Papers › Hierarchically-Attentive RNN for Album Summarization and Storytelling

Hierarchically-Attentive RNN for Album Summarization and Storytelling

9 Aug 2017EMNLP 2017 9arXiv:1708.02977archive 2025-07-28

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.

PaperPDFConference PDF

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

RetrievalVisual Storytelling

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Visual Storytelling VIST h-attn-rank BLEU-3 20.78 #32 of 33 Archive leaderboard report
Visual Storytelling VIST h-attn-rank CIDEr 7.38 #32 of 33 Archive leaderboard report
Visual Storytelling VIST h-attn-rank METEOR 33.94 #32 of 33 Archive leaderboard report
Visual Storytelling VIST h-attn-rank ROUGE-L 29.82 #32 of 33 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections