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/MAMP

MAMP

Reported on 56 benchmarks across 10 tasks · 2 papers

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

Computer Vision36 results

VideoonNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-08-14
91.3
best: 92.2 (ProtoGCN)
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
VideoonNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-08-14
90
best: 90.9 (ProtoGCN)
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
VideoonNTU RGB+D
Accuracy (CS)· 2023-08-14
93.1
best: 94.3 (Hulk(Finetune, ViT-L))
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
VideoonNTU RGB+D
Accuracy (CV)· 2023-08-14
97.5
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Temporal Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-08-14
91.3
best: 92.2 (ProtoGCN)
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Temporal Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-08-14
90
best: 90.9 (ProtoGCN)
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Temporal Action LocalizationonNTU RGB+D
Accuracy (CS)· 2023-08-14
93.1
best: 94.3 (Hulk(Finetune, ViT-L))
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Temporal Action LocalizationonNTU RGB+D
Accuracy (CV)· 2023-08-14
97.5
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-08-14
91.3
best: 92.2 (ProtoGCN)
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-08-14
90
best: 90.9 (ProtoGCN)
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Action LocalizationonNTU RGB+D
Accuracy (CS)· 2023-08-14
93.1
best: 94.3 (Hulk(Finetune, ViT-L))
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Action LocalizationonNTU RGB+D
Accuracy (CV)· 2023-08-14
97.5
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
VideoonDAVIS 2017 (val)
F-measure (Mean)· 2021-07-27
71.2
best: 93.4 (Cutie+ (base))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
VideoonDAVIS 2017 (val)
J&F· 2021-07-27
69.7
best: 90.7 (SAM2)
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
VideoonDAVIS 2017 (val)
Jaccard (Mean)· 2021-07-27
68.3
best: 87.5 (Cutie+ (base))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
VideoonYouTube-VOS 2018
F-Measure (Seen)· 2021-07-27
68.4
best: 91 (Cutie+ (base, MEGA))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
VideoonYouTube-VOS 2018
F-Measure (Unseen)· 2021-07-27
73.2
best: 90.2 (XMem (BL30K, MS))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
VideoonYouTube-VOS 2018
Jaccard (Seen)· 2021-07-27
67
best: 86.6 (Cutie+ (base, MEGA))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
VideoonYouTube-VOS 2018
Jaccard (Unseen)· 2021-07-27
64.5
best: 82.2 (Cutie+ (base, MEGA))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
VideoonYouTube-VOS 2018
Overall· 2021-07-27
68.2
best: 87.5 (Cutie+ (base, MEGA))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
Video Object SegmentationonDAVIS 2017 (val)
F-measure (Mean)· 2021-07-27
71.2
best: 93.4 (Cutie+ (base))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
Video Object SegmentationonDAVIS 2017 (val)
J&F· 2021-07-27
69.7
best: 90.7 (SAM2)
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
Video Object SegmentationonDAVIS 2017 (val)
Jaccard (Mean)· 2021-07-27
68.3
best: 87.5 (Cutie+ (base))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
Video Object SegmentationonYouTube-VOS 2018
F-Measure (Seen)· 2021-07-27
68.4
best: 91 (Cutie+ (base, MEGA))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
Video Object SegmentationonYouTube-VOS 2018
F-Measure (Unseen)· 2021-07-27
73.2
best: 90.2 (XMem (BL30K, MS))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
Video Object SegmentationonYouTube-VOS 2018
Jaccard (Seen)· 2021-07-27
67
best: 86.6 (Cutie+ (base, MEGA))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
Video Object SegmentationonYouTube-VOS 2018
Jaccard (Unseen)· 2021-07-27
64.5
best: 82.2 (Cutie+ (base, MEGA))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
Video Object SegmentationonYouTube-VOS 2018
Overall· 2021-07-27
68.2
best: 87.5 (Cutie+ (base, MEGA))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
F-measure (Mean)· 2021-07-27
71.2
best: 93.4 (Cutie+ (base))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
J&F· 2021-07-27
69.7
best: 90.7 (SAM2)
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
Semi-Supervised Video Object SegmentationonDAVIS 2017 (val)
Jaccard (Mean)· 2021-07-27
68.3
best: 87.5 (Cutie+ (base))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
F-Measure (Seen)· 2021-07-27
68.4
best: 91 (Cutie+ (base, MEGA))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
F-Measure (Unseen)· 2021-07-27
73.2
best: 90.2 (XMem (BL30K, MS))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
Jaccard (Seen)· 2021-07-27
67
best: 86.6 (Cutie+ (base, MEGA))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
Jaccard (Unseen)· 2021-07-27
64.5
best: 82.2 (Cutie+ (base, MEGA))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569
Semi-Supervised Video Object SegmentationonYouTube-VOS 2018
Overall· 2021-07-27
68.2
best: 87.5 (Cutie+ (base, MEGA))
Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagation arXiv:2107.12569

Time Series8 results

Action DetectiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-08-14
91.3
best: 92.2 (ProtoGCN)
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Action DetectiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-08-14
90
best: 90.9 (ProtoGCN)
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Action DetectiononNTU RGB+D
Accuracy (CS)· 2023-08-14
93.1
best: 94.3 (Hulk(Finetune, ViT-L))
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Action DetectiononNTU RGB+D
Accuracy (CV)· 2023-08-14
97.5
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-08-14
91.3
best: 96.7 (DSCNet (RGB + Pose))
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-08-14
90
best: 95.6 (DSCNet (RGB + Pose))
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Action RecognitiononNTU RGB+D
Accuracy (CS)· 2023-08-14
93.1
best: 97.4 (DSCNet (RGB + Pose))
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Action RecognitiononNTU RGB+D
Accuracy (CV)· 2023-08-14
97.5
best: 99.6 (PoseC3D (RGB + Pose))
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092

Methodology4 results

Zero-Shot LearningonNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-08-14
91.3
best: 92.2 (ProtoGCN)
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Zero-Shot LearningonNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-08-14
90
best: 90.9 (ProtoGCN)
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Zero-Shot LearningonNTU RGB+D
Accuracy (CS)· 2023-08-14
93.1
best: 94.3 (Hulk(Finetune, ViT-L))
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Zero-Shot LearningonNTU RGB+D
Accuracy (CV)· 2023-08-14
97.5
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092

Robots4 results

Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-08-14
91.3
best: 96.7 (DSCNet (RGB + Pose))
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-08-14
90
best: 95.6 (DSCNet (RGB + Pose))
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Activity RecognitiononNTU RGB+D
Accuracy (CS)· 2023-08-14
93.1
best: 97.4 (DSCNet (RGB + Pose))
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
Activity RecognitiononNTU RGB+D
Accuracy (CV)· 2023-08-14
97.5
best: 99.6 (PoseC3D (RGB + Pose))
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092

Natural Language Processing4 results

3D Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· 2023-08-14
91.3
best: 92.2 (ProtoGCN)
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
3D Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· 2023-08-14
90
best: 90.9 (ProtoGCN)
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
3D Action RecognitiononNTU RGB+D
Accuracy (CS)· 2023-08-14
93.1
best: 94.3 (Hulk(Finetune, ViT-L))
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092
3D Action RecognitiononNTU RGB+D
Accuracy (CV)· 2023-08-14
97.5
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Masked Motion Predictors are Strong 3D Action Representation Learners arXiv:2308.07092