{"url":"/dataset/ntu-rgb-d-120","name":"NTU RGB+D 120","full_name":null,"description_markdown":"NTU RGB+D 120 is a large-scale dataset for RGB+D human action recognition, which is collected from 106 distinct subjects and contains more than 114 thousand video samples and 8 million frames. This dataset contains 120 different action classes including daily, mutual, and health-related activities. \r\n\r\nSource: [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://arxiv.org/pdf/1905.04757v2.pdf)","description_withheld":null,"homepage":"http://rose1.ntu.edu.sg/Datasets/actionRecognition.asp","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/ntu-rgbd-120-a-large-scale-benchmark-for-3d","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","first_author":"Jun Liu","url":null},"license":{"name":"Custom (research-only)","url":"http://rose1.ntu.edu.sg/Datasets/actionRecognition.asp"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"Action Recognition","url":"/task/action-recognition-in-videos","datasets_with_task":"/datasets/task/action-recognition-in-videos"},{"name":"Skeleton Based Action Recognition","url":"/task/skeleton-based-action-recognition","datasets_with_task":"/datasets/task/skeleton-based-action-recognition"},{"name":"Human Interaction Recognition","url":"/task/human-interaction-recognition","datasets_with_task":"/datasets/task/human-interaction-recognition"},{"name":"Human action generation","url":"/task/human-action-generation","datasets_with_task":"/datasets/task/human-action-generation"},{"name":"Zero Shot Skeletal Action Recognition","url":"/task/zero-shot-skeletal-action-recognition","datasets_with_task":"/datasets/task/zero-shot-skeletal-action-recognition"},{"name":"Generalized Zero Shot skeletal action recognition","url":"/task/generalized-zero-shot-skeletal-action","datasets_with_task":"/datasets/task/generalized-zero-shot-skeletal-action"},{"name":"Unsupervised Skeleton Based Action Recognition","url":"/task/unsupervised-skeleton-based-action","datasets_with_task":"/datasets/task/unsupervised-skeleton-based-action"},{"name":"Self-supervised Skeleton-based Action Recognition","url":"/task/self-supervised-skeleton-based-action","datasets_with_task":"/datasets/task/self-supervised-skeleton-based-action"},{"name":"One-Shot 3D Action Recognition","url":"/task/one-shot-3d-action-recognition","datasets_with_task":"/datasets/task/one-shot-3d-action-recognition"},{"name":"Self-Supervised Human Action Recognition","url":"/task/self-supervised-human-action-recognition","datasets_with_task":"/datasets/task/self-supervised-human-action-recognition"},{"name":"Few-Shot Skeleton-Based Action Recognition","url":"/task/few-shot-skeleton-based-action-recognition","datasets_with_task":"/datasets/task/few-shot-skeleton-based-action-recognition"}],"languages":[],"variants":["NTU RGB+D 120"],"data_loaders":[{"repo":"https://github.com/WoominM/DeGCN_pytorch","url":"https://github.com/WoominM/DeGCN_pytorch","frameworks":["pytorch"]}],"num_papers_in_archive":137,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/skeleton-based-action-recognition-on-ntu-rgbd-1","task":"Skeleton Based Action Recognition","dataset_variant":"NTU RGB+D 120","rows":83,"metrics":["Accuracy (Cross-Subject)","Accuracy (Cross-Setup)","Ensembled Modalities","GFLOPS per prediction"],"first_row_in_archive_order":{"model":"ProtoGCN","paper":"/paper/revealing-key-details-to-see-differences-a","metrics":{"Accuracy (Cross-Setup)":"92.2","Accuracy (Cross-Subject)":"90.9","Ensembled Modalities":"6"},"code_links":[{"title":"firework8/ProtoGCN","url":"https://github.com/firework8/ProtoGCN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/action-recognition-in-videos-on-ntu-rgbd-120","task":"Action Recognition","dataset_variant":"NTU RGB+D 120","rows":21,"metrics":["Accuracy (Cross-Setup)","Accuracy (Cross-Subject)"],"first_row_in_archive_order":{"model":"DSCNet (RGB + Pose)","paper":"/paper/a-dense-sparse-complementary-network-for","metrics":{"Accuracy (Cross-Setup)":"96.7","Accuracy (Cross-Subject)":"95.6"},"code_links":[{"title":"Maxchengqin/DSCNet","url":"https://github.com/Maxchengqin/DSCNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/one-shot-3d-action-recognition-on-ntu-rgbd","task":"One-Shot 3D Action Recognition","dataset_variant":"NTU RGB+D 120","rows":10,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PGFA","paper":"/paper/zero-shot-skeleton-based-action-recognition-2","metrics":{"Accuracy":"69.8%"},"code_links":[{"title":"kaai520/PGFA","url":"https://github.com/kaai520/PGFA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/zero-shot-skeletal-action-recognition-on-ntu-1","task":"Zero Shot Skeletal Action Recognition","dataset_variant":"NTU RGB+D 120","rows":9,"metrics":["Accuracy (10 unseen classes)","Accuracy (24 unseen classes)","Random Split Accuracy"],"first_row_in_archive_order":{"model":"PGFA","paper":"/paper/zero-shot-skeleton-based-action-recognition-2","metrics":{"Accuracy (10 unseen classes)":"79.99","Accuracy (24 unseen classes)":"59.42","Random Split Accuracy":"71.38"},"code_links":[{"title":"kaai520/PGFA","url":"https://github.com/kaai520/PGFA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/self-supervised-human-action-recognition-on","task":"Self-Supervised Human Action Recognition","dataset_variant":"NTU RGB+D 120","rows":8,"metrics":["xsub (%)","xset (%)","Encoder","Classifier"],"first_row_in_archive_order":{"model":"CMCS","paper":"/paper/cross-model-cross-stream-learning-for-self","metrics":{"Classifier":"FC","Encoder":"ST-GCN","xset (%)":"71.7","xsub (%)":"68.5"},"code_links":[{"title":"Levigty/CMCS","url":"https://github.com/Levigty/CMCS"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/human-interaction-recognition-on-ntu-rgb-d-1","task":"Human Interaction