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/P3D

P3D

Reported on 13 benchmarks across 7 tasks · 2 papers · 9 SOTA

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

Methodology4 results

3DonDeepLesion
Sensitivity· 2022-01-05
88.55
SOTA
Advancing 3D Medical Image Analysis with Variable Dimension Transform based Supervised 3D Pre-training arXiv:2201.01426
2D ClassificationonDeepLesion
Sensitivity· 2022-01-05
88.55
SOTA
Advancing 3D Medical Image Analysis with Variable Dimension Transform based Supervised 3D Pre-training arXiv:2201.01426
2D Object DetectiononDeepLesion
Sensitivity· 2022-01-05
88.55
SOTA
Advancing 3D Medical Image Analysis with Variable Dimension Transform based Supervised 3D Pre-training arXiv:2201.01426
16konDeepLesion
Sensitivity· 2022-01-05
88.55
SOTA
Advancing 3D Medical Image Analysis with Variable Dimension Transform based Supervised 3D Pre-training arXiv:2201.01426

Robots4 results

Activity RecognitiononSports-1M
Clip Hit@1· 2017-11-28
47.9
best: 57 (R[2+1]D-RGB-32frame)
SOTA
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks arXiv:1711.10305
Activity RecognitiononActivityNet
mAP· 2017-11-28
78.9
best: 96.9 (Text4Vis (w/ ViT-L))
SOTA
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks arXiv:1711.10305
Activity RecognitiononSports-1M
Video hit@1 · 2017-11-28
66.4
best: 75.5 (ip-CSN-152 (RGB))
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks arXiv:1711.10305
Activity RecognitiononSports-1M
Video hit@5· 2017-11-28
87.4
best: 92.8 (ip-CSN-152 (RGB))
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks arXiv:1711.10305

Time Series4 results

Action RecognitiononSports-1M
Clip Hit@1· 2017-11-28
47.9
best: 57 (R[2+1]D-RGB-32frame)
SOTA
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks arXiv:1711.10305
Action RecognitiononActivityNet
mAP· 2017-11-28
78.9
best: 96.9 (Text4Vis (w/ ViT-L))
SOTA
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks arXiv:1711.10305
Action RecognitiononSports-1M
Video hit@1 · 2017-11-28
66.4
best: 75.5 (ip-CSN-152 (RGB))
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks arXiv:1711.10305
Action RecognitiononSports-1M
Video hit@5· 2017-11-28
87.4
best: 92.8 (ip-CSN-152 (RGB))
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks arXiv:1711.10305

Computer Vision1 result

Object DetectiononDeepLesion
Sensitivity· 2022-01-05
88.55
SOTA
Advancing 3D Medical Image Analysis with Variable Dimension Transform based Supervised 3D Pre-training arXiv:2201.01426