Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/MotionBert (finetune)

MotionBert (finetune)

Reported on 16 benchmarks across 8 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision6 results

VideoonNTU RGB+D
Accuracy (CS)· 2022-10-12
93
best: 94.3 (Hulk(Finetune, ViT-L))
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
VideoonNTU RGB+D
Accuracy (CV)· 2022-10-12
97.2
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
Temporal Action LocalizationonNTU RGB+D
Accuracy (CS)· 2022-10-12
93
best: 94.3 (Hulk(Finetune, ViT-L))
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
Temporal Action LocalizationonNTU RGB+D
Accuracy (CV)· 2022-10-12
97.2
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
Action LocalizationonNTU RGB+D
Accuracy (CS)· 2022-10-12
93
best: 94.3 (Hulk(Finetune, ViT-L))
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
Action LocalizationonNTU RGB+D
Accuracy (CV)· 2022-10-12
97.2
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551

Time Series4 results

Action DetectiononNTU RGB+D
Accuracy (CS)· 2022-10-12
93
best: 94.3 (Hulk(Finetune, ViT-L))
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
Action DetectiononNTU RGB+D
Accuracy (CV)· 2022-10-12
97.2
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
Action RecognitiononNTU RGB+D
Accuracy (CS)· 2022-10-12
93
best: 97.4 (DSCNet (RGB + Pose))
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
Action RecognitiononNTU RGB+D
Accuracy (CV)· 2022-10-12
97.2
best: 99.6 (PoseC3D (RGB + Pose))
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551

Methodology2 results

Zero-Shot LearningonNTU RGB+D
Accuracy (CS)· 2022-10-12
93
best: 94.3 (Hulk(Finetune, ViT-L))
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
Zero-Shot LearningonNTU RGB+D
Accuracy (CV)· 2022-10-12
97.2
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551

Robots2 results

Activity RecognitiononNTU RGB+D
Accuracy (CS)· 2022-10-12
93
best: 97.4 (DSCNet (RGB + Pose))
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
Activity RecognitiononNTU RGB+D
Accuracy (CV)· 2022-10-12
97.2
best: 99.6 (PoseC3D (RGB + Pose))
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551

Natural Language Processing2 results

3D Action RecognitiononNTU RGB+D
Accuracy (CS)· 2022-10-12
93
best: 94.3 (Hulk(Finetune, ViT-L))
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551
3D Action RecognitiononNTU RGB+D
Accuracy (CV)· 2022-10-12
97.2
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
MotionBERT: A Unified Perspective on Learning Human Motion Representations arXiv:2210.06551