{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/sota/skeleton-based-action-recognition-on-ntu-rgbd-1","task":{"name":"Skeleton Based Action Recognition","url":"/task/skeleton-based-action-recognition","note":null},"dataset":{"name":"NTU RGB+D 120","url":"/dataset/ntu-rgb-d-120"},"category":"Computer Vision","categories":["Computer Vision","Natural Language Processing","Time Series"],"category_note":null,"description":"**Skeleton-based Action Recognition** is a computer vision task that involves recognizing human actions from a sequence of 3D skeletal joint data captured from sensors such as Microsoft Kinect, Intel RealSense, and wearable devices. The goal of skeleton-based action recognition is to develop algorithms that can understand and classify human actions from skeleton data, which can be used in various applications such as human-computer interaction, sports analysis, and surveillance.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [View Adaptive Neural Networks for High\r\nPerformance Skeleton-based Human Action\r\nRecognition](https://arxiv.org/pdf/1804.07453v3.pdf) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Accuracy (Cross-Subject)","Accuracy (Cross-Setup)","Ensembled Modalities","GFLOPS per prediction"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction; the tokens 'score' and 'time' are not used on this page); null = not inferred, chart draws points only","by_metric":{"Accuracy (Cross-Subject)":"higher","Accuracy (Cross-Setup)":"higher","Ensembled Modalities":null,"GFLOPS per prediction":null}},"counts":{"rows":83,"rows_with_code":62,"rows_with_paper_page":82,"rows_dated":82,"rows_using_additional_data":5},"rows":[{"rank_in_archive_order":1,"model":"ProtoGCN","metrics":{"Accuracy (Cross-Setup)":"92.2","Accuracy (Cross-Subject)":"90.9","Ensembled Modalities":"6"},"uses_additional_data":false,"paper_date":"2024-11-28","paper":"/paper/revealing-key-details-to-see-differences-a","paper_url":"https://arxiv.org/abs/2411.18941v1","paper_title":"Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition","code":"https://github.com/firework8/ProtoGCN","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":2,"model":"JMDA (based on Skeleton MixFormer)","metrics":{"Accuracy (Cross-Setup)":"91.9","Accuracy (Cross-Subject)":"90.9"},"uses_additional_data":false,"paper_date":"2024-10-13","paper":"/paper/joint-mixing-data-augmentation-for-skeleton","paper_url":"https://doi.org/10.1145/3700878","paper_title":"Joint Mixing Data Augmentation for Skeleton-based Action Recognition","code":"https://github.com/aidarikako/JMDA","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":3,"model":"LA-GCN","metrics":{"Accuracy (Cross-Setup)":"91.8","Accuracy (Cross-Subject)":"90.7","Ensembled Modalities":"6"},"uses_additional_data":true,"paper_date":"2023-05-21","paper":"/paper/language-knowledge-assisted-representation","paper_url":"https://arxiv.org/abs/2305.12398v1","paper_title":"Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition","code":"https://github.com/damnull/lagcn","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":4,"model":"MSA-GCN","metrics":{"Accuracy (Cross-Setup)":"92.2","Accuracy (Cross-Subject)":"90.6","Ensembled Modalities":"6"},"uses_additional_data":false,"paper_date":"2024-12-19","paper":"/paper/msa-gcn-exploiting-multi-scale-temporal","paper_url":"https://ieeexplore.ieee.org/document/10807218","paper_title":"MSA-GCN: Exploiting Multi-Scale Temporal Dynamics With Adaptive Graph Convolution for Skeleton-Based Action Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":5,"model":"Shap-Mix","metrics":{"Accuracy (Cross-Setup)":"91.7","Accuracy (Cross-Subject)":"90.4","Ensembled Modalities":"4"},"uses_additional_data":false,"paper_date":"2024-07-17","paper":"/paper/shap-mix-shapley-value-guided-mixing-for-long","paper_url":"https://arxiv.org/abs/2407.12312v1","paper_title":"Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognition","code":"https://github.com/JHang2020/Shap-Mix","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":6,"model":"MMCL","metrics":{"Accuracy (Cross-Setup)":"91.7","Accuracy (Cross-Subject)":"90.3","Ensembled Modalities":"6"},"uses_additional_data":true,"paper_date":"2024-07-22","paper":"/paper/multi-modality-co-learning-for-efficient-1","paper_url":"https://arxiv.org/abs/2407.15706v6","paper_title":"Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition","code":"https://github.com/liujf69/MMCL-Action","n_code_links":1,"official":{"repos":["liujf69/MMCL-Action"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":1,"n_samples":10,"n_pointer_only_licence":10,"sample_list":"/paper/multi-modality-co-learning-for-efficient-1#ran","syntology_url":"https://syntology.ai/paper/2407.15706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15706"}}}},{"rank_in_archive_order":7,"model":"BlockGCN","metrics":{"Accuracy (Cross-Setup)":"91.5","Accuracy (Cross-Subject)":"90.3","Ensembled Modalities":"4"},"uses_additional_data":false,"paper_date":"2024-01-01","paper":"/paper/blockgcn-redefine-topology-awareness-for","paper_url":"http://openaccess.thecvf.com//content/CVPR2024/html/Zhou_BlockGCN_Redefine_Topology_Awareness_for_Skeleton-Based_Action_Recognition_CVPR_2024_paper.html","paper_title":"BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition","code":"https://github.com/zhouyuxuanyx/blockgcn","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":8,"model":"TSGCNeXt","metrics":{"Accuracy (Cross-Setup)":"91.7","Accuracy (Cross-Subject)":"90.2","Ensembled Modalities":"4"},"uses_additional_data":false,"paper_date":"2023-04-23","paper":"/paper/tsgcnext-dynamic-static-multi-graph","paper_url":"https://arxiv.org/abs/2304.11631v1","paper_title":"TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential","code":"https://github.com/vvhj/tsgcnext","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":9,"model":"HD-GCN","metrics":{"Accuracy (Cross-Setup)":"91.6","Accuracy (Cross-Subject)":"90.1","Ensembled Modalities":"6"},"uses_additional_data":false,"paper_date":"2022-08-23","paper":"/paper/hierarchically-decomposed-graph-convolutional","paper_url":"https://arxiv.org/abs/2208.10741v3","paper_title":"Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition","code":"https://github.com/Jho-Yonsei/HD-GCN","n_code_links":1,"official":{"repos":["Jho-Yonsei/HD-GCN"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":1,"n_samples":11,"n_pointer_only_licence":7,"sample_list":"/paper/hierarchically-decomposed-graph-convolutional#ran","syntology_url":"https://syntology.ai/paper/2208.10741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.10741"}}}},{"rank_in_archive_order":10,"model":"MAMP","metrics":{"Accuracy (Cross-Setup)":"91.3","Accuracy (Cross-Subject)":"90.0"},"uses_additional_data":false,"paper_date":"2023-08-14","paper":"/paper/masked-motion-predictors-are-strong-3d-action","paper_url":"https://arxiv.org/abs/2308.07092v1","paper_title":"Masked Motion Predictors are Strong 3D Action Representation Learners","code":"https://github.com/maoyunyao/mamp","n_code_links":1,"official":{"repos":["maoyunyao/mamp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/masked-motion-predictors-are-strong-3d-action#ran","syntology_url":"https://syntology.ai/paper/2308.07092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07092"}}}},{"rank_in_archive_order":11,"model":"STEP-CATFormer","metrics":{"Accuracy (Cross-Setup)":"91.2","Accuracy (Cross-Subject)":"90.0","Ensembled Modalities":"4"},"uses_additional_data":true,"paper_date":"2023-12-06","paper":"/paper/step-catformer-spatial-temporal-effective","paper_url":"https://arxiv.org/abs/2312.03288v1","paper_title":"STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action Recognition","code":"https://github.com/maclong01/STEP-CATFormer","n_code_links":1,"official":{"repos":["maclong01/STEP-CATFormer"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":4,"n_instrument":7,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":6,"sample_list":"/paper/step-catformer-spatial-temporal-effective#ran","syntology_url":"https://syntology.ai/paper/2312.03288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03288"}}}},{"rank_in_archive_order":12,"model":"Hyperformer","metrics":{"Accuracy (Cross-Setup)":"91.3","Accuracy (Cross-Subject)":"89.9","Ensembled Modalities":"4"},"uses_additional_data":false,"paper_date":"2022-11-17","paper":"/paper/hypergraph-transformer-for-skeleton-based","paper_url":"https://arxiv.org/abs/2211.09590v5","paper_title":"Hypergraph Transformer for Skeleton-based Action Recognition","code":"https://github.com/ZhouYuxuanYX/Hypergraph-Transformer-for-Skeleton-based-Action-Recognition","n_code_links":1,"official":{"repos":["ZhouYuxuanYX/Hypergraph-Transformer-for-Skeleton-based-Action-Recognition"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":1,"n_samples":12,"n_pointer_only_licence":9,"sample_list":"/paper/hypergraph-transformer-for-skeleton-based#ran","syntology_url":"https://syntology.ai/paper/2211.09590","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.09590"}}}},{"rank_in_archive_order":13,"model":"LST","metrics":{"Accuracy (Cross-Setup)":"91.1","Accuracy (Cross-Subject)":"89.9","Ensembled Modalities":"4"},"uses_additional_data":true,"paper_date":"2022-08-10","paper":"/paper/language-supervised-training-for-skeleton","paper_url":"https://arxiv.org/abs/2208.05318v2","paper_title":"Generative Action Description Prompts for Skeleton-based Action Recognition","code":"https://github.com/martinxm/gap","n_code_links":3,"official":{"repos":["martinxm/gap","martinxm/lst"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":2,"n_samples":10,"n_pointer_only_licence":4,"sample_list":"/paper/language-supervised-training-for-skeleton#ran","syntology_url":"https://syntology.ai/paper/2208.05318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.05318"}}}},{"rank_in_archive_order":14,"model":"SkateFormer","metrics":{"Accuracy (Cross-Setup)":"91.4","Accuracy (Cross-Subject)":"89.8","Ensembled Modalities":"4"},"uses_additional_data":false,"paper_date":"2024-03-14","paper":"/paper/skateformer-skeletal-temporal-transformer-for","paper_url":"https://arxiv.org/abs/2403.09508v3","paper_title":"SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition","code":"https://github.com/KAIST-VICLab/SkateFormer","n_code_links":1,"official":{"repos":["KAIST-VICLab/SkateFormer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/skateformer-skeletal-temporal-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2403.09508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09508"}}}},{"rank_in_archive_order":15,"model":"InfoGCN","metrics":{"Accuracy (Cross-Setup)":"91.2","Accuracy (Cross-Subject)":"89.8","Ensembled Modalities":"6"},"uses_additional_data":false,"paper_date":"2022-01-01","paper":"/paper/infogcn-representation-learning-for-human","paper_url":"http://openaccess.thecvf.com//content/CVPR2022/html/Chi_InfoGCN_Representation_Learning_for_Human_Skeleton-Based_Action_Recognition_CVPR_2022_paper.html","paper_title":"InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition","code":"https://github.com/stnoah1/infogcn","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":16,"model":"Stream-GCN","metrics":{"Accuracy (Cross-Setup)":"91.0","Accuracy (Cross-Subject)":"89.7"},"uses_additional_data":false,"paper_date":"2023-06-13","paper":"/paper/action-recognition-with-multi-stream-motion","paper_url":"https://arxiv.org/abs/2306.07576v1","paper_title":"Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":17,"model":"DG-STGCN","metrics":{"Accuracy (Cross-Setup)":"91.3","Accuracy (Cross-Subject)":"89.6","Ensembled Modalities":"4"},"uses_additional_data":false,"paper_date":"2022-10-12","paper":"/paper/dg-stgcn-dynamic-spatial-temporal-modeling","paper_url":"https://arxiv.org/abs/2210.05895v1","paper_title":"DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition","code":"https://github.com/kennymckormick/pyskl","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":18,"model":"SkeletonGCL (based on CTR-GCN)","metrics":{"Accuracy (Cross-Setup)":"91.0","Accuracy (Cross-Subject)":"89.5","Ensembled Modalities":"4"},"uses_additional_data":false,"paper_date":"2023-01-26","paper":"/paper/graph-contrastive-learning-for-skeleton-based","paper_url":"https://arxiv.org/abs/2301.10900v2","paper_title":"Graph Contrastive Learning for Skeleton-based Action Recognition","code":"https://github.com/oliverhxh/skeletongcl","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":19,"model":"JPFormer","metrics":{"Accuracy (Cross-Setup)":"91.4","Accuracy (Cross-Subject)":"89.4","Ensembled Modalities":"4"},"uses_additional_data":false,"paper_date":"2024-07-30","paper":"/paper/joint-partition-group-attention-for-skeleton","paper_url":"https://www.sciencedirect.com/science/article/pii/S0165168424002111","paper_title":"Joint-Partition Group Attention for skeleton-based action recognition","code":"https://github.com/HuCui2022/JPFormer","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":20,"model":"TCA-GCN","metrics":{"Accuracy (Cross-Setup)":"90.8","Accuracy (Cross-Subject)":"89.4","Ensembled Modalities":"4"},"uses_additional_data":false,"paper_date":"2022-05-31","paper":"/paper/skeleton-based-action-recognition-via","paper_url":"https://arxiv.org/abs/2205.15936v2","paper_title":"Skeleton-based Action Recognition via Temporal-Channel Aggregation","code":"https://github.com/OrdinaryQin/TCA-GCN","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":21,"model":"PSUMNet","metrics":{"Accuracy (Cross-Setup)":"90.6","Accuracy (Cross-Subject)":"89.4"},"uses_additional_data":false,"paper_date":"2022-08-11","paper":"/paper/psumnet-unified-modality-part-streams-are-all","paper_url":"https://arxiv.org/abs/2208.05775v1","paper_title":"PSUMNet: Unified Modality Part Streams are All You Need for Efficient Pose-based Action Recognition","code":"https://github.com/skelemoa/psumnet","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":22,"model":"DSTSA-GCN","metrics":{"Accuracy (Cross-Setup)":"90.97","Accuracy (Cross-Subject)":"89.12","Ensembled Modalities":"4"},"uses_additional_data":false,"paper_date":"2025-01-21","paper":"/paper/dstsa-gcn-advancing-skeleton-based-gesture","paper_url":"https://arxiv.org/abs/2501.12086v1","paper_title":"DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling","code":"https://github.com/HuCui2022/DSTSA-GCN_Gesture","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":23,"model":"TSGCNeXT","metrics":{"Accuracy (Cross-Setup)":"90.3","Accuracy (Cross-Subject)":"89.1","Ensembled Modalities":"4"},"uses_additional_data":false,"paper_date":"2023-04-23","paper":"/paper/tsgcnext-dynamic-static-multi-graph","paper_url":"https://arxiv.org/abs/2304.11631v1","paper_title":"TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential","code":"https://github.com/vvhj/tsgcnext","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":24,"model":"CTR-GCN","metrics":{"Accuracy (Cross-Setup)":"90.6","Accuracy (Cross-Subject)":"88.9","Ensembled Modalities":"4"},"uses_additional_data":false,"paper_date":"2021-07-26","paper":"/paper/channel-wise-topology-refinement-graph","paper_url":"https://arxiv.org/abs/2107.12213v2","paper_title":"Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition","code":"https://github.com/kennymckormick/pyskl","n_code_links":2,"official":{"repos":["Uason-Chen/CTR-GCN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]},"syntology":{"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":3,"sample_list":"/paper/channel-wise-topology-refinement-graph#ran","syntology_url":"https://syntology.ai/paper/2107.12213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.12213"}}}},{"rank_in_archive_order":25,"model":"Lit-llama","metrics":{"Accuracy (Cross-Setup)":"91.5","Accuracy (Cross-Subject)":"88.7"},"uses_additional_data":false,"paper_date":"2024-03-31","paper":"/paper/llms-are-good-action-recognizers","paper_url":"https://arxiv.org/abs/2404.00532v1","paper_title":"LLMs are Good Action Recognizers","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":26,"model":"STGAT","metrics":{"Accuracy (Cross-Setup)":"90.4","Accuracy (Cross-Subject)":"88.7","Ensembled Modalities":"4"},"uses_additional_data":false,"paper_date":"2022-08-18","paper":"/paper/spatial-temporal-graph-attention-network-for","paper_url":"https://arxiv.org/abs/2208.08599v2","paper_title":"Spatial Temporal Graph Attention Network for Skeleton-Based Action Recognition","code":"https://github.com/hulianyuyy/STGAT","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":27,"model":"EfficientGCN-B4","metrics":{"Accuracy (Cross-Setup)":"89.1","Accuracy (Cross-Subject)":"88.7"},"uses_additional_data":false,"paper_date":"2021-06-29","paper":"/paper/constructing-stronger-and-faster-baselines","paper_url":"https://arxiv.org/abs/2106.15125v2","paper_title":"Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition","code":"https://github.com/yfsong0709/EfficientGCNv1","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":28,"model":"ST-GCN++ [PYSKL, 3D Skeleton]","metrics":{"Accuracy (Cross-Setup)":"90.8","Accuracy (Cross-Subject)":"88.6","Ensembled Modalities":"4"},"uses_additional_data":false,"paper_date":"2022-05-19","paper":"/paper/pyskl-towards-good-practices-for-skeleton","paper_url":"https://arxiv.org/abs/2205.09443v1","paper_title":"PYSKL: Towards Good Practices for Skeleton Action Recognition","code":"https://github.com/kennymckormick/pyskl","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":29,"model":"DualHead-Net","metrics":{"Accuracy (Cross-Setup)":"89.3","Accuracy (Cross-Subject)":"88.2","Ensembled Modalities":"4"},"uses_additional_data":false,"paper_date":"2021-08-10","paper":"/paper/learning-multi-granular-spatio-temporal-graph","paper_url":"https://arxiv.org/abs/2108.04536v1","paper_title":"Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition","code":"https://github.com/tailin1009/dualhead-network","n_code_links":1,"official":{"repos":["tailin1009/dualhead-network"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":4,"sample_list":"/paper/learning-multi-granular-spatio-temporal-graph#ran","syntology_url":"https://syntology.ai/paper/2108.04536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.04536"}}}},{"rank_in_archive_order":30,"model":"AngNet-JA + BA + JBA + VJBA","metrics":{"Accuracy (Cross-Setup)":"89.2%","Accuracy (Cross-Subject)":"88.2%","Ensembled Modalities":"4"},"uses_additional_data":false,"paper_date":"2021-05-04","paper":"/paper/leveraging-third-order-features-in-skeleton","paper_url":"https://arxiv.org/abs/2105.01563v5","paper_title":"Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition","code":"https://github.com/ZhenyueQin/Angular-Skeleton-Encoding","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":31,"model":"EfficientGCN-B2","metrics":{"Accuracy (Cross-Setup)":"88.0","Accuracy (Cross-Subject)":"87.9"},"uses_additional_data":false,"paper_date":"2021-06-29","paper":"/paper/constructing-stronger-and-faster-baselines","paper_url":"https://arxiv.org/abs/2106.15125v2","paper_title":"Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition","code":"https://github.com/yfsong0709/EfficientGCNv1","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":32,"model":"Skeletal GNN","metrics":{"Accuracy (Cross-Setup)":"89.2","Accuracy (Cross-Subject)":"87.5","Ensembled Modalities":"4"},"uses_additional_data":false,"paper_date":"2021-08-16","paper":"/paper/learning-skeletal-graph-neural-networks-for","paper_url":"https://arxiv.org/abs/2108.07181v2","paper_title":"Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":33,"model":"MaskCLR","metrics":{"Accuracy (Cross-Setup)":"89.5","Accuracy (Cross-Subject)":"87.4"},"uses_additional_data":false,"paper_date":"2024-01-01","paper":"/paper/maskclr-attention-guided-contrastive-learning","paper_url":"http://openaccess.thecvf.com//content/CVPR2024/html/Abdelfattah_MaskCLR_Attention-Guided_Contrastive_Learning_for_Robust_Action_Representation_Learning_CVPR_2024_paper.html","paper_title":"MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":34,"model":"MSSTNet","metrics":{"Accuracy (Cross-Setup)":"88.3","Accuracy (Cross-Subject)":"87.4"},"uses_additional_data":false,"paper_date":"2023-05-12","paper":"/paper/multi-scale-spatial-temporal-convolutional","paper_url":"https://link.springer.com/article/10.1007/s10044-023-01156-w#Sec8","paper_title":"Multi-scale spatial–temporal convolutional neural network for skeleton-based action recognition","code":"https://github.com/Maxchengqin/MSSTNet_2D_3D","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":35,"model":"PA-ResGCN-B19","metrics":{"Accuracy (Cross-Setup)":"88.3","Accuracy (Cross-Subject)":"87.3"},"uses_additional_data":false,"paper_date":"2020-10-20","paper":"/paper/stronger-faster-and-more-explainable-a-graph","paper_url":"https://arxiv.org/abs/2010.09978v1","paper_title":"Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition","code":"https://github.com/yfsong0709/EfficientGCNv1","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":36,"model":"Ensemble-top5 (MS-G3D Net + 4s Shift-GCN + VA-CNN (ResNeXt101) + 2s SDGCN + GCN-NAS (retrained))","metrics":{"Accuracy (Cross-Setup)":"88.8%","Accuracy (Cross-Subject)":"87.22%"},"uses_additional_data":false,"paper_date":"2020-07-04","paper":"/paper/quo-vadis-skeleton-action-recognition","paper_url":"https://arxiv.org/abs/2007.02072v2","paper_title":"Quo Vadis, Skeleton Action Recognition ?","code":"https://github.com/skelemoa/quovadis","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":37,"model":"PoseC3D (w. HRNet 2D Skeleton)","metrics":{"Accuracy (Cross-Setup)":"90.3","Accuracy (Cross-Subject)":"86.9"},"uses_additional_data":false,"paper_date":"2021-04-28","paper":"/paper/revisiting-skeleton-based-action-recognition","paper_url":"https://arxiv.org/abs/2104.13586v2","paper_title":"Revisiting Skeleton-based Action Recognition","code":"https://github.com/open-mmlab/mmaction2","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":38,"model":"MS-G3D Net","metrics":{"Accuracy (Cross-Setup)":"88.4%","Accuracy (Cross-Subject)":"86.9%"},"uses_additional_data":false,"paper_date":"2020-03-31","paper":"/paper/disentangling-and-unifying-graph-convolutions","paper_url":"https://arxiv.org/abs/2003.14111v2","paper_title":"Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition","code":"https://github.com/kennymckormick/pyskl","n_code_links":3,"official":{"repos":["kenziyuliu/ms-g3d"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"sample_list":"/paper/disentangling-and-unifying-graph-convolutions#ran","syntology_url":"https://syntology.ai/paper/2003.14111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.14111"}}}},{"rank_in_archive_order":39,"model":"DSTA-Net","metrics":{"Accuracy (Cross-Setup)":"89.0 %","Accuracy (Cross-Subject)":"86.6%"},"uses_additional_data":false,"paper_date":"2020-07-07","paper":"/paper/decoupled-spatial-temporal-attention-network","paper_url":"https://arxiv.org/abs/2007.03263v1","paper_title":"Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognition","code":"https://github.com/lshiwjx/DSTA-Net","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":40,"model":"VPN","metrics":{"Accuracy (Cross-Setup)":"87.8","Accuracy (Cross-Subject)":"86.3"},"uses_additional_data":true,"paper_date":"2020-07-06","paper":"/paper/vpn-learning-video-pose-embedding-for","paper_url":"https://arxiv.org/abs/2007.03056v1","paper_title":"VPN: Learning Video-Pose Embedding for Activities of Daily Living","code":"https://github.com/srijandas07/VPN","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":41,"model":"ST-GCN [PYSKL, 3D Skeleton]","metrics":{"Accuracy (Cross-Setup)":"88.4","Accuracy (Cross-Subject)":"86.2"},"uses_additional_data":false,"paper_date":"2018-01-23","paper":"/paper/spatial-temporal-graph-convolutional-networks-1","paper_url":"http://arxiv.org/abs/1801.07455v2","paper_title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","code":"https://github.com/open-mmlab/mmskeleton","n_code_links":24,"official":{"repos":["yysijie/st-gcn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/spatial-temporal-graph-convolutional-networks-1#ran","syntology_url":"https://syntology.ai/paper/1801.07455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.07455"}}}},{"rank_in_archive_order":42,"model":"4s Shift-GCN","metrics":{"Accuracy (Cross-Setup)":"87.6%","Accuracy (Cross-Subject)":"85.9%","Ensembled Modalities":"4"},"uses_additional_data":false,"paper_date":"2020-06-01","paper":"/paper/skeleton-based-action-recognition-with-shift","paper_url":"http://openaccess.thecvf.com/content_CVPR_2020/html/Cheng_Skeleton-Based_Action_Recognition_With_Shift_Graph_Convolutional_Network_CVPR_2020_paper.html","paper_title":"Skeleton-Based Action Recognition With Shift Graph Convolutional Network","code":"https://github.com/kchengiva/Shift-GCN","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":43,"model":"EfficientGCN-B0","metrics":{"Accuracy (Cross-Setup)":"84.3","Accuracy (Cross-Subject)":"85.9"},"uses_additional_data":false,"paper_date":"2021-06-29","paper":"/paper/constructing-stronger-and-faster-baselines","paper_url":"https://arxiv.org/abs/2106.15125v2","paper_title":"Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition","code":"https://github.com/yfsong0709/EfficientGCNv1","n_code_links":4,"official":null,"syntology":null},{"rank_in_archive_order":44,"model":"FGCN","metrics":{"Accuracy (Cross-Setup)":"87.4%","Accuracy (Cross-Subject)":"85.4%"},"uses_additional_data":false,"paper_date":"2020-03-17","paper":"/paper/feedback-graph-convolutional-network-for","paper_url":"https://arxiv.org/abs/2003.07564v1","paper_title":"Feedback Graph Convolutional Network for Skeleton-based Action Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":45,"model":"VA-CNN (ResNeXt-101)","metrics":{"Accuracy (Cross-Setup)":"86.90","Accuracy (Cross-Subject)":"84.88"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":46,"model":"S-TR (2-stream)","metrics":{"Accuracy (Cross-Setup)":"86.2","Accuracy (Cross-Subject)":"84.8","GFLOPS per