From Deterministic to Generative: Multimodal Stochastic RNNs for Video Captioning

Video captioning, in essential, is a complex natural process, which is affected by various uncertainties stemming from video content, subjective judgment, and so on. In this paper, we build on the recent progress in using encoder-decoder framework for video captioning and address what we find to be a critical deficiency of the existing...

The relationship between inundation duration and Spartina alterniflora growth along the Jiangsu coast, China

The above-ground biomass of Spartina alterniflora salt marsh meadows is influenced by numerous interacting factors, among them elevation, tidal range and inundation duration. Bio-geomorphological models make use of either linear or quadratic equations, but it is important to be aware that the variables are area specific and hence not generic. In...

Condition monitoring of urban rail transit by local energy harvesting

The goal of this study is to develop a vibration-based electromagnetic energy harvesting prototype that provides power to rail-side monitoring equipment and sensors by collecting wheel-rail vibration energy when the train travels. This technology helps power rail–side equipment in off-grid and remote areas. This article introduces the...