This paper focuses on a novel and challenging vision task, dense video captioning, which aims to automatically describe a video clip with multiple informative and diverse caption sentences. The proposed method is trained without explicit annotation of fine-grained sentence to video regionsequence correspondence, but is only based on weak videolevel sentence annotations. It differs from existing video captioning systems in three technical aspects. First, we propose lexical fully convolutional neural networks (Lexical-FCN) with weakly supervised multi-instance multi-label learning to weakly link video regions with lexical labels. Second, we introduce a novel submodular maximization scheme to generate multiple informative and diverse regionsequences based on the Lexical-FCN outputs. A winnertakes-all scheme is adopted to weakly associate sentences to region-sequences in the training phase. Third, a sequenceto-sequence learning based language model is trained with the weakly supervised information obtained through the association process. We show that the proposed method can not only produce informative and diverse dense captions, but also outperform state-of-the-art single video captioning methods by a large margin.
This paper is related to the analysis of the dynamic behaviour of a liquid-feed direct methanol fuel cell (DMFC) under different operating conditions, based on an isothermal model accounting for the mass balances the charge balances, the reaction micro-kinetics and the mass transport phenomena. Conceptually, the fuel cell system is decomposed into its subsystems (anode and cathode compartments, diffusion layers, catalyst layers on both electrodes, proton exchange membrane (PEM)). The models of the subsystems are coupled to a DMFC model which is represented by a set of differential-algebraic equation of index one. Dynamic simulation with this model show that the undesired cross-over of the reactant methanol through the PEM can be reduced by periodically pulsed methanol feeding to the anode compartment. The simulated results are in good agreement with experimental cell voltage data obtained from a laboratory-scale DMFC which was operated with different dynamic feeding strategies
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.