AI Paper Atlas

Research map / Benchmarks / MSR Action3D

MSR Action3D leaderboard

11 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MSR Action3D. Best accuracy: 97.3 (Ker-RP-RBF+α-CML+SVM, CVPR 2017).

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.

MSR Action3D · accuracy

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

#accuracy ↑MethodPaperTopic
197.3Ker-RP-RBF+α-CML+SVMRevisiting Metric Learning for SPD Matrix Based Visual Representation
CVPR 2017 · Table 3
Matrix and tensor methods
294.8ST-LSTM (Tree) + Trust GateSkeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates
TPAMI 2017 · Table 10
Action recognition
394.8ST-LSTM (Tree) + Trust GateSpatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition
ECCV 2016 · text
Action recognition
494.57Transition ForestsTransition Forests: Learning Discriminative Temporal Transitions for Action Recognition and Detection
CVPR 2017 · Table: Comparison with forest-
Action recognition
593.38Contrastive prediction and reconstruction
PSTNet
Contrastive Predictive Autoencoders for Dynamic Point Cloud Self-Supervised Learning
AAAI 2023 · Table 7
Point cloud classification
693Our modelA Hierarchical Pose-Based Approach to Complex Action Understanding Using Dictionaries of Actionlets and Motion Poselets
CVPR 2016 · MSR-Action3D results table
Action recognition
792.29PointLSTM-lateAn Efficient PointLSTM for Point Clouds Based Gesture Recognition
CVPR 2020 · Table 5
Point cloud classification
890.94P4Transformer, 24 framesPoint 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos
CVPR 2021 · Table 1
Point cloud classification
988.5MeteorNet-cls (24 frames)MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences
ICCV 2019 · Table 2
Point cloud classification
1087Separable ST-GST (5, 20, 3)Spatio-Temporal Graph Scattering Transform
ICLR 2021 · Additional Experiments, full p
Knowledge and temporal graphs
1 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.