{"url":"/task/controllable-image-captioning","name":"controllable image captioning","slug":"controllable-image-captioning","description_markdown":"generate image captions conditioned on control signals","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":14,"papers_with_code":8,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/image-captioning","name":"Image Captioning"}],"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":8,"of":8,"tagged_in_all":14,"items":[{"url":"/paper/from-simple-to-professional-a-combinatorial","title":"From Simple to Professional: A Combinatorial Controllable Image Captioning Agent","date":"2024-12-15","arxiv_id":"2412.11025","repositories_listed":1,"syntology":null},{"url":"/paper/cic-bart-ssa-controllable-image-captioning","title":"CIC-BART-SSA: Controllable Image Captioning with Structured Semantic Augmentation","date":"2024-07-16","arxiv_id":"2407.11393","repositories_listed":1,"syntology":null},{"url":"/paper/caption-anything-interactive-image","title":"Caption Anything: Interactive Image Description with Diverse Multimodal Controls","date":"2023-05-04","arxiv_id":"2305.02677","repositories_listed":1,"syntology":{"n":10,"n_ran":3,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/clid-controlled-length-image-descriptions","title":"CLID: Controlled-Length Image Descriptions with Limited Data","date":"2022-11-27","arxiv_id":"2211.14835","repositories_listed":1,"syntology":null},{"url":"/paper/human-like-controllable-image-captioning-with","title":"Human-like Controllable Image Captioning with Verb-specific Semantic Roles","date":"2021-03-22","arxiv_id":"2103.12204","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/language-driven-region-pointer-advancement","title":"Language-Driven Region Pointer Advancement for Controllable Image Captioning","date":"2020-11-30","arxiv_id":"2011.14901","repositories_listed":1,"syntology":null},{"url":"/paper/length-controllable-image-captioning","title":"Length-Controllable Image Captioning","date":"2020-07-19","arxiv_id":"2007.09580","repositories_listed":1,"syntology":null},{"url":"/paper/show-control-and-tell-a-framework-for","title":"Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions","date":"2018-11-26","arxiv_id":"1811.10652","repositories_listed":1,"syntology":null}],"syntology_records":2,"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"}}