{"url":"/task/motion-captioning","name":"Motion Captioning","slug":"motion-captioning","description_markdown":"Generating textual description for human motion.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":11,"papers_with_code":6,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"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":2,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/motion-captioning-on-humanml3d","slug":"motion-captioning-on-humanml3d","dataset":"HumanML3D","dataset_url":"/dataset/humanml3d","rows_in_archive":4,"metrics":["BLEU-4","BERTScore"],"first_row_in_archive_order":{"model":"ST-MLP","paper_title":"Guided Attention for Interpretable Motion Captioning","paper_url":"/paper/guided-attention-for-interpretable-motion","paper_date":"2023-10-11","arxiv_id":"2310.07324","code_links":[{"title":"rd20karim/m2t-interpretable","url":"https://github.com/rd20karim/m2t-interpretable"}],"syntology":null}},{"leaderboard":"/sota/motion-captioning-on-kit-motion-language","slug":"motion-captioning-on-kit-motion-language","dataset":"KIT Motion-Language","dataset_url":"/dataset/kit-motion-language","rows_in_archive":3,"metrics":["BLEU-4","BERTScore"],"first_row_in_archive_order":{"model":"MLP+GRU","paper_title":"Motion2Language, unsupervised learning of synchronized semantic motion segmentation","paper_url":"/paper/motion2language-unsupervised-learning-of","paper_date":"2023-10-16","arxiv_id":"2310.10594","code_links":[{"title":"rd20karim/M2T-Segmentation","url":"https://github.com/rd20karim/M2T-Segmentation"}],"syntology":null}}],"datasets":[{"url":"/dataset/humanml3d","name":"HumanML3D","full_name":"","num_papers_in_archive":201},{"url":"/dataset/kit-motion-language","name":"KIT Motion-Language","full_name":"","num_papers_in_archive":48}],"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":6,"of":6,"tagged_in_all":11,"items":[{"url":"/paper/motiongpt-human-motion-as-a-foreign-language","title":"MotionGPT: Human Motion as a Foreign Language","date":"2023-06-26","arxiv_id":"2306.14795","repositories_listed":3,"syntology":{"n":9,"n_ran":1,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/transformer-with-controlled-attention-for","title":"Transformer with Controlled Attention for Synchronous Motion Captioning","date":"2024-09-13","arxiv_id":"2409.09177","repositories_listed":1,"syntology":null},{"url":"/paper/motionllm-multimodal-motion-language-learning","title":"Motion-Agent: A Conversational Framework for Human Motion Generation with LLMs","date":"2024-05-27","arxiv_id":"2405.17013","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/motion2language-unsupervised-learning-of","title":"Motion2Language, unsupervised learning of synchronized semantic motion segmentation","date":"2023-10-16","arxiv_id":"2310.10594","repositories_listed":1,"syntology":null},{"url":"/paper/guided-attention-for-interpretable-motion","title":"Guided Attention for Interpretable Motion Captioning","date":"2023-10-11","arxiv_id":"2310.07324","repositories_listed":1,"syntology":null},{"url":"/paper/tm2t-stochastic-and-tokenized-modeling-for","title":"TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts","date":"2022-07-04","arxiv_id":"2207.01696","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_unverified":2,"n_pointer_only":1}}],"syntology_records":3,"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"}}