3M: Multi-style image caption generation using Multi-modality features under Multi-UPDOWN model

In this paper, we build a multi-style generative model for stylish image captioning which uses multi-modality features, ResNeXt and text features generated by DenseCap. We propose the 3M model, Multi-UPDOWN caption that encodes decodes them into captions. demonstrate effectiveness of our on generating human-like captions examining its performance two datasets, PERSONALITY-CAPTIONS dataset, FlickrStyle10K dataset. compare against variety state-of-the-art baselines various automatic NLP metrics such as BLEU, ROUGE-L, CIDEr, SPICE, etc \footnote{code will be available at https://github.com/cici-ai-club/3M}. A qualitative study has also been done to verify can used different stylized