prediction":"32.4"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/online-skeleton-based-action-recognition-with","paper_url":"https://arxiv.org/abs/2203.11009v2","paper_title":"Continual Spatio-Temporal Graph Convolutional Networks","code":"https://github.com/lukashedegaard/continual-skeletons","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":47,"model":"CoS-TR* (2-stream)","metrics":{"Accuracy (Cross-Setup)":"86.1","Accuracy (Cross-Subject)":"84.8","GFLOPS per prediction":"0.3"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/online-skeleton-based-action-recognition-with","paper_url":"https://arxiv.org/abs/2203.11009v2","paper_title":"Continual Spatio-Temporal Graph Convolutional Networks","code":"https://github.com/lukashedegaard/continual-skeletons","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":48,"model":"ST-GCN [PYSKL, 2D Skeleton]","metrics":{"Accuracy (Cross-Setup)":"89.0","Accuracy (Cross-Subject)":"84.7"},"uses_additional_data":false,"paper_date":"2018-01-23","paper":"/paper/spatial-temporal-graph-convolutional-networks-1","paper_url":"http://arxiv.org/abs/1801.07455v2","paper_title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","code":"https://github.com/open-mmlab/mmskeleton","n_code_links":24,"official":{"repos":["yysijie/st-gcn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0,"sample_list":"/paper/spatial-temporal-graph-convolutional-networks-1#ran","syntology_url":"https://syntology.ai/paper/1801.07455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.07455"}}}},{"rank_in_archive_order":49,"model":"3s-HYSP","metrics":{"Accuracy (Cross-Setup)":"86.3","Accuracy (Cross-Subject)":"84.5"},"uses_additional_data":false,"paper_date":"2023-03-10","paper":"/paper/hyperbolic-self-paced-learning-for-self","paper_url":"https://arxiv.org/abs/2303.06242v1","paper_title":"HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations","code":"https://github.com/paolomandica/hysp","n_code_links":1,"official":{"repos":["paolomandica/hysp"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":9,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":9,"n_samples":13,"n_pointer_only_licence":0,"sample_list":"/paper/hyperbolic-self-paced-learning-for-self#ran","syntology_url":"https://syntology.ai/paper/2303.06242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06242"}}}},{"rank_in_archive_order":50,"model":"CoST-GCN* (2-stream)","metrics":{"Accuracy (Cross-Setup)":"85.5","Accuracy (Cross-Subject)":"84.0","GFLOPS per prediction":"0.32"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/online-skeleton-based-action-recognition-with","paper_url":"https://arxiv.org/abs/2203.11009v2","paper_title":"Continual Spatio-Temporal Graph Convolutional Networks","code":"https://github.com/lukashedegaard/continual-skeletons","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":51,"model":"AGCN (2-stream)","metrics":{"Accuracy (Cross-Setup)":"85.4","Accuracy (Cross-Subject)":"84","GFLOPS per prediction":"37.38"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/online-skeleton-based-action-recognition-with","paper_url":"https://arxiv.org/abs/2203.11009v2","paper_title":"Continual Spatio-Temporal Graph Convolutional Networks","code":"https://github.com/lukashedegaard/continual-skeletons","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":52,"model":"ST-GCN (2-stream)","metrics":{"Accuracy (Cross-Setup)":"85.1","Accuracy (Cross-Subject)":"83.7","GFLOPS per prediction":"33.46"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/online-skeleton-based-action-recognition-with","paper_url":"https://arxiv.org/abs/2203.11009v2","paper_title":"Continual Spatio-Temporal Graph Convolutional Networks","code":"https://github.com/lukashedegaard/continual-skeletons","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":53,"model":"ST-TR-agcn","metrics":{"Accuracy (Cross-Setup)":"84.7%","Accuracy (Cross-Subject)":"82.7%"},"uses_additional_data":false,"paper_date":"2020-08-17","paper":"/paper/spatial-temporal-transformer-network-for","paper_url":"https://arxiv.org/abs/2008.07404v4","paper_title":"Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks","code":"https://github.com/Chiaraplizz/ST-TR","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":54,"model":"HYSP","metrics":{"Accuracy (Cross-Setup)":"82","Accuracy (Cross-Subject)":"81.4"},"uses_additional_data":false,"paper_date":"2023-03-10","paper":"/paper/hyperbolic-self-paced-learning-for-self","paper_url":"https://arxiv.org/abs/2303.06242v1","paper_title":"HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations","code":"https://github.com/paolomandica/hysp","n_code_links":1,"official":{"repos":["paolomandica/hysp"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":9,"ran_from_kinds":["official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":9,"n_samples":13,"n_pointer_only_licence":0,"sample_list":"/paper/hyperbolic-self-paced-learning-for-self#ran","syntology_url":"https://syntology.ai/paper/2303.06242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06242"}}}},{"rank_in_archive_order":55,"model":"3s RA-GCN","metrics":{"Accuracy (Cross-Setup)":"82.7%","Accuracy (Cross-Subject)":"81.1%"},"uses_additional_data":false,"paper_date":"2020-08-09","paper":"/paper/richly-activated-graph-convolutional-network","paper_url":"https://arxiv.org/abs/2008.03791v2","paper_title":"Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition","code":"https://github.com/amira-mira/RA-GCNv22","n_code_links":3,"official":null,"syntology":null},{"rank_in_archive_order":56,"model":"3s-USDRL (DSTE) This work","metrics":{"Accuracy (Cross-Setup)":"79.3","Accuracy (Cross-Subject)":"80.6"},"uses_additional_data":false,"paper_date":"2024-12-12","paper":"/paper/usdrl-unified-skeleton-based-dense","paper_url":"https://arxiv.org/abs/2412.09220v2","paper_title":"USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation","code":"https://github.com/wengwanjiang/usdrl","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":57,"model":"Mix-Dimension","metrics":{"Accuracy (Cross-Setup)":"83.2%","Accuracy (Cross-Subject)":"80.5%"},"uses_additional_data":false,"paper_date":"2020-07-30","paper":"/paper/mix-dimension-in-poincare-geometry-for-3d","paper_url":"https://arxiv.org/abs/2007.15678v2","paper_title":"Mix Dimension in Poincaré Geometry for 3D Skeleton-based Action Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":58,"model":"CoAGCN* (2-stream)","metrics":{"Accuracy (Cross-Setup)":"82","Accuracy (Cross-Subject)":"80.4","GFLOPS per