No abstract

No abstract

Temporal action proposal generation plays an important role in video action understanding, which requires localizing high-quality action content precisely. However, generating temporal proposals with both precise boundaries and high-quality action content is extremely challenging. To address this issue, we propose a novel Boundary Content Graph Neural Network (BC-GNN) to model the insightful relations between the boundary and action content of temporal proposals by the graph neural networks. In BC-GNN, the boundaries and content of temporal proposals are taken as the nodes and edges of the graph neural network, respectively, where they are spontaneously linked. Then a novel graph computation operation is proposed to update features of edges and nodes. After that, one updated edge and two nodes it connects are used to predict boundary probabilities and content confidence score, which will be combined to generate a final high-quality proposal. Experiments are conducted on two mainstream datasets: ActivityNet-1.3 and THUMOS14. Without the bells and whistles, BC-GNN outperforms previous state-ofthe-art methods in both temporal action proposal and temporal action detection tasks.

Four kinds of rail steels were tested to investigate the wear behaviors of wheel-rail materials under three kinds of axle loads. Results indicate that the increase in axle load not only significantly enlarges the wear loss but also enlarges the depth and the length of the fatigue cracks. However, with the decreases in the hardness ratios, some ripples are exhibited on the surface, and the wear surfaces become much rougher; the subsurface analyses deliver the presence of extremely rough surface, and the deformation depths are irregular. The relationship between the total wear loss of the wheel/rail system and the hardness ratio indicates that the hardness ratio of wheel/rail steels has slight impact on the total wear loss at a low axle load; however, the decrease in the hardness ratio enlarges the total wear loss significantly at a high axle load. In summary, a quenched rail should be chosen for the heavy-haul railway, and the hardness of the wheel steel should be raised to a degree close to the rail. However, a hot rolled rail is much suitable for the high-speed railway, and the wheel hardness should be smaller than the rail.