Mesh is an important and powerful type of data for 3D shapes and widely studied in the field of computer vision and computer graphics. Regarding the task of 3D shape representation, there have been extensive research efforts concentrating on how to represent 3D shapes well using volumetric grid, multi-view and point cloud. However, there is little effort on using mesh data in recent years, due to the complexity and irregularity of mesh data. In this paper, we propose a mesh neural network, named MeshNet, to learn 3D shape representation from mesh data. In this method, face-unit and feature splitting are introduced, and a general architecture with available and effective blocks are proposed. In this way, MeshNet is able to solve the complexity and irregularity problem of mesh and conduct 3D shape representation well. We have applied the proposed MeshNet method in the applications of 3D shape classification and retrieval. Experimental results and comparisons with the state-of-the-art methods demonstrate that the proposed MeshNet can achieve satisfying 3D shape classification and retrieval performance, which indicates the effectiveness of the proposed method on 3D shape representation.

No abstract

Abstract. Edge impurity transport has been investigated in the stochastic layer of Large Helical Device (LHD) and the scrape-off layer (SOL) of Huan Liuqi-2A (HL-2A) tokamak, as a comparative analysis based on the three-dimensional (3D) edge transport code EMC3-EIRENE and on the carbon emission profile measurement. The 3D simulation predicts impurity screening effect in the both devices, but also predicts different impurity behavior against collisionality and impurity source location between the two devices. The difference is caused by geometrical structures of the magnetic field lines in the stochastic layer and X-point poloidal divertor SOL, i.e., number of poloidal turns of flux tubes affecting poloidal distribution of plasma parameters and impact of perpendicular transport on parallel pressure conservation and energy transport. These processes have an influence on the impurity screening efficiency at upstream and downstream positions of field lines. The carbon emission measured in the stochastic layer of LHD clearly indicates the screening effect in high density region. The result can be qualitatively interpreted by the present modeling, although the modeling shows a slight difference in the quantitative behavior of carbon ions in the stochastic layer of LHD. On the other hand, comparison of the carbon emission profile from HL-2A with the modeling is not straightforward. It is found that the impurity distribution in the HL-2A SOL is very sensitive to the impurity source location. In order to interpret the experimental observation a further study is necessary, in particular, on the impurity source distribution in the divertor plate and the first wall.

No abstract

Understanding questions and finding clues for answers are the key for video question answering. Compared with image question answering, video question answering (Video QA) requires to find the clues accurately on both spatial and temporal dimension simultaneously, and thus is more challenging. However, the relationship between spatio-temporal information and question still has not been well utilized in most existing methods for Video QA. To tackle this problem, we propose a Question-Guided Spatio-Temporal Contextual Attention Network (QueST) method. In QueST, we divide the semantic features generated from question into two separate parts: the spatial part and the temporal part, respectively guiding the process of constructing the contextual attention on spatial and temporal dimension. Under the guidance of the corresponding contextual attention, visual features can be better exploited on both spatial and temporal dimensions. To evaluate the effectiveness of the proposed method, experiments are conducted on TGIF-QA dataset, MSRVTT-QA dataset and MSVD-QA dataset. Experimental results and comparisons with the state-of-the-art methods have shown that our method can achieve superior performance.