisade tissues, and epidermal cells in the leaf margin area. The auxin content in the leaf margin area was significantly greater than that in the main vein tissue. The cell density of the palisade tissue and the ratio of palisade tissue to spongy tissue in the curled leaf margin of the RE lines were found to be significantly decreased. RNA-seq analysis revealed that the RE hormone-signaling pathway genes were significantly enriched compared with those of the OE and WT lines; in particular, the auxin response-related genes SAURs (i.e., SAUR23, SAUR24, SAUR28, and SAUR50) and GH3.10 were found to be significantly upregulated. qRT-PCR analysis indicated that BpPIN3 expression at the leaf margin was significantly lower than that near the main vein in the RE lines. In contrast, the expression levels of SAURs and GH3.10 were significantly higher than those near the midrib. In conclusion, BpPIN3 regulates the expression of auxin response-related genes and the polar transport of auxin to change the polar form of the proximal and distal axes of birch leaves.

No abstract