{"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/diverse-and-coherent-paragraph-generation","title":"Diverse and Coherent Paragraph Generation from Images","arxiv_id":"1809.00681","date":"2018-09-03","proceeding":"ECCV 2018 9","authors":["Moitreya Chatterjee","Alexander G. Schwing"],"abstract":"Paragraph generation from images, which has gained popularity recently, is an\nimportant task for video summarization, editing, and support of the disabled.\nTraditional image captioning methods fall short on this front, since they\naren't designed to generate long informative descriptions. Moreover, the\nvanilla approach of simply concatenating multiple short sentences, possibly\nsynthesized from a classical image captioning system, doesn't embrace the\nintricacies of paragraphs: coherent sentences, globally consistent structure,\nand diversity. To address those challenges, we propose to augment paragraph\ngeneration techniques with 'coherence vectors', 'global topic vectors', and\nmodeling of the inherent ambiguity of associating paragraphs with images, via a\nvariational auto-encoder formulation. We demonstrate the effectiveness of the\ndeveloped approach on two datasets, outperforming existing state-of-the-art\ntechniques on both.","url_abs":"http://arxiv.org/abs/1809.00681v1","url_pdf":"http://arxiv.org/pdf/1809.00681v1.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":"diversity","task_name":"Diversity"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"image-paragraph-captioning","task_name":"Image Paragraph Captioning"},{"task_slug":"video-summarization","task_name":"Video Summarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-paragraph-captioning-on-image-paragraph","task":"Image Paragraph Captioning","dataset":"Image Paragraph Captioning","model":"Diverse and Coherent Paragraph Generation from Images","rank_in_archive_order":5,"of":10,"metrics":{"BLEU-4":"9.43","CIDEr":"20.93","METEOR":"18.62"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.00681","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}