The visual storytelling (VST) task aims at generating a reasonable and coherent paragraph-level story with the image stream as input. Different from caption that is a direct and literal description of image content, the story in the VST task tends to contain plenty of imaginary concepts that do not appear in the image. This requires the AI agent to reason and associate with the imaginary concepts based on implicit commonsense knowledge to generate a reasonable story describing the image stream. Therefore, in this work, we present a commonsense-driven generative model, which aims to introduce crucial commonsense from the external knowledge base for visual storytelling. Our approach first extracts a set of candidate knowledge graphs from the knowledge base. Then, an elaborately designed vision-aware directional encoding schema is adopted to effectively integrate the most informative commonsense. Besides, we strive to maximize the semantic similarity within the output during decoding to enhance the coherence of the generated text. Results show that our approach can outperform the state-of-the-art systems by a large margin, which achieves a 29\% relative improvement of CIDEr score. With additional commonsense and semantic-relevance based objective, the generated stories are more diverse and coherent.
Biological invasion seriously threatens ecological stability and social development. One of the bases for forming invasion is alien species’ strong phenotypic plasticity. Phenotypic plasticity can help alien species adapt to environmental changes and enhance their invasive ability. China is one of the countries seriously affected by drought. Under the background of environmental drought, exploring the reasons why invasive plants can gain growth advantages and mastering the phenotypic changes of invasive plants in response to drought stress are conducive to helping us understand more about the invasion mechanism of invasive species. In this paper, the research progresses of invasive plants’ morphological plasticity and physiological plasticity under drought stress in recent years are reviewed, the invasive plants’ morphological and physiological metabolic characteristics under drought are summarized, and the growth advantages of invasive plants are discussed, which provided a scientific theoretical basis for alleviating the serious harm caused by biological invasion to China’s natural environment.
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.