{"url":"/dataset/expi","name":"Expi","full_name":"Extreme Pose Interaction","description_markdown":"Extreme Pose Interaction (ExPI) Dataset is a new person interaction dataset of Lindy Hop dancing actions. In Lindy Hop, the two dancers are called leader and\r\nfollower. The authors recorded two couples of dancers in a multi-camera setup equipped also with a motion-capture system.\r\n16 different actions are performed in ExPI dataset, some by the two couples of dancers, some by only one of the couples. Each action was repeated five times\r\nto account for variability. More precisely, for each recorded sequence, ExPI provides: \r\n(i) Multi-view videos at 25FPS from all the cameras in the recording setup; \r\n(ii) Mocap data (3D position of 18 joints for each person) at 25FPS synchronized with the videos.; \r\n(iii) camera calibration information; and (iv) 3D shapes as textured meshes for each frame.\r\n\r\nOverall, the dataset contains 115 sequences with 30k visual frames for each viewpoint and 60k 3D instances annotated","description_withheld":null,"homepage":"https://github.com/GUO-W/MultiMotion","introduced_date":"2021-05-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/multi-person-extreme-motion-prediction-with","title":"Multi-Person Extreme Motion Prediction","first_author":"Wen Guo","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Tracking","url":"/datasets/modality/tracking"}],"tasks":[{"name":"Human Pose Forecasting","url":"/task/human-pose-forecasting","datasets_with_task":"/datasets/task/human-pose-forecasting"},{"name":"Pose Prediction","url":"/task/pose-prediction","datasets_with_task":"/datasets/task/pose-prediction"},{"name":"Multi-Person Pose forecasting","url":"/task/multi-person-pose-forecasting","datasets_with_task":"/datasets/task/multi-person-pose-forecasting"},{"name":"motion prediction","url":"/task/motion-prediction","datasets_with_task":"/datasets/task/motion-prediction"}],"languages":[],"variants":["Expi","Expi - common actions split","Expi - unseen actions split"],"data_loaders":[],"num_papers_in_archive":16,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multi-person-pose-forecasting-on-expi-common","task":"Multi-Person Pose forecasting","dataset_variant":"Expi - common actions split","rows":6,"metrics":["Average MPJPE (mm) @ 1000 ms","Average MPJPE (mm) @ 200 ms","Average MPJPE (mm) @ 400 ms","Average MPJPE (mm) @ 600 ms"],"first_row_in_archive_order":{"model":"Best Practices for 2-Body Pose Forecasting","paper":"/paper/best-practices-for-2-body-pose-forecasting","metrics":{"Average MPJPE (mm) @ 1000 ms":"202","Average MPJPE (mm) @ 200 ms":"39","Average MPJPE (mm) @ 400 ms":"86","Average MPJPE (mm) @ 600 ms":"129"},"code_links":[{"title":"edodema/BestPractices2Body","url":"https://github.com/edodema/BestPractices2Body"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multi-person-pose-forecasting-on-expi-unseen","task":"Multi-Person Pose forecasting","dataset_variant":"Expi - unseen actions split","rows":5,"metrics":["Average MPJPE (mm) @ 400 ms","Average MPJPE (mm) @ 600 ms","Average MPJPE (mm) @ 800 ms"],"first_row_in_archive_order":{"model":"Best Practices for 2-Body Pose Forecasting","paper":"/paper/best-practices-for-2-body-pose-forecasting","metrics":{"Average MPJPE (mm) @ 400 ms":"100","Average MPJPE (mm) @ 600 ms":"149","Average MPJPE (mm) @ 800 ms":"191"},"code_links":[{"title":"edodema/BestPractices2Body","url":"https://github.com/edodema/BestPractices2Body"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/human-pose-forecasting-on-expi-common-actions","task":"Human Pose Forecasting","dataset_variant":"Expi - common actions split","rows":1,"metrics":["Average MPJPE (mm) @ 200 ms"],"first_row_in_archive_order":{"model":"siMLPe","paper":"/paper/back-to-mlp-a-simple-baseline-for-human","metrics":{"Average MPJPE (mm) @ 200 ms":"80"},"code_links":[{"title":"dulucas/simlpe","url":"https://github.com/dulucas/simlpe"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/pgformer-proxy-bridged-game-transformer-for","title":"PGformer: Proxy-Bridged Game Transformer for Multi-Person Highly Interactive Extreme Motion Prediction","date":"2023-06-06","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/best-practices-for-2-body-pose-forecasting","title":"Best Practices for 2-Body Pose Forecasting","date":"2023-04-12","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":17,"samples_ran":3,"samples_unverified":14,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/back-to-mlp-a-simple-baseline-for-human","title":"Back to MLP: A Simple Baseline for Human Motion Prediction","date":"2022-07-04","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":3,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/multi-person-3d-motion-prediction-with-multi-1","title":"Multi-Person 3D Motion Prediction with Multi-Range Transformers","date":"2021-11-23","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/multi-person-extreme-motion-prediction-with","title":"Multi-Person Extreme Motion Prediction","date":"2021-05-18","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-trajectory-dependencies-for-human","title":"Learning Trajectory Dependencies for Human Motion Prediction","date":"2019-08-15","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":0,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":4,"samples_harvested":30,"samples_ran":9,"samples_unverified":21,"pointer_only_for_licence":3,"papers_with_no_sample_that_ran":1,"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."}