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/VPN

VPN

Reported on 63 benchmarks across 13 tasks · 4 papers · 8 SOTA

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

Computer Vision31 results

VideoonNTU RGB+D 120
Accuracy (Cross-Subject)· uses extra data· 2020-07-06
86.3
best: 90.9 (ProtoGCN)
SOTA
VPN: Learning Video-Pose Embedding for Activities of Daily Living arXiv:2007.03056
Temporal Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Subject)· uses extra data· 2020-07-06
86.3
best: 90.9 (ProtoGCN)
SOTA
VPN: Learning Video-Pose Embedding for Activities of Daily Living arXiv:2007.03056
Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Subject)· uses extra data· 2020-07-06
86.3
best: 90.9 (ProtoGCN)
SOTA
VPN: Learning Video-Pose Embedding for Activities of Daily Living arXiv:2007.03056
VideoonNTU RGB+D 120
Accuracy (Cross-Setup)· uses extra data· 2020-07-06
87.8
best: 92.2 (ProtoGCN)
VPN: Learning Video-Pose Embedding for Activities of Daily Living arXiv:2007.03056
Temporal Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Setup)· uses extra data· 2020-07-06
87.8
best: 92.2 (ProtoGCN)
VPN: Learning Video-Pose Embedding for Activities of Daily Living arXiv:2007.03056
Action LocalizationonNTU RGB+D 120
Accuracy (Cross-Setup)· uses extra data· 2020-07-06
87.8
best: 92.2 (ProtoGCN)
VPN: Learning Video-Pose Embedding for Activities of Daily Living arXiv:2007.03056
VideoonDAVIS 2016
F-measure (Decay)· 2016-12-16
14.4
best: 27.2 (OFL)
Video Propagation Networks arXiv:1612.05478
VideoonDAVIS 2016
F-measure (Mean)· 2016-12-16
65.6
best: 94.7 (SwinB-DeAOT-L)
Video Propagation Networks arXiv:1612.05478
VideoonDAVIS 2016
F-measure (Recall)· 2016-12-16
69
best: 97.1 (STCN)
Video Propagation Networks arXiv:1612.05478
VideoonDAVIS 2016
J&F· 2016-12-16
67.9
best: 93.4 (ISVOS (BL30K, MS))
Video Propagation Networks arXiv:1612.05478
VideoonDAVIS 2016
Jaccard (Decay)· 2016-12-16
12.4
best: 28.9 (BVS)
Video Propagation Networks arXiv:1612.05478
VideoonDAVIS 2016
Jaccard (Mean)· 2016-12-16
70.2
best: 92.5 (ISVOS (BL30K, MS))
Video Propagation Networks arXiv:1612.05478
VideoonDAVIS 2016
Jaccard (Recall)· 2016-12-16
82.3
best: 98.1 (STCN)
Video Propagation Networks arXiv:1612.05478
Video Object SegmentationonDAVIS 2016
F-measure (Decay)· 2016-12-16
14.4
best: 27.2 (OFL)
Video Propagation Networks arXiv:1612.05478
Video Object SegmentationonDAVIS 2016
F-measure (Mean)· 2016-12-16
65.6
best: 94.7 (SwinB-DeAOT-L)
Video Propagation Networks arXiv:1612.05478
Video Object SegmentationonDAVIS 2016
F-measure (Recall)· 2016-12-16
69
best: 97.1 (STCN)
Video Propagation Networks arXiv:1612.05478
Video Object SegmentationonDAVIS 2016
J&F· 2016-12-16
67.9
best: 93.4 (ISVOS (BL30K, MS))
Video Propagation Networks arXiv:1612.05478
Video Object SegmentationonDAVIS 2016
Jaccard (Decay)· 2016-12-16
12.4
best: 28.9 (BVS)
Video Propagation Networks arXiv:1612.05478
Video Object SegmentationonDAVIS 2016
Jaccard (Mean)· 2016-12-16
70.2
best: 92.5 (ISVOS (BL30K, MS))
Video Propagation Networks arXiv:1612.05478
Video Object SegmentationonDAVIS 2016
Jaccard (Recall)· 2016-12-16
82.3
best: 98.1 (STCN)
Video Propagation Networks arXiv:1612.05478
Semi-Supervised Video Object SegmentationonDAVIS 2016
F-measure (Decay)· 2016-12-16
14.4
best: 27.2 (OFL)
Video Propagation Networks arXiv:1612.05478
Semi-Supervised Video Object SegmentationonDAVIS 2016
F-measure (Mean)· 2016-12-16
65.6
best: 94.7 (SwinB-DeAOT-L)
Video Propagation Networks arXiv:1612.05478
Semi-Supervised Video Object SegmentationonDAVIS 2016
F-measure (Recall)· 2016-12-16
69
best: 97.1 (STCN)
Video Propagation Networks arXiv:1612.05478
Semi-Supervised Video Object SegmentationonDAVIS 2016
J&F· 2016-12-16
67.9
best: 93.4 (ISVOS (BL30K, MS))
Video Propagation Networks arXiv:1612.05478
Semi-Supervised Video Object SegmentationonDAVIS 2016
Jaccard (Decay)· 2016-12-16
12.4
best: 28.9 (BVS)
Video Propagation Networks arXiv:1612.05478
Semi-Supervised Video Object SegmentationonDAVIS 2016
Jaccard (Mean)· 2016-12-16
70.2
best: 92.5 (ISVOS (BL30K, MS))
Video Propagation Networks arXiv:1612.05478
Semi-Supervised Video Object SegmentationonDAVIS 2016
Jaccard (Recall)· 2016-12-16
82.3
best: 98.1 (STCN)
Video Propagation Networks arXiv:1612.05478
VideoonKTH
Cond· 2016-10-03
10
Video Pixel Networks arXiv:1610.00527
VideoonKTH
PSNR· 2016-10-03
23.76
best: 29.85 (WAM)
Video Pixel Networks arXiv:1610.00527
VideoonKTH
Pred· 2016-10-03
20
best: 40 (Grid-keypoints)
Video Pixel Networks arXiv:1610.00527
VideoonKTH
SSIM· 2016-10-03
0.746
best: 0.951 (MSPred)
Video Pixel Networks arXiv:1610.00527

