Browse › Computer Vision › Skeleton Based Action Recognition › NTU RGB+D 120
NTU RGB+D 120 Benchmark (Skeleton Based Action Recognition)
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.
The archive carries no text for this table; the description above is the archive's text for the task Skeleton Based Action Recognition. archive 2025-07-28
Over time archive 2025-07-28
The chart needs JavaScript; the table below carries every value.
Direction inferred from the metric name, not from the archive: Accuracy (Cross-Subject) (higher is better), Accuracy (Cross-Setup) (higher is better). Not inferred (points only, no best-so-far line): Ensembled Modalities, GFLOPS per prediction. Points are placed at the row's paper date; 82 of 83 rows carry one.
Results archive 2025-07-28
Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.
| Paper | Code | Ran Syntology | Report | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | ProtoGCN | 90.9 | 92.2 | 6 | – | Paper | Code | 2024 | linked, not harvested | report | |
| 2 | JMDA (based on Skeleton MixFormer) | 90.9 | 91.9 | – | Paper | Code | 2024 | linked, not harvested | report | ||
| 3 | LA-GCN | 90.7 | 91.8 | 6 | ✓ | Paper | Code | 2023 | linked, not harvested | report | |
| 4 | MSA-GCN | 90.6 | 92.2 | 6 | – | Paper | – | 2024 | no code linked | report | |
| 5 | Shap-Mix | 90.4 | 91.7 | 4 | – | Paper | Code | 2024 | linked, not harvested | report | |
| 6 | MMCL | 90.3 | 91.7 | 6 | ✓ | Paper | Code | 2024 | 9 of 10 ran · 1 unverified | report | |
| 7 | BlockGCN | 90.3 | 91.5 | 4 | – | Paper | Code | 2024 | linked, not harvested | report | |
| 8 | TSGCNeXt | 90.2 | 91.7 | 4 | – | Paper | Code | 2023 | linked, not harvested | report | |
| 9 | HD-GCN | 90.1 | 91.6 | 6 | – | Paper | Code | 2022 | 8 of 11 ran · 3 unverified | report | |
| 10 | MAMP | 90.0 | 91.3 | – | Paper | Code | 2023 | 3 of 4 ran · 1 unverified | report | ||
| 11 | STEP-CATFormer | 90.0 | 91.2 | 4 | ✓ | Paper | Code | 2023 | 10 of 13 ran · 3 unverified | report | |
| 12 | Hyperformer | 89.9 | 91.3 | 4 | – | Paper | Code | 2022 | 10 of 12 ran · 2 unverified | report | |
| 13 | LST | 89.9 | 91.1 | 4 | ✓ | Paper | Code | 2022 | 7 of 10 ran · 3 unverified | report | |
| 14 | SkateFormer | 89.8 | 91.4 | 4 | – | Paper | Code | 2024 | 3 of 3 ran · 0 unverified | report | |
| 15 | InfoGCN | 89.8 | 91.2 | 6 | – | Paper | Code | 2022 | linked, not harvested | report | |
| 16 | Stream-GCN | 89.7 | 91.0 | – | Paper | – | 2023 | no code linked | report | ||
| 17 | DG-STGCN | 89.6 | 91.3 | 4 | – | Paper | Code | 2022 | linked, not harvested | report | |
| 18 | SkeletonGCL (based on CTR-GCN) | 89.5 | 91.0 | 4 | – | Paper | Code | 2023 | linked, not harvested | report | |
| 19 | JPFormer | 89.4 | 91.4 | 4 | – | Paper | Code | 2024 | linked, not harvested | report | |
| 20 | TCA-GCN | 89.4 | 90.8 | 4 | – | Paper | Code | 2022 | linked, not harvested | report | |
| 21 | PSUMNet | 89.4 | 90.6 | – | Paper | Code | 2022 | linked, not harvested | report | ||
| 22 | DSTSA-GCN | 89.12 | 90.97 | 4 | – | Paper | Code | 2025 | linked, not harvested | report | |
| 23 | TSGCNeXT | 89.1 | 90.3 | 4 | – | Paper | Code | 2023 | linked, not harvested | report | |
| 24 | CTR-GCN | 88.9 | 90.6 | 4 | – | Paper | Code | 2021 | 2 of 5 ran · 3 unverified | report | |
| 25 | Lit-llama | 88.7 | 91.5 | – | Paper | – | 2024 | no code linked | report | ||
