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/MMCL

MMCL

Reported on 88 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.

Methodology23 results

Zero-Shot LearningonNTU RGB+D 120
Accuracy (Cross-Setup)· uses extra data· 2024-07-22
91.7
best: 92.2 (ProtoGCN)
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Zero-Shot LearningonNTU RGB+D 120
Accuracy (Cross-Subject)· uses extra data· 2024-07-22
90.3
best: 90.9 (ProtoGCN)
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Zero-Shot LearningonNTU RGB+D 120
Ensembled Modalities· uses extra data· 2024-07-22
6
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Zero-Shot LearningonN-UCLA
Accuracy· uses extra data· 2024-07-22
97.5
best: 99.1 (DSCNet (RGB + Pose))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Zero-Shot LearningonNTU RGB+D
Accuracy (CS)· uses extra data· 2024-07-22
93.5
best: 94.3 (Hulk(Finetune, ViT-L))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Zero-Shot LearningonNTU RGB+D
Accuracy (CV)· uses extra data· 2024-07-22
97.4
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Zero-Shot LearningonNTU RGB+D
Ensembled Modalities· uses extra data· 2024-07-22
6
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Domain AdaptationonDuke to MSMT
mAP· 2020-04-20
16.2
best: 45.2 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Domain AdaptationonDuke to MSMT
rank-1· 2020-04-20
43.6
best: 72.2 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Domain AdaptationonDuke to MSMT
rank-10· 2020-04-20
58.9
best: 86.3 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Domain AdaptationonDuke to MSMT
rank-5· 2020-04-20
54.3
best: 82.9 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Domain AdaptationonMarket to MSMT
mAP· 2020-04-20
15.1
best: 44.1 (CORE-ReID V2)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Domain AdaptationonMarket to MSMT
rank-1· 2020-04-20
40.8
best: 71.3 (CORE-ReID V2)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Domain AdaptationonMarket to MSMT
rank-10· 2020-04-20
56.7
best: 86 (CORE-ReID V2)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Domain AdaptationonMarket to MSMT
rank-5· 2020-04-20
51.8
best: 82.4 (CORE-ReID V2)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Domain AdaptationonMarket to Duke
mAP· 2020-04-20
51.4
best: 74.8 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Domain AdaptationonMarket to Duke
rank-1· 2020-04-20
72.4
best: 85 (CCTSE)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Domain AdaptationonMarket to Duke
rank-10· 2020-04-20
85
best: 94.4 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Domain AdaptationonMarket to Duke
rank-5· 2020-04-20
82.9
best: 92.4 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Domain AdaptationonDuke to Market
mAP· 2020-04-20
60.4
best: 84.4 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Domain AdaptationonDuke to Market
rank-1· 2020-04-20
84.4
best: 93.6 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Domain AdaptationonDuke to Market
rank-10· 2020-04-20
95
best: 98.7 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Domain AdaptationonDuke to Market
rank-5· 2020-04-20
92.8
best: 97.7 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228

