… image description by fusing image and text features as input. The text features contain the
semantics of keywords of images, as a supplement to image … from image to image description. …

… 在Microsoft COCO数据集上的实验结果表明,所提方法能有效捕捉图像的全局和局部特征,在
CIDEr(Consensus-based Image Description Evaluation)指标上达到了133.1%.可见基于GAT的…

… 时,多样性指标mBleu(mutual overlap-Bilingual Evaluation Understudy)提升了1.9%,同时准确
性指标CIDEr(Consensus-based Image Description Evaluation)显著提升了14.6.与典型多模态…

… : Diverse image captioning has become a research hotspot in the field of image description.
… the accuracy metric CIDEr (Consensus based Image Description Evaluation) has improved …

… 显著,在BLEU(bilingual evaluation understudy),METEOR(metric for evaluation of translation
with explicit ordering)和CIDEr(consensus-based image description evaluation)等多项评价…

… This model also outperforms the emb-gLSTM method in terms of B-1 and CIDEr(consensus-based
image description evaluation) by 5.1% and 13.3%, respectively, and the ConvCap …

… 与性能较好的方法相比,本文方法在BLEU-1,BLEU-2,BLEU-3,BLEU-4,METEOR和CIDEr(consensus-based
image description evaluation)等6个评价指标上的评分分别提升了5.7%,2.0%,1.6…

… , the proposed improved image description generation model with attention … image
description task, and this model is better than the traditional model on all the four evaluation …

… image caption models cannot make full use of image … of fusing features, an image caption
generation model with Adaptive … )-4, CIDEr (Consensus-based Image Description Evaluation) …

… understanding for gisting evaluation(ROUGE);metric for evaluation of translation …
consensus-based image description evaluation(CIDEr);semantic propositional image caption …