{"url":"/task/pose-prediction","name":"Pose Prediction","slug":"pose-prediction","description_markdown":"Pose prediction is to predict future poses given a window of previous poses.","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":163,"papers_with_code":70,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"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":8,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/pose-prediction-on-filtered-ntu-rgbd","slug":"pose-prediction-on-filtered-ntu-rgbd","dataset":"Filtered NTU RGB+D","dataset_url":"/dataset/ntu-rgb-d","rows_in_archive":3,"metrics":["MSE","MAE"],"first_row_in_archive_order":{"model":"PISEP^2 (L1 norm)","paper_title":"PISEP^2: Pseudo Image Sequence Evolution based 3D Pose Prediction","paper_url":"/paper/pisep2-pseudo-image-sequence-evolution-based","paper_date":"2019-09-04","arxiv_id":"1909.01818","code_links":[],"syntology":null}},{"leaderboard":"/sota/pose-prediction-on-gaming-3d-g3d","slug":"pose-prediction-on-gaming-3d-g3d","dataset":"Gaming 3D (G3D)","dataset_url":"/dataset/g3d","rows_in_archive":2,"metrics":["MSE","MAE"],"first_row_in_archive_order":{"model":"PISEP^2 (L1 norm)","paper_title":"PISEP^2: Pseudo Image Sequence Evolution based 3D Pose Prediction","paper_url":"/paper/pisep2-pseudo-image-sequence-evolution-based","paper_date":"2019-09-04","arxiv_id":"1909.01818","code_links":[],"syntology":null}},{"leaderboard":"/sota/pose-prediction-on-sun-mem","slug":"pose-prediction-on-sun-mem","dataset":"SUN-Mem","dataset_url":null,"rows_in_archive":1,"metrics":["AP50","AUPRC","AUROC"],"first_row_in_archive_order":{"model":"TIP-sum PPM-GGM-DDM-DF","paper_title":"Tri-graph Information Propagation for Polypharmacy Side Effect Prediction","paper_url":"/paper/tri-graph-information-propagation-for","paper_date":"2020-01-28","arxiv_id":"2001.10516","code_links":[{"title":"NYXFLOWER/TIP","url":"https://github.com/NYXFLOWER/TIP"}],"syntology":null}}],"datasets":[{"url":"/dataset/ntu-rgb-d","name":"NTU RGB+D","full_name":"","num_papers_in_archive":476},{"url":"/dataset/g3d","name":"G3D","full_name":"Gaming 3D Dataset","num_papers_in_archive":28},{"url":"/dataset/expi","name":"Expi","full_name":"Extreme Pose Interaction","num_papers_in_archive":16},{"url":"/dataset/sportspose","name":"SportsPose","full_name":"SportsPose - A Dynamic 3D sports pose dataset","num_papers_in_archive":4},{"url":"/dataset/drunkard-s-dataset","name":"Drunkard's Dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/vrmocap-vr-mocap-dataset-for-pose","name":"VRMocap: VR Mocap Dataset for Pose Reconstruction","full_name":"","num_papers_in_archive":2},{"url":"/dataset/vr-mocap","name":"VR Mocap Dataset for Pose/Orientation Prediction","full_name":"","num_papers_in_archive":1},{"url":"/dataset/infiniterep","name":"InfiniteRep","full_name":"InfiniteRep","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/3d-human-pose-estimation","name":"3D Human 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":70,"tagged_in_all":163,"items":[{"url":"/paper/bottom-up-higher-resolution-networks-for","title":"HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation","date":"2019-08-27","arxiv_id":"1908.10357","repositories_listed":19,"syntology":{"n":27,"n_ran":5,"n_unverified":22,"n_pointer_only":0}},{"url":"/paper/estimating-6d-pose-from-localizing-designated","title":"Estimating 6D Pose From Localizing Designated Surface Keypoints","date":"2018-12-04","arxiv_id":"1812.01387","repositories_listed":6,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/towards-3d-human-pose-estimation-in-the-wild","title":"Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach","date":"2017-04-08","arxiv_id":"1704.02447","repositories_listed":6,"syntology":null},{"url":"/paper/segmentation-driven-6d-object-pose-estimation","title":"Segmentation-driven 6D Object Pose Estimation","date":"2018-12-06","arxiv_id":"1812.02541","repositories_listed":5,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/real-time-seamless-single-shot-6d-object-pose","title":"Real-Time Seamless Single Shot 6D Object Pose Prediction","date":"2017-11-24","arxiv_id":"1711.08848","repositories_listed":5,"syntology":null},{"url":"/paper/ho-3d-a-multi-user-multi-object-dataset-for","title":"HOnnotate: A method for 3D Annotation of Hand and Object Poses","date":"2019-07-02","arxiv_id":"1907.01481","repositories_listed":4,"syntology":null},{"url":"/paper/uni-mol-docking-v2-towards-realistic-and","title":"Uni-Mol Docking V2: Towards Realistic and Accurate Binding Pose Prediction","date":"2024-05-20","arxiv_id":"2405.11769","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/pharmaconet-accelerating-structure-based","title":"PharmacoNet: Accelerating Large-Scale Virtual Screening by Deep Pharmacophore