Computer Vision21 results

VideoonNTU RGB+D 120
Accuracy (Cross-Setup)· uses extra data· 2024-07-22
91.7
best: 92.2 (ProtoGCN)
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
VideoonNTU RGB+D 120
Accuracy (Cross-Subject)· uses extra data· 2024-07-22
90.3
best: 90.9 (ProtoGCN)
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
VideoonNTU RGB+D 120
Ensembled Modalities· uses extra data· 2024-07-22
6
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
VideoonN-UCLA
Accuracy· uses extra data· 2024-07-22
97.5
best: 99.1 (DSCNet (RGB + Pose))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
VideoonNTU RGB+D
Accuracy (CS)· uses extra data· 2024-07-22
93.5
best: 94.3 (Hulk(Finetune, ViT-L))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
VideoonNTU RGB+D
Accuracy (CV)· uses extra data· 2024-07-22
97.4
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
VideoonNTU RGB+D
Ensembled Modalities· uses extra data· 2024-07-22
6
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Temporal Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Setup)· uses extra data· 2024-07-22
91.7
best: 92.2 (ProtoGCN)
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Temporal Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Subject)· uses extra data· 2024-07-22
90.3
best: 90.9 (ProtoGCN)
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Temporal Action LocalizationonNTU RGB+D 120
Ensembled Modalities· uses extra data· 2024-07-22
6
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Temporal Action LocalizationonN-UCLA
Accuracy· uses extra data· 2024-07-22
97.5
best: 99.1 (DSCNet (RGB + Pose))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Temporal Action LocalizationonNTU RGB+D
Accuracy (CS)· uses extra data· 2024-07-22
93.5
best: 94.3 (Hulk(Finetune, ViT-L))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Temporal Action LocalizationonNTU RGB+D
Accuracy (CV)· uses extra data· 2024-07-22
97.4
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Temporal Action LocalizationonNTU RGB+D
Ensembled Modalities· uses extra data· 2024-07-22
6
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Setup)· uses extra data· 2024-07-22
91.7
best: 92.2 (ProtoGCN)
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Subject)· uses extra data· 2024-07-22
90.3
best: 90.9 (ProtoGCN)
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Action LocalizationonNTU RGB+D 120
Ensembled Modalities· uses extra data· 2024-07-22
6
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Action LocalizationonN-UCLA
Accuracy· uses extra data· 2024-07-22
97.5
best: 99.1 (DSCNet (RGB + Pose))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Action LocalizationonNTU RGB+D
Accuracy (CS)· uses extra data· 2024-07-22
93.5
best: 94.3 (Hulk(Finetune, ViT-L))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Action LocalizationonNTU RGB+D
Accuracy (CV)· uses extra data· 2024-07-22
97.4
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Action LocalizationonNTU RGB+D
Ensembled Modalities· uses extra data· 2024-07-22
6
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706

Other16 results

Unsupervised Domain AdaptationonDuke to MSMT
mAP· 2020-04-20
16.2
best: 45.2 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Unsupervised Domain AdaptationonDuke to MSMT
rank-1· 2020-04-20
43.6
best: 72.2 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Unsupervised Domain AdaptationonDuke to MSMT
rank-10· 2020-04-20
58.9
best: 86.3 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Unsupervised Domain AdaptationonDuke to MSMT
rank-5· 2020-04-20
54.3
best: 82.9 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Unsupervised Domain AdaptationonMarket to MSMT
mAP· 2020-04-20
15.1
best: 44.1 (CORE-ReID V2)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Unsupervised Domain AdaptationonMarket to MSMT
rank-1· 2020-04-20
40.8
best: 71.3 (CORE-ReID V2)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Unsupervised Domain AdaptationonMarket to MSMT
rank-10· 2020-04-20
56.7
best: 86 (CORE-ReID V2)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Unsupervised Domain AdaptationonMarket to MSMT
rank-5· 2020-04-20
51.8
best: 82.4 (CORE-ReID V2)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Unsupervised Domain AdaptationonMarket to Duke
mAP· 2020-04-20
51.4
best: 74.8 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Unsupervised Domain AdaptationonMarket to Duke
rank-1· 2020-04-20
72.4
best: 85 (CCTSE)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Unsupervised Domain AdaptationonMarket to Duke
rank-10· 2020-04-20
85
best: 94.4 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Unsupervised Domain AdaptationonMarket to Duke
rank-5· 2020-04-20
82.9
best: 92.4 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Unsupervised Domain AdaptationonDuke to Market
mAP· 2020-04-20
60.4
best: 84.4 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Unsupervised Domain AdaptationonDuke to Market
rank-1· 2020-04-20
84.4
best: 93.6 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Unsupervised Domain AdaptationonDuke to Market
rank-10· 2020-04-20
95
best: 98.7 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228
Unsupervised Domain AdaptationonDuke to Market
rank-5· 2020-04-20
92.8
best: 97.7 (CORE-ReID)
Unsupervised Person Re-identification via Multi-label Classification arXiv:2004.09228

