{"url":"/task/image-paragraph-captioning","name":"Image Paragraph Captioning","slug":"image-paragraph-captioning","description_markdown":"Image paragraph captioning involves generating a detailed, multi-sentence description of the content of an image.","categories":[{"name":"Graphs","url":"/area/graphs"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":17,"papers_with_code":5,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/image-paragraph-captioning-on-image-paragraph","slug":"image-paragraph-captioning-on-image-paragraph","dataset":"Image Paragraph Captioning","dataset_url":"/dataset/image-paragraph-captioning","rows_in_archive":10,"metrics":["BLEU-4","METEOR","CIDEr"],"first_row_in_archive_order":{"model":"HSGED(SLL)","paper_title":"Hierarchical Scene Graph Encoder-Decoder for Image Paragraph Captioning","paper_url":"/paper/hierarchical-scene-graph-encoder-decoder-for","paper_date":"2020-10-12","arxiv_id":null,"code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/image-paragraph-captioning","name":"Image Paragraph Captioning","full_name":"","num_papers_in_archive":31}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":5,"of":5,"tagged_in_all":17,"items":[{"url":"/paper/a-hierarchical-approach-for-generating","title":"A Hierarchical Approach for Generating Descriptive Image Paragraphs","date":"2016-11-20","arxiv_id":"1611.06607","repositories_listed":3,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/vlis-unimodal-language-models-guide","title":"VLIS: Unimodal Language Models Guide Multimodal Language Generation","date":"2023-10-15","arxiv_id":"2310.09767","repositories_listed":1,"syntology":null},{"url":"/paper/matching-visual-features-to-hierarchical","title":"Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioning","date":"2021-05-10","arxiv_id":"2105.04143","repositories_listed":1,"syntology":null},{"url":"/paper/context-aware-visual-policy-network-for-fine","title":"Context-Aware Visual Policy Network for Fine-Grained Image Captioning","date":"2019-06-06","arxiv_id":"1906.02365","repositories_listed":1,"syntology":null},{"url":"/paper/training-for-diversity-in-image-paragraph","title":"Training for Diversity in Image Paragraph Captioning","date":"2018-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":1,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}