{"url":"/dataset/open-hypermotionx","name":"Open-HypermotionX","full_name":null,"description_markdown":"## 🏃‍♂️ Open-HypermotionX Dataset\r\n\r\n**Open-Hypermotion** is a large-scale, high-quality dataset designed for training and evaluating **pose-guided human image animation** models, with a special focus on **complex, dynamic human motions** (*Hypermotion*), such as flips, spins, and acrobatics.\r\n\r\n### 🔍 Key Features\r\n\r\n- **Multimodal Annotations**:\r\n  - 2D human **pose sequences**\r\n  - **Reference images** for appearance control\r\n  - **Video clips** of target motions\r\n  - **Text descriptions** of actions\r\n- **Motion Diversity**:\r\n  - Covers both common activities and high-difficulty dynamic actions\r\n- **Task-Specific Subsets**:\r\n  - Pose-guided animation","description_withheld":null,"homepage":"https://vivocameraresearch.github.io/hypermotion/","introduced_date":"2018-12-31","introduced_date_note":null,"introduced_by":null,"license":{"name":"LICENSE-2.0","url":"http://www.apache.org/licenses/LICENSE-2.0"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Video Generation","url":"/task/video-generation","datasets_with_task":"/datasets/task/video-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Open-HypermotionX"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}