Time Series14 results

Action DetectiononNTU RGB+D 120
Accuracy (Cross-Setup)· uses extra data· 2024-07-22
91.7
best: 92.2 (ProtoGCN)
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Action DetectiononNTU RGB+D 120
Accuracy (Cross-Subject)· uses extra data· 2024-07-22
90.3
best: 90.9 (ProtoGCN)
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Action DetectiononNTU RGB+D 120
Ensembled Modalities· uses extra data· 2024-07-22
6
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Action DetectiononN-UCLA
Accuracy· uses extra data· 2024-07-22
97.5
best: 99.1 (DSCNet (RGB + Pose))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Action DetectiononNTU RGB+D
Accuracy (CS)· uses extra data· 2024-07-22
93.5
best: 94.3 (Hulk(Finetune, ViT-L))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Action DetectiononNTU RGB+D
Accuracy (CV)· uses extra data· 2024-07-22
97.4
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Action DetectiononNTU RGB+D
Ensembled Modalities· uses extra data· 2024-07-22
6
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· uses extra data· 2024-07-22
91.7
best: 96.7 (DSCNet (RGB + Pose))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· uses extra data· 2024-07-22
90.3
best: 95.6 (DSCNet (RGB + Pose))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Action RecognitiononNTU RGB+D 120
Ensembled Modalities· uses extra data· 2024-07-22
6
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Action RecognitiononN-UCLA
Accuracy· uses extra data· 2024-07-22
97.5
best: 99.1 (DSCNet (RGB + Pose))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Action RecognitiononNTU RGB+D
Accuracy (CS)· uses extra data· 2024-07-22
93.5
best: 97.4 (DSCNet (RGB + Pose))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Action RecognitiononNTU RGB+D
Accuracy (CV)· uses extra data· 2024-07-22
97.4
best: 99.6 (PoseC3D (RGB + Pose))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Action RecognitiononNTU RGB+D
Ensembled Modalities· uses extra data· 2024-07-22
6
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706

Robots7 results

Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· uses extra data· 2024-07-22
91.7
best: 96.7 (DSCNet (RGB + Pose))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· uses extra data· 2024-07-22
90.3
best: 95.6 (DSCNet (RGB + Pose))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Activity RecognitiononNTU RGB+D 120
Ensembled Modalities· uses extra data· 2024-07-22
6
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Activity RecognitiononN-UCLA
Accuracy· uses extra data· 2024-07-22
97.5
best: 99.1 (DSCNet (RGB + Pose))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Activity RecognitiononNTU RGB+D
Accuracy (CS)· uses extra data· 2024-07-22
93.5
best: 97.4 (DSCNet (RGB + Pose))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Activity RecognitiononNTU RGB+D
Accuracy (CV)· uses extra data· 2024-07-22
97.4
best: 99.6 (PoseC3D (RGB + Pose))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
Activity RecognitiononNTU RGB+D
Ensembled Modalities· uses extra data· 2024-07-22
6
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706

Natural Language Processing7 results

3D Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· uses extra data· 2024-07-22
91.7
best: 92.2 (ProtoGCN)
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
3D Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· uses extra data· 2024-07-22
90.3
best: 90.9 (ProtoGCN)
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
3D Action RecognitiononNTU RGB+D 120
Ensembled Modalities· uses extra data· 2024-07-22
6
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
3D Action RecognitiononN-UCLA
Accuracy· uses extra data· 2024-07-22
97.5
best: 99.1 (DSCNet (RGB + Pose))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
3D Action RecognitiononNTU RGB+D
Accuracy (CS)· uses extra data· 2024-07-22
93.5
best: 94.3 (Hulk(Finetune, ViT-L))
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
3D Action RecognitiononNTU RGB+D
Accuracy (CV)· uses extra data· 2024-07-22
97.4
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706
3D Action RecognitiononNTU RGB+D
Ensembled Modalities· uses extra data· 2024-07-22
6
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition arXiv:2407.15706