Multi-Modal Enhancement Transformer Network for Skeleton-Based Human Interaction Recognition.

Skeleton-based human interaction recognition is a challenging task in the field of vision and image processing. Graph Convolutional Networks (GCNs) achieved remarkable performance by modeling the human skeleton as a topology. However, existing GCN-based methods have two problems: (1) Existing frameworks cannot effectively take advantage of the complementary features of different skeletal modalities. There is no information transfer channel between various specific modalities. (2) Limited by the structure of the skeleton topology, it is hard to capture and learn the information about two-person interactions. To solve these problems, inspired by the human visual neural network, we propose a multi-modal enhancement transformer (ME-Former) network for skeleton-based human interaction recognition. ME-Former includes a multi-modal enhancement module (ME) and a context progressive fusion block (CPF). More specifically, each ME module consists of a multi-head cross-modal attention block (MH-CA) and a two-person hypergraph self-attention block (TH-SA), which are responsible for enhancing the skeleton features of a specific modality from other skeletal modalities and modeling spatial dependencies between joints using the specific modality, respectively. In addition, we propose a two-person skeleton topology and a two-person hypergraph representation. The TH-SA block can embed their structural information into the self-attention to better learn two-person interaction. The CPF block is capable of progressively transforming the features of different skeletal modalities from low-level features to higher-order global contexts, making the enhancement process more efficient. Extensive experiments on benchmark NTU-RGB+D 60 and NTU-RGB+D 120 datasets consistently verify the effectiveness of our proposed ME-Former by outperforming state-of-the-art methods.

Evaluation of tourism competitiveness and mechanisms of spatial differentiation in Xinjiang, China.

Evaluation of tourism competitiveness is useful for measuring the level of regional tourism development. It is of great importance to understand the advantages and disadvantages of tourism development correctly and formulate corresponding development strategies. To investigate tourism competitiveness, this paper established an evaluation index system, including tourism development competitiveness, tourism resource competitiveness, and tourism-support competitiveness, for 14 prefectures and cities in Xinjiang in China. The characteristics and laws of spatial differentiation were analyzed. Factor analysis was applied to examine the spatial differentiation of regional tourism competitiveness. The results showed an obvious spatial differentiation in tourism competitiveness among the 14 prefectures and cities. In terms of development competitiveness, Yili and Urumqi constituted the spatial center, followed by Changji, Altay, and Ba Prefecture. As the provincial capital, Urumqi has political, economic, cultural, transportation, and geographic advantages, but its competitiveness is not prominent in terms of monopoly and efficiency. In terms of resource competitiveness, Yili is the core attraction, while Urumqi, Kashgar, Altay, and Ba Prefecture are dominant attractions. With respect to supporting competitiveness, Bo Prefecture has high value, followed by Urumqi City and Aksu. Hetian and Ke Prefecture have the lowest values. The comprehensive competitiveness of tourism is centered on Yili. Urumqi and Bo Prefecture are subcenters, and Changji, Altay, Ba Prefecture, Aksu, and Kashgar are characterized as multi-polar competition areas. Using the KMO and Bartlett's sphericity tests, the cumulative contribution variance of the eigenvalues of the eight factors extracted by the maximum variance rotation method was found to be 92.714%. Socio-economic conditions, tourism resources, infrastructure construction, regional cultural influence, ecological environment carrying capacity, tertiary industry development, tourism service level, and living security system are the main driving factors affecting the spatial differentiation of tourism competitiveness in Xinjiang. Analyzing the spatial evolution characteristics and the driving factors of the regional tourism competitiveness in Xinjiang, this paper seeks to promote the optimal allocation of tourism production factors in the macro regional system, and provide theoretical guidance and an empirical basis for the comprehensive and harmonic development of regional tourism.

Single-molecule trapping and spectroscopy reveals photophysical heterogeneity of phycobilisomes quenched by Orange Carotenoid Protein.

The Orange Carotenoid Protein (OCP) is a cytosolic photosensor that is responsible for non-photochemical quenching (NPQ) of the light-harvesting process in most cyanobacteria. Upon photoactivation by blue-green light, OCP binds to the phycobilisome antenna complex, providing an excitonic trap to thermally dissipate excess energy. At present, both the binding site and NPQ mechanism of OCP are unknown. Using an Anti-Brownian ELectrokinetic (ABEL) trap, we isolate single phycobilisomes in free solution, both in the presence and absence of activated OCP, to directly determine the photophysics and heterogeneity of OCP-quenched phycobilisomes. Surprisingly, we observe two distinct OCP-quenched states, with lifetimes 0.09 ns (6% of unquenched brightness) and 0.21 ns (11% brightness). Photon-by-photon Monte Carlo simulations of exciton transfer through the phycobilisome suggest that the observed quenched states are kinetically consistent with either two or one bound OCPs, respectively, underscoring an additional mechanism for excitation control in this key photosynthetic unit.

Risk of introducing exotic fruit flies, Ceratitis capitata, Ceratitis cosyra, and Ceratitis rosa (Diptera: Tephritidae), into southern China.

Exotic fruit flies (Ceratitis spp.) are often serious agricultural pests. Here, we used, pathway analysis and Monte Carlo simulations to assess the risk of introduction of Ceratitis capitata (Wiedemann), Ceratitis cosyra (Walker), and Ceratitis rosa Karsch, into southern China with fruit consignments and incoming travelers. Historical data, expert opinions, relevant literature, and archives were used to set appropriate parameters in the pathway analysis. Based on the ongoing quarantine/ inspection strategies of China, as well as the interception records, we estimated the annual number of each fruit fly species entering Guangdong province undetected with commercially imported fruit, and the associated risk. We also estimated the gross number of pests arriving at Guangdong ports with incoming travelers and the associated risk. Sensitivity analysis also was performed to test the impact of parameter changes and to assess how the risk could be reduced. Results showed that the risk of introduction of the three fruit fly species into southern China with fruit consignments, which are mostly transported by ship, exists but is relatively low. In contrast, the risk of introduction with incoming travelers is high and hence deserves intensive attention. Sensitivity analysis indicated that either ensuring all shipments meet current phytosanitary requirements or increasing the proportion of fruit imports sampled for inspection could substantially reduce the risk associated with commercial imports. Sensitivity analysis also provided justification for banning importation of fresh fruit by international travelers. Thus, inspection and quarantine in conjunction with intensive detection were important mitigation measures to reduce the risk of Ceratitis spp. introduced into China.