| 26 | STGAT | 88.7 | 90.4 | 4 | – | Paper | Code | 2022 | linked, not harvested | report | |
| 27 | EfficientGCN-B4 | 88.7 | 89.1 | – | Paper | Code | 2021 | linked, not harvested | report | ||
| 28 | ST-GCN++ [PYSKL, 3D Skeleton] | 88.6 | 90.8 | 4 | – | Paper | Code | 2022 | linked, not harvested | report | |
| 29 | DualHead-Net | 88.2 | 89.3 | 4 | – | Paper | Code | 2021 | 4 of 4 ran · 0 unverified | report | |
| 30 | AngNet-JA + BA + JBA + VJBA | 88.2% | 89.2% | 4 | – | Paper | Code | 2021 | linked, not harvested | report | |
| 31 | EfficientGCN-B2 | 87.9 | 88.0 | – | Paper | Code | 2021 | linked, not harvested | report | ||
| 32 | Skeletal GNN | 87.5 | 89.2 | 4 | – | Paper | – | 2021 | no code linked | report | |
| 33 | MaskCLR | 87.4 | 89.5 | – | Paper | – | 2024 | no code linked | report | ||
| 34 | MSSTNet | 87.4 | 88.3 | – | Paper | Code | 2023 | linked, not harvested | report | ||
| 35 | PA-ResGCN-B19 | 87.3 | 88.3 | – | Paper | Code | 2020 | linked, not harvested | report | ||
| 36 | Ensemble-top5 (MS-G3D Net + 4s Shift-GCN + VA-CNN (ResNeXt101) + 2s SDGCN + GCN-NAS (retrained)) | 87.22% | 88.8% | – | Paper | Code | 2020 | linked, not harvested | report | ||
| 37 | PoseC3D (w. HRNet 2D Skeleton) | 86.9 | 90.3 | – | Paper | Code | 2021 | linked, not harvested | report | ||
| 38 | MS-G3D Net | 86.9% | 88.4% | – | Paper | Code | 2020 | 3 of 3 ran · 0 unverified | report | ||
| 39 | DSTA-Net | 86.6% | 89.0 % | – | Paper | Code | 2020 | linked, not harvested | report | ||
| 40 | VPN | 86.3 | 87.8 | ✓ | Paper | Code | 2020 | linked, not harvested | report | ||
| 41 | ST-GCN [PYSKL, 3D Skeleton] | 86.2 | 88.4 | – | Paper | Code | 2018 | 2 of 2 ran · 0 unverified | report | ||
| 42 | 4s Shift-GCN | 85.9% | 87.6% | 4 | – | Paper | Code | 2020 | linked, not harvested | report | |
| 43 | EfficientGCN-B0 | 85.9 | 84.3 | – | Paper | Code | 2021 | linked, not harvested | report | ||
| 44 | FGCN | 85.4% | 87.4% | – | Paper | – | 2020 | no code linked | report | ||
| 45 | VA-CNN (ResNeXt-101) | 84.88 | 86.90 | – | – | – | not matched | report | |||
| 46 | S-TR (2-stream) | 84.8 | 86.2 | 32.4 | – | Paper | Code | 2022 | linked, not harvested | report | |
| 47 | CoS-TR* (2-stream) | 84.8 | 86.1 | 0.3 | – | Paper | Code | 2022 | linked, not harvested | report | |
| 48 | ST-GCN [PYSKL, 2D Skeleton] | 84.7 | 89.0 | – | Paper | Code | 2018 | 2 of 2 ran · 0 unverified | report | ||
| 49 | 3s-HYSP | 84.5 | 86.3 | – | Paper | Code | 2023 | 2 of 13 ran · 11 unverified | report | ||
| 50 | CoST-GCN* (2-stream) | 84.0 | 85.5 | 0.32 | – | Paper | Code | 2022 | linked, not harvested | report | |
| 51 | AGCN (2-stream) | 84 | 85.4 | 37.38 | – | Paper | Code | 2022 | linked, not harvested | report | |
| 52 | ST-GCN (2-stream) | 83.7 | 85.1 | 33.46 | – | Paper | Code | 2022 | linked, not harvested | report | |
| 53 | ST-TR-agcn | 82.7% | 84.7% | – | Paper | Code | 2020 | linked, not harvested | report | ||
| 54 | HYSP | 81.4 | 82 | – | Paper | Code | 2023 | 2 of 13 ran · 11 unverified | report | ||
| 55 | 3s RA-GCN | 81.1% | 82.7% | – | Paper | Code | 2020 | linked, not harvested | report | ||
| 56 | 3s-USDRL (DSTE) This work | 80.6 | 79.3 | – | Paper | Code | 2024 | linked, not harvested | report | ||
| 57 | Mix-Dimension | 80.5% | 83.2% | – | Paper | – | 2020 | no code linked | report | ||
| 58 | CoAGCN* (2-stream) | 80.4 | 82 | 0.44 | – | Paper | Code | 2022 | linked, not harvested | report | |
