{"url":"/task/human-motion-prediction","name":"Human motion prediction","slug":"human-motion-prediction","description_markdown":"Action prediction is a pre-fact video understanding task, which focuses on future states, in other words, it needs to reason about future states or infer action labels before the end of action execution.","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":162,"papers_with_code":68,"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":5,"subtasks":1,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/emdb","name":"EMDB","full_name":"","num_papers_in_archive":32},{"url":"/dataset/gta-im-dataset","name":"GTA-IM Dataset","full_name":"GTA Indoor Motion","num_papers_in_archive":11},{"url":"/dataset/mocapact","name":"MoCapAct","full_name":"Motion Capture with Actions","num_papers_in_archive":4},{"url":"/dataset/viena2","name":"VIENA2","full_name":"","num_papers_in_archive":4},{"url":"/dataset/nuisi-dataset","name":"NuiSI Dataset","full_name":"Nuitrack Skeleton Interaction Dataset","num_papers_in_archive":1}],"subtasks":[{"url":"/task/stochastic-human-motion-prediction","name":"Stochastic Human Motion Prediction"}],"parent_tasks":[{"url":"/task/trajectory-prediction","name":"Trajectory Prediction"}],"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":68,"tagged_in_all":162,"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/history-repeats-itself-human-motion","title":"History Repeats Itself: Human Motion Prediction via Motion Attention","date":"2020-07-23","arxiv_id":"2007.11755","repositories_listed":3,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/social-stgcnn-a-social-spatio-temporal-graph","title":"Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction","date":"2020-02-27","arxiv_id":"2002.11927","repositories_listed":3,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/bihmp-gan-bidirectional-3d-human-motion","title":"BiHMP-GAN: Bidirectional 3D Human Motion Prediction GAN","date":"2018-12-06","arxiv_id":"1812.02591","repositories_listed":3,"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/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/generative-model-enhanced-human-motion-1","title":"Generative Model-Enhanced Human Motion Prediction","date":"2020-10-05","arxiv_id":"2010.11699","repositories_listed":2,"syntology":{"n":10,"n_ran":6,"n_unverified":4,"n_pointer_only":3}},{"url":"/paper/peeking-into-the-future-predicting-future","title":"Peeking into the Future: Predicting Future Person Activities and Locations in Videos","date":"2019-02-11","arxiv_id":"1902.03748","repositories_listed":2,"syntology":{"n":27,"n_ran":2,"n_unverified":25,"n_pointer_only":22}},{"url":"/paper/stochastic-human-motion-prediction-with-1","title":"Stochastic Human Motion Prediction with Memory of Action Transition and Action Characteristic","date":"2025-07-05","arxiv_id":"2507.04062","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-continual-learning-with-prior-1","title":"Temporal Continual Learning with Prior Compensation for Human Motion Prediction","date":"2025-07-05","arxiv_id":"2507.04060","repositories_listed":1,"syntology":null},{"url":"/paper/multi-resolution-haar-network-enhancing-human","title":"Multi-Resolution Haar Network: Enhancing human motion prediction via Haar transform","date":"2025-05-19","arxiv_id":"2505.12631","repositories_listed":1,"syntology":null},{"url":"/paper/multi-transmotion-pre-trained-model-for-human","title":"Multi-Transmotion: Pre-trained Model for Human Motion Prediction","date":"2024-11-04","arxiv_id":"2411.02673","repositories_listed":1,"syntology":{"n":14,"n_ran":0,"n_unverified":14,"n_pointer_only":14}},{"url":"/paper/bad-bidirectional-auto-regressive-diffusion","title":"BAD: Bidirectional Auto-regressive Diffusion for Text-to-Motion Generation","date":"2024-09-17","arxiv_id":"2409.10847","repositories_listed":1,"syntology":null},{"url":"/paper/learning-semantic-latent-directions-for","title":"Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction","date":"2024-07-16","arxiv_id":"2407.11494","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/a-mixture-of-experts-approach-to-3d-human","title":"A Mixture of Experts Approach to 3D Human Motion Prediction","date":"2024-05-09","arxiv_id":"2405.06088","repositories_listed":1,"syntology":null},{"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/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/momask-generative-masked-modeling-of-3d-human","title":"MoMask: Generative Masked Modeling of 3D Human Motions","date":"2023-11-29","arxiv_id":"2312.00063","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/dynamic-compositional-graph-convolutional","title":"Dynamic Compositional Graph Convolutional Network for Efficient Composite Human Motion Prediction","date":"2023-11-23","arxiv_id":"2311.13781","repositories_listed":1,"syntology":null},{"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/spatio-temporal-branching-for-motion","title":"Spatio-Temporal Branching for Motion Prediction using Motion Increments","date":"2023-08-02","arxiv_id":"2308.01097","repositories_listed":1,"syntology":null},{"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/evaluating-adversarial-robustness-of","title":"Physics-constrained Attack against Convolution-based Human Motion Prediction","date":"2023-06-21","arxiv_id":"2306.11990","repositories_listed":1,"syntology":null},{"url":"/paper/stochastic-multi-person-3d-motion-forecasting","title":"Stochastic Multi-Person 3D Motion Forecasting","date":"2023-06-08","arxiv_id":"2306.05421","repositories_listed":1,"syntology":null},{"url":"/paper/towards-globally-consistent-stochastic-human","title":"CoMusion: Towards Consistent Stochastic Human Motion Prediction via Motion Diffusion","date":"2023-05-21","arxiv_id":"2305.12554","repositories_listed":1,"syntology":null},{"url":"/paper/a-neuro-symbolic-approach-for-enhanced-human","title":"A Neuro-Symbolic Approach for Enhanced Human Motion Prediction","date":"2023-04-23","arxiv_id":"2304.11740","repositories_listed":1,"syntology":null},{"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}],"syntology_records":11,"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"}}