TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Visual Storytelling	VIST	h-attn-rank	BLEU-3	20.78	# 15
Visual Storytelling	VIST	h-attn-rank	METEOR	33.94	# 27
Visual Storytelling	VIST	h-attn-rank	CIDEr	7.38	# 24
Visual Storytelling	VIST	h-attn-rank	ROUGE-L	29.82	# 18

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/hierarchically-attentive-rnn-for-album/visual-storytelling-on-vist)](https://paperswithcode.com/sota/visual-storytelling-on-vist?p=hierarchically-attentive-rnn-for-album)`

Hierarchically-Attentive RNN for Album Summarization and Storytelling

EMNLP 2017 · Licheng Yu, Mohit Bansal, Tamara L. Berg ·

We address the problem of end-to-end visual storytelling. Given a photo album, our model first selects the most representative (summary) photos, and then composes a natural language story for the album. For this task, we make use of the Visual Storytelling dataset and a model composed of three hierarchically-attentive Recurrent Neural Nets (RNNs) to: encode the album photos, select representative (summary) photos, and compose the story. Automatic and human evaluations show our model achieves better performance on selection, generation, and retrieval than baselines.