| 59 | S-TR (1-stream) | 80.2 | 81.8 | 16.2 | – | Paper | Code | 2022 | linked, not harvested | report | |
| 60 | CoS-TR* (1-stream) | 79.7 | 81.7 | 0.15 | – | Paper | Code | 2022 | linked, not harvested | report | |
| 61 | AGCN (1-stream) | 79.7 | 80.7 | 18.69 | – | Paper | Code | 2022 | linked, not harvested | report | |
| 62 | CoST-GCN* (1-stream) | 79.4 | 81.6 | 0.16 | – | Paper | Code | 2022 | linked, not harvested | report | |
| 63 | ST-GCN (1-stream) | 79 | 16.73 | – | Paper | Code | 2022 | linked, not harvested | report | ||
| 64 | GVFE + AS-GCN with DH-TCN | 78.3% | 79.8% | – | Paper | – | 2019 | no code linked | report | ||
| 65 | CoAGCN* (1-stream) | 77.3 | 79.1 | 0.22 | – | Paper | Code | 2022 | linked, not harvested | report | |
| 66 | Gimme Signals (Skeleton, AIS) | 70.8% | 71.6% | – | Paper | Code | 2020 | linked, not harvested | report | ||
| 67 | Logsig-RNN | 68.3% | 67.2% | – | Paper | – | 2019 | no code linked | report | ||
| 68 | TSRJI (Late Fusion) + HCN | 67.9% | 62.8% | – | Paper | Code | 2019 | linked, not harvested | report | ||
| 69 | SkeleMotion + Yang et al. (2018) | 67.7% | 66.9% | – | Paper | Code | 2019 | 3 of 3 ran · 0 unverified | report | ||
| 70 | TSRJI (Late Fusion) | 65.5% | 59.7% | – | Paper | Code | 2019 | linked, not harvested | report | ||
| 71 | Body Pose Evolution Map | 64.6% | 66.9% | – | Paper | – | 2018 | no code linked | report | ||
| 72 | SkeleMotion [Magnitude-Orientation (TSA)] | 62.9% | 63.0% | – | Paper | Code | 2019 | 3 of 3 ran · 0 unverified | report | ||
| 73 | Multi-Task CNN with RotClips | 62.2% | 61.8% | – | Paper | – | 2018 | no code linked | report | ||
| 74 | Two-Stream Attention LSTM | 61.2% | 63.3% | – | Paper | – | 2017 | no code linked | report | ||
| 75 | Skeleton Visualization (Single Stream) | 60.3% | 63.2% | – | Paper | – | 2017 | no code linked | report | ||
| 76 | FSNet | 59.9% | 62.4% | – | Paper | – | 2019 | no code linked | report | ||
| 77 | Multi-Task Learning Network | 58.4% | 57.9% | – | Paper | – | 2017 | no code linked | report | ||
| 78 | GCA-LSTM | 58.3% | 59.2% | – | Paper | – | 2017 | no code linked | report | ||
| 79 | Internal Feature Fusion | 58.2% | 60.9% | – | Paper | – | 2017 | no code linked | report | ||
| 80 | Spatio-Temporal LSTM | 55.7% | 57.9% | – | Paper | – | 2016 | no code linked | report | ||
| 81 | Dynamic Skeletons | 50.8% | 54.7% | – | Paper | – | 2016 | no code linked | report | ||
| 82 | Soft RNN | 36.3% | 44.9% | – | Paper | – | 2018 | no code linked | report | ||
| 83 | Part-Aware LSTM | 25.5% | 26.3% | – | Paper | Code | 2016 | linked, not harvested | report |
All 83 rows shown. 82 link to a paper page on this site; 5 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28
Syntology Ran reads "N of M ran · U unverified": of the M code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and the other U = M−N are unverified (harvested, no recorded run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 16 rows have a graph line, from 13 distinct papers; 16 rows (13 papers) have at least one sample that ran. Counting each paper once: Syntology ran 66 of 93 samples; 27 unverified. Separately, 24 of those 93 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Read from the graph 2026-09-24. Per-sample status is on the paper page.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections