… Similarly, the discriminative captions can also improve the accuracy of the caption. It can be
… tive to optimize the image captioning model, which encourages generating fine-grained and …

… In this paper, we propose a novel image captioning model with fine-grained and semantic-guided
visual attention based on a novel Fully Convolutional Network (FCN)-LSTM framework…

… image captioning. In this paper, we propose an evaluation metric specifically for video captioning
… We consider not only coarse-grained embedding matching between video and text but …

… A More Image Captioning Examples We provide more image captioning examples using
different reward functions in Table 5. Overall, the captions from the model with CLIP-S+…

… fine-grained, error-aware evaluation method REO to measure the quality of machine-generated
image captions … ground truth, extra description beyond image content, and omitted …

… the proposed fine-grained image captioning framework. We first formulate the image
caption… 3.1 Overview We formulate the task of image captioning into a sequential decision-making …

… Furthermore, we review the primary datasets used to explore image captions, from
domain-specific benchmarks to domain-specific datasets collected to investigate specific aspects of …

… a c-RNN image captioning model, which as far as we know, is the first one to model image
captions in character level. Compared with existing works on image captioning, there are two …

… used to extract image features in image captioning, and the … and do not pay attention to
fine-grained details because of the … properly generates captions by fusing fine-grained features …

… recurrent neural networks for image captioning. However, in … in an image can give more
fined-grained captioning of a … of image captioning by fusing text feature available in an image …