Modeling","date":"2023-10-01","arxiv_id":"2310.00681","repositories_listed":3,"syntology":{"n":8,"n_ran":8,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/animal-avatars-reconstructing-animatable-3d","title":"Animal Avatars: Reconstructing Animatable 3D Animals from Casual Videos","date":"2024-03-25","arxiv_id":"2403.17103","repositories_listed":2,"syntology":null},{"url":"/paper/towards-robust-and-unconstrained-full-range","title":"Towards Robust and Unconstrained Full Range of Rotation Head Pose Estimation","date":"2023-09-14","arxiv_id":"2309.07654","repositories_listed":2,"syntology":null},{"url":"/paper/act3d-infinite-resolution-action-detection","title":"Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation","date":"2023-06-30","arxiv_id":"2306.17817","repositories_listed":2,"syntology":null},{"url":"/paper/6d-rotation-representation-for-unconstrained","title":"6D Rotation Representation For Unconstrained Head Pose Estimation","date":"2022-02-25","arxiv_id":"2202.12555","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_unverified":3,"n_pointer_only":3}},{"url":"/paper/unsupervised-part-based-disentangling-of","title":"Unsupervised Part-Based Disentangling of Object Shape and Appearance","date":"2019-03-16","arxiv_id":"1903.06946","repositories_listed":2,"syntology":null},{"url":"/paper/3d-hand-shape-and-pose-from-images-in-the","title":"3D Hand Shape and Pose from Images in the Wild","date":"2019-02-09","arxiv_id":"1902.03451","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/protein-ligand-scoring-with-convolutional","title":"Protein-Ligand Scoring with Convolutional Neural Networks","date":"2016-12-08","arxiv_id":"1612.02751","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"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/exploring-mutual-cross-modal-attention-for","title":"Exploring Mutual Cross-Modal Attention for Context-Aware Human Affordance Generation","date":"2025-02-19","arxiv_id":"2502.13637","repositories_listed":1,"syntology":null},{"url":"/paper/gapartmanip-a-large-scale-part-centric","title":"GAPartManip: A Large-scale Part-centric Dataset for Material-Agnostic Articulated Object Manipulation","date":"2024-11-27","arxiv_id":"2411.18276","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/quickbind-a-light-weight-and-interpretable","title":"QuickBind: A Light-Weight And Interpretable Molecular Docking Model","date":"2024-10-21","arxiv_id":"2410.16474","repositories_listed":1,"syntology":null},{"url":"/paper/sparse-prototype-network-for-explainable","title":"Sparse Prototype Network for Explainable Pedestrian Behavior Prediction","date":"2024-10-16","arxiv_id":"2410.12195","repositories_listed":1,"syntology":null},{"url":"/paper/assessing-interaction-recovery-of-predicted","title":"Assessing interaction recovery of predicted protein-ligand poses","date":"2024-09-30","arxiv_id":"2409.20227","repositories_listed":1,"syntology":null},{"url":"/paper/geometric-transformation-uncertainty-for","title":"Geometric Transformation Uncertainty for Improving 3D Fetal Brain Pose Prediction from Freehand 2D Ultrasound Videos","date":"2024-05-21","arxiv_id":"2405.13235","repositories_listed":1,"syntology":null},{"url":"/paper/deep-se-3-equivariant-geometric-reasoning-for","title":"Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks","date":"2024-04-20","arxiv_id":"2404.13478","repositories_listed":1,"syntology":{"n":22,"n_ran":13,"n_unverified":9,"n_pointer_only":1}},{"url":"/paper/deeprli-a-multi-objective-framework-for","title":"DeepRLI: A Multi-objective Framework for Universal Protein--Ligand Interaction Prediction","date":"2024-01-19","arxiv_id":"2401.10806","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-ligand-pose-sampling-for-molecular","title":"Enhancing Ligand Pose Sampling for Molecular Docking","date":"2023-11-30","arxiv_id":"2312.00191","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/diffbind-a-se-3-equivariant-network-for","title":"DiffBindFR: An SE(3) Equivariant Network for Flexible Protein-Ligand Docking","date":"2023-11-26","arxiv_id":"2311.15201","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_unverified":2,"n_pointer_only":15}},{"url":"/paper/simcol3d-3d-reconstruction-during-colonoscopy","title":"SimCol3D -- 3D Reconstruction during Colonoscopy Challenge","date":"2023-07-20","arxiv_id":"2307.11261","repositories_listed":1,"syntology":null},{"url":"/paper/seeing-the-pose-in-the-pixels-learning-pose","title":"Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformers","date":"2023-06-15","arxiv_id":"2306.09331","repositories_listed":1,"syntology":null},{"url":"/paper/aria-digital-twin-a-new-benchmark-dataset-for","title":"Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception","date":"2023-06-10","arxiv_id":"2306.06362","repositories_listed":1,"syntology":null}],"syntology_records":12,"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"}}