Playing Games18 results

Atari GamesonAtari 2600 Krull
Score· 2017-07-11
15930
best: 594540 (GDI-H3)
SOTA
Value Prediction Network arXiv:1707.03497
Video GamesonAtari 2600 Krull
Score· 2017-07-11
15930
best: 594540 (GDI-H3)
SOTA
Value Prediction Network arXiv:1707.03497
Atari GamesonAtari 2600 Ms. Pacman
Score· 2017-07-11
2689
best: 243401.1 (MuZero)
Value Prediction Network arXiv:1707.03497
Atari GamesonAtari 2600 Enduro
Score· 2017-07-11
382
best: 14330 (GDI-I3)
Value Prediction Network arXiv:1707.03497
Atari GamesonAtari 2600 Frostbite
Score· 2017-07-11
3811
best: 631378.53 (MuZero)
Value Prediction Network arXiv:1707.03497
Atari GamesonAtari 2600 Amidar
Score· 2017-07-11
641
best: 29660.08 (Agent57)
Value Prediction Network arXiv:1707.03497
Atari GamesonAtari 2600 Crazy Climber
Score· 2017-07-11
54119
best: 565909.85 (Agent57)
Value Prediction Network arXiv:1707.03497
Atari GamesonAtari 2600 Alien
Score· 2017-07-11
1429
best: 741812.63 (MuZero)
Value Prediction Network arXiv:1707.03497
Atari GamesonAtari 2600 Seaquest
Score· 2017-07-11
5628
best: 1000000 (GDI-H3(200M frames))
Value Prediction Network arXiv:1707.03497
Atari GamesonAtari 2600 Q*Bert
Score· 2017-07-11
14517
best: 580328.14 (Agent57)
Value Prediction Network arXiv:1707.03497
Video GamesonAtari 2600 Ms. Pacman
Score· 2017-07-11
2689
best: 243401.1 (MuZero)
Value Prediction Network arXiv:1707.03497
Video GamesonAtari 2600 Enduro
Score· 2017-07-11
382
best: 14330 (GDI-I3)
Value Prediction Network arXiv:1707.03497
Video GamesonAtari 2600 Frostbite
Score· 2017-07-11
3811
best: 631378.53 (MuZero)
Value Prediction Network arXiv:1707.03497
Video GamesonAtari 2600 Amidar
Score· 2017-07-11
641
best: 29660.08 (Agent57)
Value Prediction Network arXiv:1707.03497
Video GamesonAtari 2600 Crazy Climber
Score· 2017-07-11
54119
best: 565909.85 (Agent57)
Value Prediction Network arXiv:1707.03497
Video GamesonAtari 2600 Alien
Score· 2017-07-11
1429
best: 741812.63 (MuZero)
Value Prediction Network arXiv:1707.03497
Video GamesonAtari 2600 Seaquest
Score· 2017-07-11
5628
best: 1000000 (GDI-H3(200M frames))
Value Prediction Network arXiv:1707.03497
Video GamesonAtari 2600 Q*Bert
Score· 2017-07-11
14517
best: 580328.14 (Agent57)
Value Prediction Network arXiv:1707.03497

