{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/hierarchically-attentive-rnn-for-album","title":"Hierarchically-Attentive RNN for Album Summarization and Storytelling","arxiv_id":"1708.02977","date":"2017-08-09","proceeding":"EMNLP 2017 9","authors":["Licheng Yu","Mohit Bansal","Tamara L. Berg"],"abstract":"We address the problem of end-to-end visual storytelling. Given a photo\nalbum, our model first selects the most representative (summary) photos, and\nthen composes a natural language story for the album. For this task, we make\nuse of the Visual Storytelling dataset and a model composed of three\nhierarchically-attentive Recurrent Neural Nets (RNNs) to: encode the album\nphotos, select representative (summary) photos, and compose the story.\nAutomatic and human evaluations show our model achieves better performance on\nselection, generation, and retrieval than baselines.","url_abs":"http://arxiv.org/abs/1708.02977v1","url_pdf":"http://arxiv.org/pdf/1708.02977v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"visual-storytelling","task_name":"Visual Storytelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-storytelling-on-vist","task":"Visual Storytelling","dataset":"VIST","model":"h-attn-rank","rank_in_archive_order":32,"of":33,"metrics":{"BLEU-3":"20.78","CIDEr":"7.38","METEOR":"33.94","ROUGE-L":"29.82"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1708.02977","atlas_url":"https://app.syntology.ai/?focus=1708.02977","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}