AI Paper Atlas

Research map / Benchmarks / NTU RGB+D 120 X-Set

NTU RGB+D 120 X-Set leaderboard

13 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on NTU RGB+D 120 X-Set. Best accuracy: 92.2 (ProtoGCN (6-ensemble), CVPR 2025).

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 RGB+D 120 X-Set · accuracy

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

#accuracy ↑MethodPaperTopic
192.2ProtoGCN (6-ensemble)
PYSKL
Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition
CVPR 2025 · Table 1
Action recognition
291.9HiOD (6-ensemble)Hierarchical-aware Orthogonal Disentanglement Framework for Fine-grained Skeleton-based Action Recognition
ICCV 2025 · Table 1
Action recognition
391.7OursSkeleton-based Action Recognition with Non-linear Dependency Modeling and Hilbert-Schmidt Independence Criterion
AAAI 2025 · Table: NTU RGB+D 120
Molecules and proteins
491.7STC-Net (6-ensemble)Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition
ICCV 2023 · Table 1
Knowledge and temporal graphs
591.5BlockGCNBlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition
CVPR 2024 · Table 2
Knowledge and temporal graphs
691.5LLM-AR
LLaMA-13B
LLMs are Good Action Recognizers
CVPR 2024 · Table 1
Language, safety and interpretability
791.3CTR-GCN w/ Koopman Pooling
CTR-GCN
Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action Recognition
CVPR 2023 · Table 1
Action recognition
891.1GAP (4 ensemble)
CTR-GCN
Generative Action Description Prompts for Skeleton-based Action Recognition
ICCV 2023 · Table 4
Action recognition
990.9Ours
CTR-GCN
Learning Discriminative Representations for Skeleton Based Action Recognition
CVPR 2023 · Table: Performance comparison
Action recognition
1090.6CTR-GCNChannel-Wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition
ICCV 2021 · Table 5
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.