prediction":"0.44"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/online-skeleton-based-action-recognition-with","paper_url":"https://arxiv.org/abs/2203.11009v2","paper_title":"Continual Spatio-Temporal Graph Convolutional Networks","code":"https://github.com/lukashedegaard/continual-skeletons","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":59,"model":"S-TR (1-stream)","metrics":{"Accuracy (Cross-Setup)":"81.8","Accuracy (Cross-Subject)":"80.2","GFLOPS per prediction":"16.2"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/online-skeleton-based-action-recognition-with","paper_url":"https://arxiv.org/abs/2203.11009v2","paper_title":"Continual Spatio-Temporal Graph Convolutional Networks","code":"https://github.com/lukashedegaard/continual-skeletons","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":60,"model":"CoS-TR* (1-stream)","metrics":{"Accuracy (Cross-Setup)":"81.7","Accuracy (Cross-Subject)":"79.7","GFLOPS per prediction":"0.15"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/online-skeleton-based-action-recognition-with","paper_url":"https://arxiv.org/abs/2203.11009v2","paper_title":"Continual Spatio-Temporal Graph Convolutional Networks","code":"https://github.com/lukashedegaard/continual-skeletons","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":61,"model":"AGCN (1-stream)","metrics":{"Accuracy (Cross-Setup)":"80.7","Accuracy (Cross-Subject)":"79.7","GFLOPS per prediction":"18.69"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/online-skeleton-based-action-recognition-with","paper_url":"https://arxiv.org/abs/2203.11009v2","paper_title":"Continual Spatio-Temporal Graph Convolutional Networks","code":"https://github.com/lukashedegaard/continual-skeletons","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":62,"model":"CoST-GCN* (1-stream)","metrics":{"Accuracy (Cross-Setup)":"81.6","Accuracy (Cross-Subject)":"79.4","GFLOPS per prediction":"0.16"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/online-skeleton-based-action-recognition-with","paper_url":"https://arxiv.org/abs/2203.11009v2","paper_title":"Continual Spatio-Temporal Graph Convolutional Networks","code":"https://github.com/lukashedegaard/continual-skeletons","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":63,"model":"ST-GCN (1-stream)","metrics":{"Accuracy (Cross-Subject)":"79","GFLOPS per prediction":"16.73"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/online-skeleton-based-action-recognition-with","paper_url":"https://arxiv.org/abs/2203.11009v2","paper_title":"Continual Spatio-Temporal Graph Convolutional Networks","code":"https://github.com/lukashedegaard/continual-skeletons","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":64,"model":"GVFE + AS-GCN with DH-TCN","metrics":{"Accuracy (Cross-Setup)":"79.8%","Accuracy (Cross-Subject)":"78.3%"},"uses_additional_data":false,"paper_date":"2019-12-20","paper":"/paper/vertex-feature-encoding-and-hierarchical","paper_url":"https://arxiv.org/abs/1912.09745v1","paper_title":"Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatial-Temporal Graph Convolutional Network for Action Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":65,"model":"CoAGCN* (1-stream)","metrics":{"Accuracy (Cross-Setup)":"79.1","Accuracy (Cross-Subject)":"77.3","GFLOPS per prediction":"0.22"},"uses_additional_data":false,"paper_date":"2022-03-21","paper":"/paper/online-skeleton-based-action-recognition-with","paper_url":"https://arxiv.org/abs/2203.11009v2","paper_title":"Continual Spatio-Temporal Graph Convolutional Networks","code":"https://github.com/lukashedegaard/continual-skeletons","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":66,"model":"Gimme Signals (Skeleton, AIS)","metrics":{"Accuracy (Cross-Setup)":"71.6%","Accuracy (Cross-Subject)":"70.8%"},"uses_additional_data":false,"paper_date":"2020-03-13","paper":"/paper/gimme-signals-discriminative-signal-encoding","paper_url":"https://arxiv.org/abs/2003.06156v2","paper_title":"Gimme Signals: Discriminative signal encoding for multimodal activity recognition","code":"https://github.com/raphaelmemmesheimer/gimme_signals_action_recognition","n_code_links":2,"official":null,"syntology":null},{"rank_in_archive_order":67,"model":"Logsig-RNN","metrics":{"Accuracy (Cross-Setup)":"67.2%","Accuracy (Cross-Subject)":"68.3%"},"uses_additional_data":false,"paper_date":"2019-08-22","paper":"/paper/learning-stochastic-differential-equations-1","paper_url":"https://arxiv.org/abs/1908.08286v2","paper_title":"Learning stochastic differential equations using RNN with log signature features","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":68,"model":"TSRJI (Late Fusion) + HCN","metrics":{"Accuracy (Cross-Setup)":"62.8%","Accuracy (Cross-Subject)":"67.9%"},"uses_additional_data":false,"paper_date":"2019-09-11","paper":"/paper/skeleton-image-representation-for-3d-action","paper_url":"https://arxiv.org/abs/1909.05704v1","paper_title":"Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Joints","code":"https://github.com/carloscaetano/skeleton-images","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":69,"model":"SkeleMotion + Yang et al. (2018)","metrics":{"Accuracy (Cross-Setup)":"66.9%","Accuracy (Cross-Subject)":"67.7%"},"uses_additional_data":false,"paper_date":"2019-07-30","paper":"/paper/skelemotion-a-new-representation-of-skeleton","paper_url":"https://arxiv.org/abs/1907.13025v1","paper_title":"SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition","code":"https://github.com/carloscaetano/skeleton-images","n_code_links":1,"official":{"repos":["carloscaetano/skeleton-images"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/skelemotion-a-new-representation-of-skeleton#ran","syntology_url":"https://syntology.ai/paper/1907.13025","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.13025"}}}},{"rank_in_archive_order":70,"model":"TSRJI (Late Fusion)","metrics":{"Accuracy (Cross-Setup)":"59.7%","Accuracy (Cross-Subject)":"65.5%"},"uses_additional_data":false,"paper_date":"2019-09-11","paper":"/paper/skeleton-image-representation-for-3d-action","paper_url":"https://arxiv.org/abs/1909.05704v1","paper_title":"Skeleton Image Representation for 3D Action Recognition based on Tree Structure and Reference Joints","code":"https://github.com/carloscaetano/skeleton-images","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":71,"model":"Body Pose Evolution Map","metrics":{"Accuracy (Cross-Setup)":"66.9%","Accuracy (Cross-Subject)":"64.6%"},"uses_additional_data":false,"paper_date":"2018-06-01","paper":"/paper/recognizing-human-actions-as-the-evolution-of","paper_url":"http://openaccess.thecvf.com/content_cvpr_2018/html/Liu_Recognizing_Human_Actions_CVPR_2018_paper.html","paper_title":"Recognizing Human Actions as the Evolution of Pose Estimation Maps","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":72,"model":"SkeleMotion [Magnitude-Orientation (TSA)]","metrics":{"Accuracy (Cross-Setup)":"63.0%","Accuracy (Cross-Subject)":"62.9%"},"uses_additional_data":false,"paper_date":"2019-07-30","paper":"/paper/skelemotion-a-new-representation-of-skeleton","paper_url":"https://arxiv.org/abs/1907.13025v1","paper_title":"SkeleMotion: A New Representation of Skeleton Joint Sequences Based on Motion Information for 3D Action Recognition","code":"https://github.com/carloscaetano/skeleton-images","n_code_links":1,"official":{"repos":["carloscaetano/skeleton-images"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3,"sample_list":"/paper/skelemotion-a-new-representation-of-skeleton#ran","syntology_url":"https://syntology.ai/paper/1907.13025","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.13025"}}}},{"rank_in_archive_order":73,"model":"Multi-Task CNN with RotClips","metrics":{"Accuracy (Cross-Setup)":"61.8%","Accuracy (Cross-Subject)":"62.2%"},"uses_additional_data":false,"paper_date":"2018-03-05","paper":"/paper/learning-clip-representations-for-skeleton","paper_url":"https://doi.org/10.1109/TIP.2018.2812099","paper_title":"Learning clip representations for skeleton-based 3d action recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":74,"model":"Two-Stream Attention LSTM","metrics":{"Accuracy (Cross-Setup)":"63.3%","Accuracy (Cross-Subject)":"61.2%"},"uses_additional_data":false,"paper_date":"2017-07-18","paper":"/paper/skeleton-based-human-action-recognition-with","paper_url":"http://arxiv.org/abs/1707.05740v5","paper_title":"Skeleton-Based Human Action Recognition with Global Context-Aware Attention LSTM Networks","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":75,"model":"Skeleton Visualization (Single Stream)","metrics":{"Accuracy (Cross-Setup)":"63.2%","Accuracy (Cross-Subject)":"60.3%"},"uses_additional_data":false,"paper_date":"2017-08-01","paper":"/paper/enhanced-skeleton-visualization-for-view","paper_url":"https://doi.org/10.1016/j.patcog.2017.02.030","paper_title":"Enhanced skeleton visualization for view invariant human action recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":76,"model":"FSNet","metrics":{"Accuracy (Cross-Setup)":"62.4%","Accuracy (Cross-Subject)":"59.9%"},"uses_additional_data":false,"paper_date":"2019-02-08","paper":"/paper/skeleton-based-online-action-prediction-using","paper_url":"http://arxiv.org/abs/1902.03084v2","paper_title":"Skeleton-Based Online Action Prediction Using Scale Selection Network","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":77,"model":"Multi-Task Learning Network","metrics":{"Accuracy (Cross-Setup)":"57.9%","Accuracy (Cross-Subject)":"58.4%"},"uses_additional_data":false,"paper_date":"2017-03-09","paper":"/paper/a-new-representation-of-skeleton-sequences","paper_url":"http://arxiv.org/abs/1703.03492v3","paper_title":"A New Representation of Skeleton Sequences for 3D Action Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":78,"model":"GCA-LSTM","metrics":{"Accuracy (Cross-Setup)":"59.2%","Accuracy (Cross-Subject)":"58.3%"},"uses_additional_data":false,"paper_date":"2017-07-01","paper":"/paper/global-context-aware-attention-lstm-networks","paper_url":"http://openaccess.thecvf.com/content_cvpr_2017/html/Liu_Global_Context-Aware_Attention_CVPR_2017_paper.html","paper_title":"Global Context-Aware Attention LSTM Networks for 3D Action Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":79,"model":"Internal Feature Fusion","metrics":{"Accuracy (Cross-Setup)":"60.9%","Accuracy (Cross-Subject)":"58.2%"},"uses_additional_data":false,"paper_date":"2017-06-26","paper":"/paper/skeleton-based-action-recognition-using","paper_url":"http://arxiv.org/abs/1706.08276v1","paper_title":"Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":80,"model":"Spatio-Temporal LSTM","metrics":{"Accuracy (Cross-Setup)":"57.9%","Accuracy (Cross-Subject)":"55.7%"},"uses_additional_data":false,"paper_date":"2016-07-24","paper":"/paper/spatio-temporal-lstm-with-trust-gates-for-3d","paper_url":"http://arxiv.org/abs/1607.07043v1","paper_title":"Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":81,"model":"Dynamic Skeletons","metrics":{"Accuracy (Cross-Setup)":"54.7%","Accuracy (Cross-Subject)":"50.8%"},"uses_additional_data":false,"paper_date":"2016-12-15","paper":"/paper/jointly-learning-heterogeneous-features-for-1","paper_url":"https://doi.org/10.1109/TPAMI.2016.2640292","paper_title":"Jointly learning heterogeneous features for rgb-d activity recognition","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":82,"model":"Soft RNN","metrics":{"Accuracy (Cross-Setup)":"44.9%","Accuracy (Cross-Subject)":"36.3%"},"uses_additional_data":false,"paper_date":"2018-08-06","paper":"/paper/early-action-prediction-by-soft-regression","paper_url":"https://doi.org/10.1109/TPAMI.2018.2863279","paper_title":"Early action prediction by soft regression","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":83,"model":"Part-Aware LSTM","metrics":{"Accuracy (Cross-Setup)":"26.3%","Accuracy (Cross-Subject)":"25.5%"},"uses_additional_data":false,"paper_date":"2016-04-11","paper":"/paper/ntu-rgbd-a-large-scale-dataset-for-3d-human","paper_url":"http://arxiv.org/abs/1604.02808v1","paper_title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","code":"https://github.com/shahroudy/NTURGB-D","n_code_links":2,"official":null,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"adjudicator":"Claude Opus 5.5","adjudicator_from":"groundwork/59_code_with_papers/LB_EXTRACTOR_PREREG.md (not recorded in lb_measurement.json; the file's frozen_commit, measured_on and counts equal the run the pre-registration records)","adjudicator_sensitivity":[69,70],"adjudicator_specificity":[101,103],"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication by a model (adjudicator) of accepted entries on a held-out split of archive papers, rules frozen before the test; adjudicator_sensitivity and adjudicator_specificity are its own controls as [judged right, of]; it was not measured on the newer papers placed here","measurement_sentence":"Measured before publishing, on held-out archive papers: the extractor was given 883 of them and produced output for 881 (the other 2 had no title and were excluded