{"url":"/task/human-pose-forecasting","name":"Human Pose Forecasting","slug":"human-pose-forecasting","description_markdown":"Human pose forecasting is the task of detecting and predicting future human poses.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [EgoPose](https://github.com/Khrylx/EgoPose) )</span>","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":58,"papers_with_code":44,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"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":7,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/human-pose-forecasting-on-human36m","slug":"human-pose-forecasting-on-human36m","dataset":"Human3.6M","dataset_url":"/dataset/human3-6m","rows_in_archive":33,"metrics":["Average MPJPE (mm) @ 400ms","Average MPJPE (mm) @ 1000 ms","MAR, walking, 400ms","MAR, walking, 1,000ms","APD","ADE","FDE","MMADE","MMFDE","CMD","FID","Average NDMS at 4s "],"first_row_in_archive_order":{"model":"GCNext","paper_title":"GCNext: Towards the Unity of Graph Convolutions for Human Motion Prediction","paper_url":"/paper/gcnext-towards-the-unity-of-graph","paper_date":"2023-12-19","arxiv_id":"2312.11850","code_links":[{"title":"bradleywang0416/gcnext","url":"https://github.com/bradleywang0416/gcnext"}],"syntology":null}},{"leaderboard":"/sota/human-pose-forecasting-on-amass","slug":"human-pose-forecasting-on-amass","dataset":"AMASS","dataset_url":"/dataset/amass","rows_in_archive":11,"metrics":["Average MPJPE (mm) 1000 msec","FDE@1000ms (mm)","FDE@560ms (mm)","FDE@720ms (mm)","FDE@880ms (mm)","ADE","FDE","APD","APDE"],"first_row_in_archive_order":{"model":"STS-GCN","paper_title":"Space-Time-Separable Graph Convolutional Network for Pose Forecasting","paper_url":"/paper/space-time-separable-graph-convolutional-1","paper_date":"2021-10-09","arxiv_id":"2110.04573","code_links":[{"title":"fraluca/stsgcn","url":"https://github.com/fraluca/stsgcn"}],"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/human-pose-forecasting-on-humaneva-i","slug":"human-pose-forecasting-on-humaneva-i","dataset":"HumanEva-I","dataset_url":null,"rows_in_archive":11,"metrics":["APD@2000ms","ADE@2000ms","FDE@2000ms","MMADE@2000ms","MMFDE@2000ms"],"first_row_in_archive_order":{"model":"TCD","paper_title":"A generic diffusion-based approach for 3D human pose prediction in the wild","paper_url":"/paper/a-generic-diffusion-based-approach-for-3d","paper_date":"2022-10-11","arxiv_id":"2210.05669","code_links":[{"title":"vita-epfl/deposit","url":"https://github.com/vita-epfl/deposit"}],"syntology":null}},{"leaderboard":"/sota/human-pose-forecasting-on-3dpw","slug":"human-pose-forecasting-on-3dpw","dataset":"3DPW","dataset_url":"/dataset/3dpw","rows_in_archive":7,"metrics":["Average MPJPE (mm) 1000 msec","FDE@1000ms (mm)","FDE@560ms (mm)","FDE@720ms (mm)","FDE@880ms (mm)"],"first_row_in_archive_order":{"model":"STS-GCN","paper_title":"Space-Time-Separable Graph Convolutional Network for Pose Forecasting","paper_url":"/paper/space-time-separable-graph-convolutional-1","paper_date":"2021-10-09","arxiv_id":"2110.04573","code_links":[{"title":"fraluca/stsgcn","url":"https://github.com/fraluca/stsgcn"}],"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/human-pose-forecasting-on-gta-im-dataset","slug":"human-pose-forecasting-on-gta-im-dataset","dataset":"GTA-IM Dataset","dataset_url":"/dataset/gta-im-dataset","rows_in_archive":3,"metrics":["Path Error","Pose Error"],"first_row_in_archive_order":{"model":"Xing et al.","paper_title":"Scene-aware Human Motion Forecasting via Mutual Distance Prediction","paper_url":"/paper/scene-aware-human-motion-forecasting-via","paper_date":"2023-10-01","arxiv_id":"2310.00615","code_links":[{"title":"xccyue/MutualDistance","url":"https://github.com/xccyue/MutualDistance"}],"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":7}}},{"leaderboard":"/sota/human-pose-forecasting-on-harper","slug":"human-pose-forecasting-on-harper","dataset":"HARPER","dataset_url":"/dataset/harper","rows_in_archive":3,"metrics":["Average MPJPE (mm) @ 400ms","Average MPJPE (mm) @ 1000ms","Last Frame MPJPE (mm) @ 400ms","Last Frame MPJPE (mm) @ 