Recognition","dataset_variant":"NTU RGB+D 120","rows":6,"metrics":["Accuracy (Cross-Setup)","Accuracy (Cross-Subject)"],"first_row_in_archive_order":{"model":"SkateFormer","paper":"/paper/skateformer-skeletal-temporal-transformer-for","metrics":{"Accuracy (Cross-Setup)":"93.2","Accuracy (Cross-Subject)":"92.3"},"code_links":[{"title":"KAIST-VICLab/SkateFormer","url":"https://github.com/KAIST-VICLab/SkateFormer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/generalized-zero-shot-skeletal-action-1","task":"Generalized Zero Shot skeletal action recognition","dataset_variant":"NTU RGB+D 120","rows":4,"metrics":["Harmonic Mean (10 unseen classes)","Harmonic Mean (24 unseen classes)","Random Split Harmonic Mean"],"first_row_in_archive_order":{"model":"SA-DVAE","paper":"/paper/sa-dvae-improving-zero-shot-skeleton-based","metrics":{"Harmonic Mean (10 unseen classes)":"60.42","Harmonic Mean (24 unseen classes)":"44.50","Random Split Harmonic Mean":"47.54"},"code_links":[{"title":"pha123661/SA-DVAE","url":"https://github.com/pha123661/SA-DVAE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/human-action-generation-on-ntu-rgb-d-120","task":"Human action generation","dataset_variant":"NTU RGB+D 120","rows":2,"metrics":["FID (CS)","FID (CV)"],"first_row_in_archive_order":{"model":"Kinetic-GAN","paper":"/paper/generative-adversarial-graph-convolutional","metrics":{"FID (CS)":"5.967","FID (CV)":"6.751"},"code_links":[{"title":"degardinbruno/kinetic-gan","url":"https://github.com/degardinbruno/kinetic-gan"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/zero-shot-skeleton-based-action-recognition-2","title":"Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment","date":"2025-07-01","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/skeletonx-data-efficient-skeleton-based","title":"SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature Aggregation","date":"2025-04-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dstsa-gcn-advancing-skeleton-based-gesture","title":"DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling","date":"2025-01-21","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/msa-gcn-exploiting-multi-scale-temporal","title":"MSA-GCN: Exploiting Multi-Scale Temporal Dynamics With Adaptive Graph Convolution for Skeleton-Based Action Recognition","date":"2024-12-19","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/usdrl-unified-skeleton-based-dense","title":"USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation","date":"2024-12-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/revealing-key-details-to-see-differences-a","title":"Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition","date":"2024-11-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tdsm-triplet-diffusion-for-skeleton-text","title":"TDSM: Triplet Diffusion for Skeleton-Text Matching in Zero-Shot Action Recognition","date":"2024-11-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/joint-mixing-data-augmentation-for-skeleton","title":"Joint Mixing Data Augmentation for Skeleton-based Action Recognition","date":"2024-10-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/chase-learning-convex-hull-adaptive-shift-for","title":"CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition","date":"2024-10-09","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cross-model-cross-stream-learning-for-self","title":"Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition","date":"2024-09-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/epam-net-an-efficient-pose-driven-attention","title":"EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition","date":"2024-08-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/joint-partition-group-attention-for-skeleton","title":"Joint-Partition Group Attention for skeleton-based action recognition","date":"2024-07-30","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/multi-modality-co-learning-for-efficient-1","title":"Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition","date":"2024-07-22","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":9,"samples_unverified":1,"pointer_only_for_licence":10,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/sa-dvae-improving-zero-shot-skeleton-based","title":"SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders","date":"2024-07-18","rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/shap-mix-shapley-value-guided-mixing-for-long","title":"Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognition","date":"2024-07-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/part-aware-unified-representation-of-language-1","title":"Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition","date":"2024-06-19","rows_on_this_dataset":1,"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":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/fine-grained-side-information-guided-dual","title":"Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognition","date":"2024-04-11","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/llms-are-good-action-recognizers","title":"LLMs are Good Action Recognizers","date":"2024-03-31","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/skateformer-skeletal-temporal-transformer-for","title":"SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition","date":"2024-03-14","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":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/explore-human-parsing-modality-for-action-1","title":"Explore Human Parsing Modality for Action