before any model call, so they are not part of this measurement). A model adjudicator (Claude Opus 5.5), blind to which entries were real, judged 108 of 110 accepted entries correct on those held-out archive papers; its own controls: 69 of 70 archive-confirmed entries judged true, 101 of 103 corrupted copies judged false. It was not measured on the newer papers whose results are placed on this site.","coverage":{"sentence":"Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.","complete":false,"papers_newer_than_archive":18637,"papers_checked":8886,"papers_checked_no_leaderboard_matched":3717,"papers_read_nothing_to_place":733,"papers_could_not_be_read":41,"papers_could_not_be_read_by_status":{"unparseable":41},"papers_extracted_not_yet_verified":0,"boards_without_verdict":3,"papers_not_yet_extracted":8975},"board_status":{"sentence":"Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), none had this board among the leaderboards the extractor considered for their tables yet (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,596 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), so none await a verdict here.","note":"papers, from the extractor's own records, over the newer papers whose tables were read; proposed = no_cell_passed_checks + rejected_by_independent_check + accepted_not_placed + awaiting_verdict + placed; counts, never a rate","eligible":true,"eligible_note":"false when the extractor never considers this board: it loads only boards with archive rows and at least one metric column (lb_extract.py Boards), so no newer paper can be proposed here; archive_rows and metric_columns say which","archive_rows":83,"metric_columns":4,"papers_read":8888,"papers_read_checked":8886,"papers_read_awaiting_verdict":2,"papers_read_verified":8888,"papers_read_not_yet_verified":0,"papers_read_at_candidate_cap":1596,"papers_read_list_full_without_this_board":1596,"candidates":0,"candidates_capped_note":"candidates = papers that had this board among the leaderboards the extractor considered for their tables; the extractor keeps at most 10 per paper and 4 per dataset, so a board crowded out of a paper's list is not counted and candidates is a floor; papers_read_list_full_without_this_board counts the read papers whose list did not hold this board and had reached 10, or held 4 boards of this board's dataset (the only papers that could have crowded it out); papers_read_at_candidate_cap counts, over every board, the papers whose list reached 10","proposed":0,"no_cell_passed_checks":0,"rejected_by_independent_check":0,"accepted_not_placed":0,"awaiting_verdict":0,"placed":0,"placed_entries_listed":0,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): none placed; no newer paper judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables a model judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"a model","models_as_recorded":[],"a_record_without_a_model":false,"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here","order":"newest first by arXiv id (the identifier's order, not a rank)","outcomes":{"placed":"placed","no_cell_passed_checks":"no cell passed the extractor's checks","refused_by_rule":"refused by a rule","rejected":"rejected by the independent check","accepted_not_placed":"accepted by the independent check but not placed by this site","awaiting":"awaiting a verdict"},"reason_note":"for refused_by_rule, the rules' plain words for the reason codes the record gives (never the quoted or the actual cell text); null for every other outcome","total":0,"shown_on_page":0,"no_cell_split":{"no_cell_passed_checks_in_ledger":0,"rows_refused_by_rule":0,"rows_no_cell_passed_checks":0},"rows":[]},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per row: of M harvested code samples from that row's paper, n_ran executed on a synthesized fixture (n_ran = n_ran_checked + n_instrument; n_instrument counts failures of Syntology's instrument, not of the code); the other M - n_ran are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"rows_with_graph_line":16,"rows_with_any_sample_ran":16,"rows_with_a_run_with_no_instrument_failure":12,"official":{"state_rule":"the archive's official repositories have samples for this paper that ran: 'official (archive's flag): N ran' (N counts them, instrument failures included); they have samples, none ran: 'official: harvested, nothing ran'; they have no sample for this paper and another sample ran: 'community repositories only' when every sample that ran came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, else 'official: no sample here; runs from other or unrecorded repositories' (a repository named in the paper or found in its text by Syntology, or no repository recorded); otherwise 'official: harvested for another paper' or 'official: not harvested'. Absent when the archive marks no repository official. Official is the archive's is_official flag, not an authorship verdict","flag":"the archive's is_official flag for the paper's code link; not a verdict on who wrote the code","rows_with_an_archive_official_repository":16,"rows_whose_official_repository_has_a_sample_that_ran":14,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":10,"rows_community_repositories_only":2,"rows_runs_from_other_or_unrecorded_repositories":0,"note":"rows[].official, per row with a graph line: repos (marked official in the archive), state, n_ran and n_unverified (samples from those repositories), and ran_from_kinds (the kinds of repository the paper's samples that ran came from; 'unlocated' is no repository recorded)"},"filters":{"ran_modes":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"the page's filters hide rows and never renumber them; they read the Ran cell's counts, the same figures rows[].syntology and rows[].official carry"},"row_route":"rows[].syntology carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","distinct_papers_with_graph_line":13,"distinct_papers_with_any_sample_ran":13,"distinct_papers_with_a_run_with_no_instrument_failure":10,"samples_over_distinct_papers":{"n_ran":73,"n_constructed":2,"n_ran_checked":41,"n_instrument":32,"n_unverified":20,"n_samples":93,"n_pointer_only_licence":50,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":82,"n_constructed":2,"n_ran_checked":47,"n_instrument":35,"n_unverified":29,"n_samples":111,"n_pointer_only_licence":53,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}},"record_sha256":"668a3402fbf945968fa664371446aa8812cfcb855aed3df83f8c01dc117d09b0","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}