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/TPS

TPS

Reported on 25 benchmarks across 5 tasks · 2 papers · 22 SOTA

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

Computer Vision11 results

Image ManipulationonLRS2
LPIPS (S1)· 2021-09-13
0.12
SOTA
Image Shape Manipulation from a Single Augmented Training Sample arXiv:2109.06151
Image ManipulationonLRS2
LPIPS (S2)· 2021-09-13
0.21
SOTA
Image Shape Manipulation from a Single Augmented Training Sample arXiv:2109.06151
Image ManipulationonLRS2
LPIPS (S3)· 2021-09-13
0.1
SOTA
Image Shape Manipulation from a Single Augmented Training Sample arXiv:2109.06151
Image ManipulationonLRS2
LPIPS (S4)· 2021-09-13
0.22
SOTA
Image Shape Manipulation from a Single Augmented Training Sample arXiv:2109.06151
Image ManipulationonLRS2
LPIPS (S5)· 2021-09-13
0.14
SOTA
Image Shape Manipulation from a Single Augmented Training Sample arXiv:2109.06151
Image ManipulationonLRS2
SIFID (S1)· 2021-09-13
0.07
SOTA
Image Shape Manipulation from a Single Augmented Training Sample arXiv:2109.06151
Image ManipulationonLRS2
SIFID (S2)· 2021-09-13
0.12
SOTA
Image Shape Manipulation from a Single Augmented Training Sample arXiv:2109.06151
Image ManipulationonLRS2
SIFID (S3)· 2021-09-13
0.04
SOTA
Image Shape Manipulation from a Single Augmented Training Sample arXiv:2109.06151
Image ManipulationonLRS2
SIFID (S4)· 2021-09-13
0.12
SOTA
Image Shape Manipulation from a Single Augmented Training Sample arXiv:2109.06151
Image ManipulationonLRS2
SIFID (S5)· 2021-09-13
0.06
SOTA
Image Shape Manipulation from a Single Augmented Training Sample arXiv:2109.06151
VideoonKinetics-400
Acc@1· 2022-07-27
82.5
best: 93.6 (OmniVec2)
Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition arXiv:2207.13259

Medical10 results

Image GenerationonLRS2
LPIPS (S1)· 2021-09-13
0.12
SOTA
Image Shape Manipulation from a Single Augmented Training Sample arXiv:2109.06151
Image GenerationonLRS2
LPIPS (S2)· 2021-09-13
0.21
SOTA
Image Shape Manipulation from a Single Augmented Training Sample arXiv:2109.06151
Image GenerationonLRS2
LPIPS (S3)· 2021-09-13
0.1
SOTA
Image Shape Manipulation from a Single Augmented Training Sample arXiv:2109.06151
Image GenerationonLRS2
LPIPS (S4)· 2021-09-13
0.22
SOTA
Image Shape Manipulation from a Single Augmented Training Sample arXiv:2109.06151
Image GenerationonLRS2
LPIPS (S5)· 2021-09-13
0.14
SOTA
Image Shape Manipulation from a Single Augmented Training Sample arXiv:2109.06151
Image GenerationonLRS2
SIFID (S1)· 2021-09-13
0.07
SOTA
Image Shape Manipulation from a Single Augmented Training Sample arXiv:2109.06151
Image GenerationonLRS2
SIFID (S2)· 2021-09-13
0.12
SOTA
Image Shape Manipulation from a Single Augmented Training Sample arXiv:2109.06151
Image GenerationonLRS2
SIFID (S3)· 2021-09-13
0.04
SOTA
Image Shape Manipulation from a Single Augmented Training Sample arXiv:2109.06151
Image GenerationonLRS2
SIFID (S4)· 2021-09-13
0.12
SOTA
Image Shape Manipulation from a Single Augmented Training Sample arXiv:2109.06151
Image GenerationonLRS2
SIFID (S5)· 2021-09-13
0.06
SOTA
Image Shape Manipulation from a Single Augmented Training Sample arXiv:2109.06151

Robots2 results

Activity RecognitiononSomething-Something V1
Top 1 Accuracy· 2022-07-27
58.3
best: 70 (InternVideo)
SOTA
Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition arXiv:2207.13259
Activity RecognitiononSomething-Something V2
Top-1 Accuracy· 2022-07-27
69.8
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition arXiv:2207.13259

Time Series2 results

Action RecognitiononSomething-Something V1
Top 1 Accuracy· 2022-07-27
58.3
best: 70 (InternVideo)
SOTA
Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition arXiv:2207.13259
Action RecognitiononSomething-Something V2
Top-1 Accuracy· 2022-07-27
69.8
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition arXiv:2207.13259