AI Paper Atlas

Research map / Benchmarks / NTU-60 X-Sub

NTU-60 X-Sub leaderboard

13 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on NTU-60 X-Sub. Best accuracy: 97 (RGBPose-Conv3D, CVPR 2022).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

NTU-60 X-Sub · accuracy

13 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
197RGBPose-Conv3D
SlowOnly, R50
Revisiting Skeleton-Based Action Recognition
CVPR 2022 · Table: Multi-Modality Action R
Recognition and long-tail
294.83Mformer (rank-pool)
Higher-order Transformer
3Mformer: Multi-Order Multi-Mode Transformer for Skeletal Action Recognition
CVPR 2023 · Table: Experimental results on
Knowledge and temporal graphs
394.3Hulk-FT
ViT-L
Hulk: A Universal Knowledge Translator for Human-Centric Tasks
TPAMI 2025 · Table (skeleton action)
Robot action and navigation
494.3Ours (3D deformable transformer, R+P, no pre-training)Cross-Modal Learning with 3D Deformable Attention for Action Recognition
ICCV 2023 · Table 3
Action recognition
593.9OursRethinking Masked Data Reconstruction Pretraining for Strong 3D Action Representation Learning
AAAI 2025 · Table 2
Self-supervised and contrastive
693.9MaskCLR
DSTFormer
MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning
CVPR 2024 · Table 1
Recognition and long-tail
793.4JT-GraphFormer (4s)Spatio-Temporal Fusion for Human Action Recognition via Joint Trajectory Graph
AAAI 2024 · Table 5
Action recognition
893.1+ UKTL
MLP+HoT
Subspace Kernel Learning on Tensor Sequences
ICLR 2026 · Table 1
Matrix and tensor methods
993.1VA-ARVA-AR: Learning Velocity-Aware Action Representations with Mixture of Window Attention
AAAI 2025 · Table 1
Action recognition
1093.1DS-GCNDynamic Semantic-Based Spatial Graph Convolution Network for Skeleton-Based Human Action Recognition
AAAI 2024 · Table 6
Knowledge and temporal graphs
3 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.