Recognition","date":"2024-01-04","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":7,"samples_unverified":3,"pointer_only_for_licence":10,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/maskclr-attention-guided-contrastive-learning","title":"MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning","date":"2024-01-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/blockgcn-redefine-topology-awareness-for","title":"BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition","date":"2024-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-dense-sparse-complementary-network-for","title":"A Dense-Sparse Complementary Network for Human Action Recognition based on RGB and Skeleton Modalities","date":"2023-12-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dvanet-disentangling-view-and-action-features","title":"DVANet: Disentangling View and Action Features for Multi-View Action Recognition","date":"2023-12-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/step-catformer-spatial-temporal-effective","title":"STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action Recognition","date":"2023-12-06","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":10,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/just-add-p-pose-induced-video-transformers","title":"Just Add $π$! Pose Induced Video Transformers for Understanding Activities of Daily Living","date":"2023-11-30","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/multi-semantic-fusion-model-for-generalized","title":"Multi-Semantic Fusion Model for Generalized Zero-Shot Skeleton-Based Action Recognition","date":"2023-09-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/masked-motion-predictors-are-strong-3d-action","title":"Masked Motion Predictors are Strong 3D Action Representation Learners","date":"2023-08-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/zero-shot-skeleton-based-action-recognition","title":"Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization","date":"2023-08-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/integrating-human-parsing-and-pose-network","title":"Integrating Human Parsing and Pose Network for Human Action Recognition","date":"2023-07-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/interactive-spatiotemporal-token-attention","title":"Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition","date":"2023-07-14","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/action-recognition-with-multi-stream-motion","title":"Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization","date":"2023-06-13","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/language-knowledge-assisted-representation","title":"Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition","date":"2023-05-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-scale-spatial-temporal-convolutional","title":"Multi-scale spatial–temporal convolutional neural network for skeleton-based action recognition","date":"2023-05-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tsgcnext-dynamic-static-multi-graph","title":"TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential","date":"2023-04-23","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/hyperbolic-self-paced-learning-for-self","title":"HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations","date":"2023-03-10","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":2,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/spatiotemporal-decouple-and-squeeze","title":"Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semi-Supervised Skeleton-based Action Recognition","date":"2023-02-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/graph-contrastive-learning-for-skeleton-based","title":"Graph Contrastive Learning for Skeleton-based Action Recognition","date":"2023-01-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-view-action-recognition-using","title":"Multi-View Action Recognition Using Contrastive Learning","date":"2023-01-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/skeletr-towards-skeleton-based-action","title":"SkeleTR: Towards Skeleton-based Action Recognition in the Wild","date":"2023-01-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/modeling-the-relative-visual-tempo-for-self","title":"Modeling the Relative Visual Tempo for Self-supervised Skeleton-based Action Recognition","date":"2023-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cross-modal-learning-with-3d-deformable","title":"Cross-Modal Learning with 3D Deformable Attention for Action Recognition","date":"2022-12-12","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hypergraph-transformer-for-skeleton-based","title":"Hypergraph Transformer for Skeleton-based Action Recognition","date":"2022-11-17","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":12,"samples_ran":10,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/star-transformer-a-spatio-temporal-cross-1","title":"STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition","date":"2022-10-14","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/motionbert-unified-pretraining-for-human","title":"MotionBERT: A Unified Perspective on Learning Human Motion Representations","date":"2022-10-12","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":5,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dg-stgcn-dynamic-spatial-temporal-modeling","title":"DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition","date":"2022-10-12","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/hierarchically-decomposed-graph-convolutional","title":"Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition","date":"2022-08-23","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":8,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/spatial-temporal-graph-attention-network-for","title":"Spatial Temporal Graph Attention Network for Skeleton-Based Action Recognition","date":"2022-08-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/psumnet-unified-modality-part-streams-are-all","title":"PSUMNet: Unified