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/FlowNet2

FlowNet2

Reported on 49 benchmarks across 10 tasks · 1 paper · 43 SOTA

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

Computer Vision24 results

VideoonJHMDB Pose Tracking
PCK@0.1· 2016-12-06
45.2
best: 58.4 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
VideoonJHMDB Pose Tracking
PCK@0.2· 2016-12-06
62.9
best: 78.1 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
VideoonJHMDB Pose Tracking
PCK@0.3· 2016-12-06
73.5
best: 85.9 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
VideoonJHMDB Pose Tracking
PCK@0.4· 2016-12-06
80.6
best: 89.8 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
VideoonJHMDB Pose Tracking
PCK@0.5· 2016-12-06
85.5
best: 92.4 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Temporal Action LocalizationonJHMDB Pose Tracking
PCK@0.1· 2016-12-06
45.2
best: 58.4 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Temporal Action LocalizationonJHMDB Pose Tracking
PCK@0.2· 2016-12-06
62.9
best: 78.1 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Temporal Action LocalizationonJHMDB Pose Tracking
PCK@0.3· 2016-12-06
73.5
best: 85.9 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Temporal Action LocalizationonJHMDB Pose Tracking
PCK@0.4· 2016-12-06
80.6
best: 89.8 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Temporal Action LocalizationonJHMDB Pose Tracking
PCK@0.5· 2016-12-06
85.5
best: 92.4 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Action LocalizationonJHMDB Pose Tracking
PCK@0.1· 2016-12-06
45.2
best: 58.4 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Action LocalizationonJHMDB Pose Tracking
PCK@0.2· 2016-12-06
62.9
best: 78.1 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Action LocalizationonJHMDB Pose Tracking
PCK@0.3· 2016-12-06
73.5
best: 85.9 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Action LocalizationonJHMDB Pose Tracking
PCK@0.4· 2016-12-06
80.6
best: 89.8 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Action LocalizationonJHMDB Pose Tracking
PCK@0.5· 2016-12-06
85.5
best: 92.4 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Optical Flow EstimationonSintel-clean
Average End-Point Error· 2016-12-06
3.96
best: 0.963 (MEMFOF-L)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Optical Flow EstimationonKITTI 2015 (train)
EPE· 2016-12-06
10.08
best: 13.17 (HD3)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Optical Flow EstimationonKITTI 2015 (train)
F1-all· 2016-12-06
30
best: 33.7 (PWC-Net)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Optical Flow EstimationonSpring
1px total· 2016-12-06
6.71
best: 82.265 (PWCNet)
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Dense Pixel Correspondence EstimationonHPatches
Viewpoint I AEPE· 2016-12-06
5.99
best: 36.94 (SPyNet)
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Dense Pixel Correspondence EstimationonHPatches
Viewpoint II AEPE· 2016-12-06
15.55
best: 50.92 (SPyNet)
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Dense Pixel Correspondence EstimationonHPatches
Viewpoint III AEPE· 2016-12-06
17.09
best: 54.29 (SPyNet)
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Dense Pixel Correspondence EstimationonHPatches
Viewpoint IV AEPE· 2016-12-06
22.13
best: 62.6 (SPyNet)
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Dense Pixel Correspondence EstimationonHPatches
Viewpoint V AEPE· 2016-12-06
30.68
best: 72.57 (SPyNet)
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925

Time Series10 results

Action DetectiononJHMDB Pose Tracking
PCK@0.1· 2016-12-06
45.2
best: 58.4 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Action DetectiononJHMDB Pose Tracking
PCK@0.2· 2016-12-06
62.9
best: 78.1 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Action DetectiononJHMDB Pose Tracking
PCK@0.3· 2016-12-06
73.5
best: 85.9 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Action DetectiononJHMDB Pose Tracking
PCK@0.4· 2016-12-06
80.6
best: 89.8 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Action DetectiononJHMDB Pose Tracking
PCK@0.5· 2016-12-06
85.5
best: 92.4 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Action RecognitiononJHMDB Pose Tracking
PCK@0.1· 2016-12-06
45.2
best: 58.4 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Action RecognitiononJHMDB Pose Tracking
PCK@0.2· 2016-12-06
62.9
best: 78.1 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Action RecognitiononJHMDB Pose Tracking
PCK@0.3· 2016-12-06
73.5
best: 85.9 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Action RecognitiononJHMDB Pose Tracking
PCK@0.4· 2016-12-06
80.6
best: 89.8 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Action RecognitiononJHMDB Pose Tracking
PCK@0.5· 2016-12-06
85.5
best: 92.4 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925

Methodology5 results

Zero-Shot LearningonJHMDB Pose Tracking
PCK@0.1· 2016-12-06
45.2
best: 58.4 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Zero-Shot LearningonJHMDB Pose Tracking
PCK@0.2· 2016-12-06
62.9
best: 78.1 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Zero-Shot LearningonJHMDB Pose Tracking
PCK@0.3· 2016-12-06
73.5
best: 85.9 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Zero-Shot LearningonJHMDB Pose Tracking
PCK@0.4· 2016-12-06
80.6
best: 89.8 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Zero-Shot LearningonJHMDB Pose Tracking
PCK@0.5· 2016-12-06
85.5
best: 92.4 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925

Robots5 results

Activity RecognitiononJHMDB Pose Tracking
PCK@0.1· 2016-12-06
45.2
best: 58.4 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Activity RecognitiononJHMDB Pose Tracking
PCK@0.2· 2016-12-06
62.9
best: 78.1 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Activity RecognitiononJHMDB Pose Tracking
PCK@0.3· 2016-12-06
73.5
best: 85.9 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Activity RecognitiononJHMDB Pose Tracking
PCK@0.4· 2016-12-06
80.6
best: 89.8 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
Activity RecognitiononJHMDB Pose Tracking
PCK@0.5· 2016-12-06
85.5
best: 92.4 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925

Natural Language Processing5 results

3D Action RecognitiononJHMDB Pose Tracking
PCK@0.1· 2016-12-06
45.2
best: 58.4 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
3D Action RecognitiononJHMDB Pose Tracking
PCK@0.2· 2016-12-06
62.9
best: 78.1 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
3D Action RecognitiononJHMDB Pose Tracking
PCK@0.3· 2016-12-06
73.5
best: 85.9 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
3D Action RecognitiononJHMDB Pose Tracking
PCK@0.4· 2016-12-06
80.6
best: 89.8 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925
3D Action RecognitiononJHMDB Pose Tracking
PCK@0.5· 2016-12-06
85.5
best: 92.4 (mgPFF+ft 1st)
SOTA
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks arXiv:1612.01925