OpenCodePapers

one-shot-3d-action-recognition-on-ntu-rgbd

Human Interaction RecognitionOne-Shot 3D Action Recognition
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeAccuracyModelNameReleaseDate
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment✓ Link69.8%PGFA2025-07-01
SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature Aggregation✓ Link69.1%SkeletonX2025-04-16
MotionBERT: A Unified Perspective on Learning Human Motion Representations✓ Link67.4%MotionBERT (Finetune)2022-10-12
Skeleton-DML: Deep Metric Learning for Skeleton-Based One-Shot Action Recognition✓ Link54.2%Skeleton-DML2020-12-26
SL-DML: Signal Level Deep Metric Learning for Multimodal One-Shot Action Recognition✓ Link49.6%Deep Metric Learning (Triplet Loss, Signals)2020-04-23
One-shot action recognition in challenging therapy scenarios✓ Link46.5%TCN_OneShot2021-02-17
NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding✓ Link45.3%APSR2019-05-12
Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates42.9%Average Pooling2017-06-26
Global Context-Aware Attention LSTM Networks for 3D Action Recognition42.1%Fully Connected2017-07-01
Global Context-Aware Attention LSTM Networks for 3D Action Recognition41.0%Attention Network2017-07-01