Modality Part Streams are All You Need for Efficient Pose-based Action Recognition","date":"2022-08-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/language-supervised-training-for-skeleton","title":"Generative Action Description Prompts for Skeleton-based Action Recognition","date":"2022-08-10","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":7,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/igformer-interaction-graph-transformer-for","title":"IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition","date":"2022-07-25","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/skeleton-based-action-recognition-via","title":"Skeleton-based Action Recognition via Temporal-Channel Aggregation","date":"2022-05-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mmnet-a-model-based-multimodal-network-for","title":"MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos","date":"2022-05-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pyskl-towards-good-practices-for-skeleton","title":"PYSKL: Towards Good Practices for Skeleton Action Recognition","date":"2022-05-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/online-skeleton-based-action-recognition-with","title":"Continual Spatio-Temporal Graph Convolutional Networks","date":"2022-03-21","rows_on_this_dataset":12,"code_links":1,"syntology":null},{"paper":"/paper/infogcn-representation-learning-for-human","title":"InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition","date":"2022-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/contrastive-learning-from-extremely-augmented","title":"Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition","date":"2021-12-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/generative-adversarial-graph-convolutional","title":"Generative Adversarial Graph Convolutional Networks for Human Action Synthesis","date":"2021-10-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unsupervised-motion-representation-learning","title":"Unsupervised Motion Representation Learning with Capsule Autoencoders","date":"2021-10-01","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":20,"samples_ran":15,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-skeletal-graph-neural-networks-for","title":"Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation","date":"2021-08-16","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-multi-granular-spatio-temporal-graph","title":"Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition","date":"2021-08-10","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/channel-wise-topology-refinement-graph","title":"Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition","date":"2021-07-26","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":2,"samples_unverified":3,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/constructing-stronger-and-faster-baselines","title":"Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition","date":"2021-06-29","rows_on_this_dataset":3,"code_links":4,"syntology":null},{"paper":"/paper/vpn-rethinking-video-pose-embeddings-for","title":"VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living","date":"2021-05-17","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/leveraging-third-order-features-in-skeleton","title":"Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition","date":"2021-05-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/revisiting-skeleton-based-action-recognition","title":"Revisiting Skeleton-based Action Recognition","date":"2021-04-28","rows_on_this_dataset":2,"code_links":4,"syntology":null},{"paper":"/paper/one-shot-action-recognition-towards-novel","title":"One-shot action recognition in challenging therapy scenarios","date":"2021-02-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/syntactically-guided-generative-embeddings-1","title":"Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition","date":"2021-01-27","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/skeleton-dml-deep-metric-learning-for","title":"Skeleton-DML: Deep Metric Learning for Skeleton-Based One-Shot Action Recognition","date":"2020-12-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/prototypical-contrast-and-reverse-prediction","title":"Prototypical Contrast and Reverse Prediction: Unsupervised Skeleton Based Action Recognition","date":"2020-11-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/stronger-faster-and-more-explainable-a-graph","title":"Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition","date":"2020-10-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/spatial-temporal-transformer-network-for","title":"Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks","date":"2020-08-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/richly-activated-graph-convolutional-network","title":"Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition","date":"2020-08-09","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/augmented-skeleton-based-contrastive-action","title":"Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition","date":"2020-08-01","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":2,"samples_unverified":9,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mix-dimension-in-poincare-geometry-for-3d","title":"Mix Dimension in Poincaré Geometry for 3D Skeleton-based Action Recognition","date":"2020-07-30","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/decoupled-spatial-temporal-attention-network","title":"Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognition","date":"2020-07-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/vpn-learning-video-pose-embedding-for","title":"VPN: Learning Video-Pose Embedding for Activities of Daily Living","date":"2020-07-06","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/quo-vadis-skeleton-action-recognition","title":"Quo Vadis, Skeleton Action Recognition ?","date":"2020-07-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/skeleton-based-action-recognition-with-shift","title":"Skeleton-Based Action Recognition With Shift Graph Convolutional Network","date":"2020-06-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/signal-level-deep-metric-learning-for","title":"SL-DML: Signal Level Deep Metric Learning for Multimodal One-Shot Action Recognition","date":"2020-04-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/disentangling-and-unifying-graph-convolutions","title":"Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition","date":"2020-03-31","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/feedback-graph-convolutional-network-for","title":"Feedback Graph Convolutional Network for Skeleton-based Action Recognition","date":"2020-03-17","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/gimme-signals-discriminative-signal-encoding","title":"Gimme Signals: Discriminative signal encoding for multimodal activity recognition","date":"2020-03-13","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/vertex-feature-encoding-and-hierarchical","title":"Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatial-Temporal Graph Convolutional Network for Action Recognition","date":"2019-12-20","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/predict-cluster-unsupervised-skeleton-based","title":"PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition","date":"2019-11-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/interaction-relational-network-for-mutual","title":"Interaction Relational Network for Mutual Action Recognition","date":"2019-10-11","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/skeleton-image-representation-for-3d-action","title":"Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Joints","date":"2019-09-11","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/learning-stochastic-differential-equations-1","title":"Learning stochastic differential equations using RNN with log signature features","date":"2019-08-22","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/skelemotion-a-new-representation-of-skeleton","title":"SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition","date":"2019-07-30","rows_on_this_dataset":3,"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/ntu-rgbd-120-a-large-scale-benchmark-for-3d","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","date":"2019-05-12","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/skeleton-based-online-action-prediction-using","title":"Skeleton-Based Online Action Prediction Using Scale Selection Network","date":"2019-02-08","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/generalized-zero-and-few-shot-learning-via","title":"Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders","date":"2018-12-05","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/early-action-prediction-by-soft-regression","title":"Early action prediction by soft regression","date":"2018-08-06","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/recognizing-human-actions-as-the-evolution-of","title":"Recognizing Human Actions as the Evolution of Pose Estimation Maps","date":"2018-06-01","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/learning-clip-representations-for-skeleton","title":"Learning clip representations for skeleton-based 3d action recognition","date":"2018-03-05","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/spatial-temporal-graph-convolutional-networks-1","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","date":"2018-01-23","rows_on_this_dataset":2,"code_links":24,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/enhanced-skeleton-visualization-for-view","title":"Enhanced skeleton visualization for view invariant human action recognition","date":"2017-08-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/skeleton-based-human-action-recognition-with","title":"Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networks","date":"2017-07-18","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/global-context-aware-attention-lstm-networks","title":"Global Context-Aware Attention LSTM Networks for 3D Action Recognition","date":"2017-07-01","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/skeleton-based-action-recognition-using","title":"Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates","date":"2017-06-26","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/a-new-representation-of-skeleton-sequences","title":"A New Representation of Skeleton Sequences for 3D Action Recognition","date":"2017-03-09","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/jointly-learning-heterogeneous-features-for-1","title":"Jointly learning heterogeneous features for rgb-d activity recognition","date":"2016-12-15","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/spatio-temporal-lstm-with-trust-gates-for-3d","title":"Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition","date":"2016-07-24","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/ntu-rgbd-a-large-scale-dataset-for-3d-human","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","date":"2016-04-11","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/conditional-generative-adversarial-nets","title":"Conditional Generative Adversarial Nets","date":"2014-11-06","rows_on_this_dataset":1,"code_links":62,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":40,"samples_ran":6,"samples_unverified":34,"pointer_only_for_licence":6,"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":25,"samples_harvested":197,"samples_ran":112,"samples_unverified":85,"pointer_only_for_licence":41,"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."}