1000ms"],"first_row_in_archive_order":{"model":"EqMotion","paper_title":"EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning","paper_url":"/paper/eqmotion-equivariant-multi-agent-motion","paper_date":"2023-03-20","arxiv_id":"2303.10876","code_links":[{"title":"mediabrain-sjtu/eqmotion","url":"https://github.com/mediabrain-sjtu/eqmotion"},{"title":"pranav-chib/trajimpute","url":"https://github.com/pranav-chib/trajimpute"}],"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/human-pose-forecasting-on-expi-common-actions","slug":"human-pose-forecasting-on-expi-common-actions","dataset":"Expi - common actions split","dataset_url":"/dataset/expi","rows_in_archive":1,"metrics":["Average MPJPE (mm) @ 200 ms"],"first_row_in_archive_order":{"model":"siMLPe","paper_title":"Back to MLP: A Simple Baseline for Human Motion Prediction","paper_url":"/paper/back-to-mlp-a-simple-baseline-for-human","paper_date":"2022-07-04","arxiv_id":"2207.01567","code_links":[{"title":"dulucas/simlpe","url":"https://github.com/dulucas/simlpe"}],"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/human3-6m","name":"Human3.6M","full_name":"","num_papers_in_archive":783},{"url":"/dataset/3dpw","name":"3DPW","full_name":"","num_papers_in_archive":395},{"url":"/dataset/amass","name":"AMASS","full_name":"","num_papers_in_archive":366},{"url":"/dataset/expi","name":"Expi","full_name":"Extreme Pose Interaction","num_papers_in_archive":16},{"url":"/dataset/gta-im-dataset","name":"GTA-IM Dataset","full_name":"GTA Indoor Motion","num_papers_in_archive":11},{"url":"/dataset/pats","name":"PATS","full_name":"Pose Audio Transcript Style","num_papers_in_archive":11},{"url":"/dataset/harper","name":"HARPER","full_name":"Exploring 3D Human Pose Estimation and Forecasting from the Robot’s Perspective: The HARPER Dataset","num_papers_in_archive":5}],"subtasks":[],"parent_tasks":[{"url":"/task/pose-estimation","name":"Pose Estimation"}],"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":30,"of":44,"tagged_in_all":58,"items":[{"url":"/paper/on-human-motion-prediction-using-recurrent","title":"On human motion prediction using recurrent neural networks","date":"2017-05-06","arxiv_id":"1705.02445","repositories_listed":8,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/learning-trajectory-dependencies-for-human","title":"Learning Trajectory Dependencies for Human Motion Prediction","date":"2019-08-15","arxiv_id":"1908.05436","repositories_listed":5,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/deep-unsupervised-clustering-with-gaussian","title":"Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders","date":"2016-11-08","arxiv_id":"1611.02648","repositories_listed":4,"syntology":null},{"url":"/paper/hp-gan-probabilistic-3d-human-motion","title":"HP-GAN: Probabilistic 3D human motion prediction via GAN","date":"2017-11-27","arxiv_id":"1711.09561","repositories_listed":3,"syntology":null},{"url":"/paper/eqmotion-equivariant-multi-agent-motion","title":"EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning","date":"2023-03-20","arxiv_id":"2303.10876","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/diverse-human-motion-prediction-via-gumbel","title":"Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space","date":"2022-07-15","arxiv_id":"2207.07351","repositories_listed":2,"syntology":null},{"url":"/paper/structural-rnn-deep-learning-on-spatio","title":"Structural-RNN: Deep Learning on Spatio-Temporal Graphs","date":"2015-11-17","arxiv_id":"1511.05298","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/motionmap-representing-multimodality-in-human","title":"MotionMap: Representing Multimodality in Human Pose Forecasting","date":"2024-12-25","arxiv_id":"2412.18883","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-long-term-3d-human-pose","title":"Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning","date":"2024-04-08","arxiv_id":"2404.05218","repositories_listed":1,"syntology":{"n":32,"n_ran":23,"n_unverified":9,"n_pointer_only":32}},{"url":"/paper/context-based-interpretable-spatio-temporal","title":"Context-based Interpretable Spatio-Temporal Graph Convolutional Network for Human Motion Forecasting","date":"2024-02-21","arxiv_id":"2402.19237","repositories_listed":1,"syntology":null},{"url":"/paper/expressive-forecasting-of-3d-whole-body-human","title":"Expressive Forecasting of 3D Whole-body Human Motions","date":"2023-12-19","arxiv_id":"2312.11972","repositories_listed":1,"syntology":null},{"url":"/paper/gcnext-towards-the-unity-of-graph","title":"GCNext: Towards the Unity of Graph Convolutions for Human Motion Prediction","date":"2023-12-19","arxiv_id":"2312.11850","repositories_listed":1,"syntology":null},{"url":"/paper/scene-aware-human-motion-forecasting-via","title":"Scene-aware Human Motion Forecasting via Mutual Distance Prediction","date":"2023-10-01","arxiv_id":"2310.00615","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":7}},{"url":"/paper/staged-contact-aware-global-human-motion","title":"Staged Contact-Aware Global Human Motion Forecasting","date":"2023-09-16","arxiv_id":"2309.08947","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":3}},{"url":"/paper/interdiff-generating-3d-human-object","title":"InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion","date":"2023-08-31","arxiv_id":"2308.16905","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/multiscale-residual-learning-of-graph","title":"Multiscale Residual Learning of Graph Convolutional Sequence Chunks for Human Motion Prediction","date":"2023-08-31","arxiv_id":"2308.16801","repositories_listed":1,"syntology":null},{"url":"/paper/auxiliary-tasks-benefit-3d-skeleton-based","title":"Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction","date":"2023-08-17","arxiv_id":"2308.08942","repositories_listed":1,"syntology":{"n":19,"n_ran":13,"n_unverified":6,"n_pointer_only":19}},{"url":"/paper/transfusion-a-practical-and-effective","title":"TransFusion: A Practical and Effective Transformer-based Diffusion Model for 3D Human Motion Prediction","date":"2023-07-30","arxiv_id":"2307.16106","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-motion-conditioned-diffusion-model","title":"Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection","date":"2023-07-14","arxiv_id":"2307.07205","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/toward-reliable-human-pose-forecasting-with","title":"Toward Reliable Human Pose Forecasting with Uncertainty","date":"2023-04-13","arxiv_id":"2304.06707","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":6}},{"url":"/paper/best-practices-for-2-body-pose-forecasting","title":"Best Practices for 2-Body Pose Forecasting","date":"2023-04-12","arxiv_id":"2304.05758","repositories_listed":1,"syntology":{"n":17,"n_ran":3,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/diverse-human-motion-prediction-guided-by","title":"Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors","date":"2023-02-09","arxiv_id":"2302.04860","repositories_listed":1,"syntology":null},{"url":"/paper/hdg-ode-a-hierarchical-continuous-time-model","title":"HDG-ODE: A Hierarchical Continuous-Time Model for Human Pose Forecasting","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/belfusion-latent-diffusion-for-behavior","title":"BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction","date":"2022-11-25","arxiv_id":"2211.14304","repositories_listed":1,"syntology":null},{"url":"/paper/a-generic-diffusion-based-approach-for-3d","title":"A generic diffusion-based approach for 3D human pose prediction in the wild","date":"2022-10-11","arxiv_id":"2210.05669","repositories_listed":1,"syntology":null},{"url":"/paper/contact-aware-human-motion-forecasting","title":"Contact-aware Human Motion Forecasting","date":"2022-10-08","arxiv_id":"2210.03954","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/somoformer-multi-person-pose-forecasting-with","title":"SoMoFormer: Multi-Person Pose Forecasting with Transformers","date":"2022-08-30","arxiv_id":"2208.14023","repositories_listed":1,"syntology":null},{"url":"/paper/pose-forecasting-in-industrial-human-robot","title":"Pose Forecasting in Industrial Human-Robot Collaboration","date":"2022-07-24","arxiv_id":"2208.07308","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_unverified":2,"n_pointer_only":4}},{"url":"/paper/back-to-mlp-a-simple-baseline-for-human","title":"Back to MLP: A Simple Baseline for Human Motion Prediction","date":"2022-07-04","arxiv_id":"2207.01567","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/motionmixer-mlp-based-3d-human-body-pose","title":"MotionMixer: MLP-based 3D Human Body Pose Forecasting","date":"2022-07-01","arxiv_id":"2207.00499","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}}],"syntology_records":16,"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"}}