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/MIM

MIM

Reported on 16 benchmarks across 3 tasks · 2 papers · 6 SOTA

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

Computer Vision10 results

VideoonHuman3.6M
MAE· 2018-11-19
1782.8
best: 1120 (IAM4VP)
SOTA
Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics arXiv:1811.07490
VideoonHuman3.6M
MSE· 2018-11-19
429.9
best: 126 (IAM4VP)
SOTA
Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics arXiv:1811.07490
VideoonHuman3.6M
SSIM· 2018-11-19
0.79
best: 0.942 (IAM4VP)
SOTA
Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics arXiv:1811.07490
VideoonMoving MNIST
MAE· 2018-11-19
116.5
best: 41.96 (PredFormer)
Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics arXiv:1811.07490
VideoonMoving MNIST
MSE· 2018-11-19
52
best: 11.62 (PredFormer)
Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics arXiv:1811.07490
VideoonMoving MNIST
SSIM· 2018-11-19
0.874
best: 0.975 (MSPred)
Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics arXiv:1811.07490
Image ClassificationonCIFAR-10
Percentage correct· 2015-08-03
91.5
best: 99.5 (ViT-H/14)
On the Importance of Normalisation Layers in Deep Learning with Piecewise Linear Activation Units arXiv:1508.00330
Image ClassificationonCIFAR-100
Percentage correct· uses extra data· 2015-08-03
70.8
best: 96.08 (EffNet-L2 (SAM))
On the Importance of Normalisation Layers in Deep Learning with Piecewise Linear Activation Units arXiv:1508.00330
Image ClassificationonMNIST
Percentage error· 2015-08-03
0.4
best: 0.13 (Branching/Merging CNN + Homogeneous Vector Capsules)
On the Importance of Normalisation Layers in Deep Learning with Piecewise Linear Activation Units arXiv:1508.00330
Image ClassificationonSVHN
Percentage error· 2015-08-03
2
best: 1 (E2E-M3)
On the Importance of Normalisation Layers in Deep Learning with Piecewise Linear Activation Units arXiv:1508.00330

Time Series6 results

Video PredictiononHuman3.6M
MAE· 2018-11-19
1782.8
best: 1120 (IAM4VP)
SOTA
Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics arXiv:1811.07490
Video PredictiononHuman3.6M
MSE· 2018-11-19
429.9
best: 126 (IAM4VP)
SOTA
Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics arXiv:1811.07490
Video PredictiononHuman3.6M
SSIM· 2018-11-19
0.79
best: 0.942 (IAM4VP)
SOTA
Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics arXiv:1811.07490
Video PredictiononMoving MNIST
MAE· 2018-11-19
116.5
best: 41.96 (PredFormer)
Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics arXiv:1811.07490
Video PredictiononMoving MNIST
MSE· 2018-11-19
52
best: 11.62 (PredFormer)
Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics arXiv:1811.07490
Video PredictiononMoving MNIST
SSIM· 2018-11-19
0.874
best: 0.975 (MSPred)
Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics arXiv:1811.07490