Browse › Computer Vision › Skeleton Based Action Recognition › NTU RGB+D 120

Skeleton Based Action Recognition archive 2025-07-28

NTU RGB+D 120 Benchmark (Skeleton Based Action Recognition)

83 rows 62 with code listed 4 metrics Dataset page

Syntology Since the archive (Syntology): none placed; no newer paper judged to report on this board so far.

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

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, not an evaluation date; 82 of 83 rows carry one.

The chart needs JavaScript; the table below carries every value.

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 90.992.26 – Paper Code 2024 linked, not harvested report
2 JMDA (based on Skeleton MixFormer) 90.991.9 – Paper Code 2024 linked, not harvested report
3 LA-GCN 90.791.86 ✓ Paper Code 2023 linked, not harvested report
4 MSA-GCN 90.692.26 – Paper – 2024 no code linked report
5 Shap-Mix 90.491.74 – Paper Code 2024 linked, not harvested report
6 MMCL 90.391.76 ✓ Paper Code 2024 official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified report
7 BlockGCN 90.391.54 – Paper Code 2024 linked, not harvested report
8 TSGCNeXt 90.291.74 – Paper Code 2023 linked, not harvested report
9 HD-GCN 90.191.66 – Paper Code 2022 official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified report
10 MAMP 90.091.3 – Paper Code 2023 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified report
11 STEP-CATFormer 90.091.24 ✓ Paper Code 2023 official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified report
12 Hyperformer 89.991.34 – Paper Code 2022 official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 1 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified report
13 LST 89.991.14 ✓ Paper Code 2022 official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified report
14 SkateFormer 89.891.44 – Paper Code 2024 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified report
15 InfoGCN 89.891.26 – Paper Code 2022 linked, not harvested report
16 Stream-GCN 89.791.0 – Paper – 2023 no code linked report
17 DG-STGCN 89.691.34 – Paper Code 2022 linked, not harvested report
18 SkeletonGCL (based on CTR-GCN) 89.591.04 – Paper Code 2023 linked, not harvested report
19 JPFormer 89.491.44 – Paper Code 2024 linked, not harvested report
20 TCA-GCN 89.490.84 – Paper Code 2022 linked, not harvested report
21 PSUMNet 89.490.6 – Paper Code 2022 linked, not harvested report
22 DSTSA-GCN 89.1290.974 – Paper Code 2025 linked, not harvested report
23 TSGCNeXT 89.190.34 – Paper Code 2023 linked, not harvested report
24 CTR-GCN 88.990.64 – Paper Code 2021 official (archive's flag): 1 ran · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 2 samples that ran constructed an object rather than computing a result report
25 Lit-llama 88.791.5 – Paper – 2024 no code linked report
26 STGAT 88.790.44 – Paper Code 2022 linked, not harvested report
27 EfficientGCN-B4 88.789.1 – Paper Code 2021 linked, not harvested report
28 ST-GCN++ [PYSKL, 3D Skeleton] 88.690.84 – Paper Code 2022 linked, not harvested report
29 DualHead-Net 88.289.34 – Paper Code 2021 official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified report
30 AngNet-JA + BA + JBA + VJBA 88.2%89.2%4 – Paper Code 2021 linked, not harvested report
31 EfficientGCN-B2 87.988.0 – Paper Code 2021 linked, not harvested report
32 Skeletal GNN 87.589.24 – Paper – 2021 no code linked report
33 MaskCLR 87.489.5 – Paper – 2024 no code linked report
34 MSSTNet 87.488.3 – Paper Code 2023 linked, not harvested report
35 PA-ResGCN-B19 87.388.3 – 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) 86.990.3 – Paper Code 2021 linked, not harvested report
38 MS-G3D Net 86.9%88.4% – Paper Code 2020 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified report
39 DSTA-Net 86.6%89.0 % – Paper Code 2020 linked, not harvested report
40 VPN 86.387.8 ✓ Paper Code 2020 linked, not harvested report
41 ST-GCN [PYSKL, 3D Skeleton] 86.288.4 – Paper Code 2018 community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
42 4s Shift-GCN 85.9%87.6%4 – Paper Code 2020 linked, not harvested report
43 EfficientGCN-B0 85.984.3 – Paper Code 2021 linked, not harvested report
44 FGCN 85.4%87.4% – Paper – 2020 no code linked report
45 VA-CNN (ResNeXt-101) 84.8886.90 – – – not matched report
46 S-TR (2-stream) 84.886.232.4 – Paper Code 2022 linked, not harvested report
47 CoS-TR* (2-stream) 84.886.10.3 – Paper Code 2022 linked, not harvested report
48 ST-GCN [PYSKL, 2D Skeleton] 84.789.0 – Paper Code 2018 community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
49 3s-HYSP 84.586.3 – Paper Code 2023 official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified report
50 CoST-GCN* (2-stream) 84.085.50.32 – Paper Code 2022 linked, not harvested report
51 AGCN (2-stream) 8485.437.38 – Paper Code 2022 linked, not harvested report
52 ST-GCN (2-stream) 83.785.133.46 – Paper Code 2022 linked, not harvested report
53 ST-TR-agcn 82.7%84.7% – Paper Code 2020 linked, not harvested report
54 HYSP 81.482 – Paper Code 2023 official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified report
55 3s RA-GCN 81.1%82.7% – Paper Code 2020 linked, not harvested report
56 3s-USDRL (DSTE) This work 80.679.3 – Paper Code 2024 linked, not harvested report
57 Mix-Dimension 80.5%83.2% – Paper – 2020 no code linked report
58 CoAGCN* (2-stream) 80.4820.44 – Paper Code 2022 linked, not harvested report
59 S-TR (1-stream) 80.281.816.2 – Paper Code 2022 linked, not harvested report
60 CoS-TR* (1-stream) 79.781.70.15 – Paper Code 2022 linked, not harvested report
61 AGCN (1-stream) 79.780.718.69 – Paper Code 2022 linked, not harvested report
62 CoST-GCN* (1-stream) 79.481.60.16 – Paper Code 2022 linked, not harvested report
63 ST-GCN (1-stream) 7916.73 – 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) 77.379.10.22 – 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 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 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 official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 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 ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”: of the code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and U are unverified (harvested, no recorded run). Of the N, C constructed an object rather than computing a result (a part of N, never taken away from it), K ran with no instrument failure (honoured or violated the contract Syntology drafted, or ran with no contract checked) and I are failures of Syntology's instrument, not of the code (a wrong contract draft, or a contract check that could not 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. Rows whose paper has a sample that ran: 16 (12 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument). Papers: 13 with a sample that ran: 10 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument. Whose code ran. When the archive marks a repository official for the row's paper, the cell starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code): “official (archive's flag): N ran” counts the samples from it that ran, instrument failures included; “official: harvested, nothing ran”; when it has no sample for this paper and other samples ran, “community repositories only” if every one 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, and “official: no sample here; runs from other or unrecorded repositories” if any came from a repository named in the paper or found in its text by Syntology, or has no repository recorded; “official: harvested for another paper” (no sample from it is linked to this paper) or “official: not harvested”. No state is printed when the archive marks none official. The cell's tooltip names the repositories the samples that ran came from. Of the 16 rows with a graph line, 16 have an archive-official repository: on 14 a sample from it ran (10 with a run with no instrument failure), on 2 the samples that ran came from community repositories only, and on 0 from other or unrecorded repositories. The filters above hide rows and never renumber them; the first two count, by default, only a run with no instrument failure, and offer any run, instrument failures included. Counting each paper once, of 93 samples: 73 ran (of which 2 constructed an object rather than computing a result; 41 with no instrument failure: 13 honoured, 8 violated, 20 with no contract checked; 32 where Syntology's instrument failed) · 20 unverified. Separately, 50 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. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. Per-sample status is on the paper page; each Ran cell links to that paper's sample list. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Since the archive Syntology

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. 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.

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