Time Series8 results

Action DetectiononNTU RGB+D 120
Accuracy (Cross-Subject)· uses extra data· 2020-07-06
86.3
best: 90.9 (ProtoGCN)
SOTA
VPN: Learning Video-Pose Embedding for Activities of Daily Living arXiv:2007.03056
Action DetectiononNTU RGB+D 120
Accuracy (Cross-Setup)· uses extra data· 2020-07-06
87.8
best: 92.2 (ProtoGCN)
VPN: Learning Video-Pose Embedding for Activities of Daily Living arXiv:2007.03056
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· uses extra data· 2020-07-06
87.8
best: 96.7 (DSCNet (RGB + Pose))
VPN: Learning Video-Pose Embedding for Activities of Daily Living arXiv:2007.03056
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· uses extra data· 2020-07-06
86.3
best: 95.6 (DSCNet (RGB + Pose))
VPN: Learning Video-Pose Embedding for Activities of Daily Living arXiv:2007.03056
Video PredictiononKTH
Cond· 2016-10-03
10
Video Pixel Networks arXiv:1610.00527
Video PredictiononKTH
PSNR· 2016-10-03
23.76
best: 29.85 (WAM)
Video Pixel Networks arXiv:1610.00527
Video PredictiononKTH
Pred· 2016-10-03
20
best: 40 (Grid-keypoints)
Video Pixel Networks arXiv:1610.00527
Video PredictiononKTH
SSIM· 2016-10-03
0.746
best: 0.951 (MSPred)
Video Pixel Networks arXiv:1610.00527

Methodology2 results

Zero-Shot LearningonNTU RGB+D 120
Accuracy (Cross-Subject)· uses extra data· 2020-07-06
86.3
best: 90.9 (ProtoGCN)
SOTA
VPN: Learning Video-Pose Embedding for Activities of Daily Living arXiv:2007.03056
Zero-Shot LearningonNTU RGB+D 120
Accuracy (Cross-Setup)· uses extra data· 2020-07-06
87.8
best: 92.2 (ProtoGCN)
VPN: Learning Video-Pose Embedding for Activities of Daily Living arXiv:2007.03056

Natural Language Processing2 results

3D Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· uses extra data· 2020-07-06
86.3
best: 90.9 (ProtoGCN)
SOTA
VPN: Learning Video-Pose Embedding for Activities of Daily Living arXiv:2007.03056
3D Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· uses extra data· 2020-07-06
87.8
best: 92.2 (ProtoGCN)
VPN: Learning Video-Pose Embedding for Activities of Daily Living arXiv:2007.03056

Robots2 results

Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)· uses extra data· 2020-07-06
87.8
best: 96.7 (DSCNet (RGB + Pose))
VPN: Learning Video-Pose Embedding for Activities of Daily Living arXiv:2007.03056
Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)· uses extra data· 2020-07-06
86.3
best: 95.6 (DSCNet (RGB + Pose))
VPN: Learning Video-Pose Embedding for Activities of Daily Living arXiv:2007.03056