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/ACT

ACT

Reported on 36 benchmarks across 6 tasks · 3 papers · 8 SOTA

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

Computer Vision27 results

Shape Representation Of 3D Point CloudsonModelNet40 10-way (20-shot)
Overall Accuracy· uses extra data· 2022-12-16
95.6
best: 96.5 (ReCon++)
SOTA
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
Shape Representation Of 3D Point CloudsonModelNet40 10-way (10-shot)
Overall Accuracy· uses extra data· 2022-12-16
93.3
best: 95 (Point-JEPA)
SOTA
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
3D Point Cloud ClassificationonModelNet40 10-way (20-shot)
Overall Accuracy· uses extra data· 2022-12-16
95.6
best: 96.5 (ReCon++)
SOTA
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
3D Point Cloud ClassificationonModelNet40 10-way (10-shot)
Overall Accuracy· uses extra data· 2022-12-16
93.3
best: 95 (Point-JEPA)
SOTA
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
3D Point Cloud ReconstructiononModelNet40 10-way (20-shot)
Overall Accuracy· uses extra data· 2022-12-16
95.6
best: 96.5 (ReCon++)
SOTA
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
3D Point Cloud ReconstructiononModelNet40 10-way (10-shot)
Overall Accuracy· uses extra data· 2022-12-16
93.3
best: 95 (Point-JEPA)
SOTA
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
Shape Representation Of 3D Point CloudsonScanObjectNN
Overall Accuracy· uses extra data· 2022-12-16
89.17
best: 97.2 (OmniVec2)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
Shape Representation Of 3D Point CloudsonModelNet40 10-way (20-shot)
Standard Deviation· uses extra data· 2022-12-16
2.8
best: 13.5 (PointNet)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
Shape Representation Of 3D Point CloudsonModelNet40 5-way (10-shot)
Overall Accuracy· uses extra data· 2022-12-16
96.8
best: 98 (PointGPT)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
Shape Representation Of 3D Point CloudsonModelNet40 5-way (10-shot)
Standard Deviation· uses extra data· 2022-12-16
2.3
best: 16 (PointNet++)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
Shape Representation Of 3D Point CloudsonModelNet40 10-way (10-shot)
Standard Deviation· uses extra data· 2022-12-16
4
best: 13.5 (PointNet)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
Shape Representation Of 3D Point CloudsonModelNet40 5-way (20-shot)
Overall Accuracy· uses extra data· 2022-12-16
98
best: 99.5 (ReCon++)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
Shape Representation Of 3D Point CloudsonModelNet40 5-way (20-shot)
Standard Deviation· uses extra data· 2022-12-16
1.4
best: 15.5 (PointNet)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
3D Point Cloud ClassificationonScanObjectNN
Overall Accuracy· uses extra data· 2022-12-16
89.17
best: 97.2 (OmniVec2)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
3D Point Cloud ClassificationonModelNet40 10-way (20-shot)
Standard Deviation· uses extra data· 2022-12-16
2.8
best: 13.5 (PointNet)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
3D Point Cloud ClassificationonModelNet40 5-way (10-shot)
Overall Accuracy· uses extra data· 2022-12-16
96.8
best: 98 (PointGPT)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
3D Point Cloud ClassificationonModelNet40 5-way (10-shot)
Standard Deviation· uses extra data· 2022-12-16
2.3
best: 16 (PointNet++)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
3D Point Cloud ClassificationonModelNet40 10-way (10-shot)
Standard Deviation· uses extra data· 2022-12-16
4
best: 13.5 (PointNet)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
3D Point Cloud ClassificationonModelNet40 5-way (20-shot)
Overall Accuracy· uses extra data· 2022-12-16
98
best: 99.5 (ReCon++)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
3D Point Cloud ClassificationonModelNet40 5-way (20-shot)
Standard Deviation· uses extra data· 2022-12-16
1.4
best: 15.5 (PointNet)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
3D Point Cloud ReconstructiononScanObjectNN
Overall Accuracy· uses extra data· 2022-12-16
89.17
best: 97.2 (OmniVec2)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
3D Point Cloud ReconstructiononModelNet40 10-way (20-shot)
Standard Deviation· uses extra data· 2022-12-16
2.8
best: 13.5 (PointNet)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
3D Point Cloud ReconstructiononModelNet40 5-way (10-shot)
Overall Accuracy· uses extra data· 2022-12-16
96.8
best: 98 (PointGPT)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
3D Point Cloud ReconstructiononModelNet40 5-way (10-shot)
Standard Deviation· uses extra data· 2022-12-16
2.3
best: 16 (PointNet++)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
3D Point Cloud ReconstructiononModelNet40 10-way (10-shot)
Standard Deviation· uses extra data· 2022-12-16
4
best: 13.5 (PointNet)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
3D Point Cloud ReconstructiononModelNet40 5-way (20-shot)
Overall Accuracy· uses extra data· 2022-12-16
98
best: 99.5 (ReCon++)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320
3D Point Cloud ReconstructiononModelNet40 5-way (20-shot)
Standard Deviation· uses extra data· 2022-12-16
1.4
best: 15.5 (PointNet)
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?arXiv:2212.08320

Methodology4 results

Domain AdaptationonMarket to Duke
mAP· 2019-12-03
54.5
best: 74.8 (CORE-ReID)
SOTA
Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification arXiv:1912.01349
Domain AdaptationonMarket to Duke
rank-1· 2019-12-03
72.4
best: 85 (CCTSE)
Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification arXiv:1912.01349
Domain AdaptationonDuke to Market
mAP· 2019-12-03
60.6
best: 84.4 (CORE-ReID)
Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification arXiv:1912.01349
Domain AdaptationonDuke to Market
rank-1· 2019-12-03
80.5
best: 93.6 (CORE-ReID)
Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification arXiv:1912.01349

Other4 results

Unsupervised Domain AdaptationonMarket to Duke
mAP· 2019-12-03
54.5
best: 74.8 (CORE-ReID)
SOTA
Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification arXiv:1912.01349
Unsupervised Domain AdaptationonMarket to Duke
rank-1· 2019-12-03
72.4
best: 85 (CCTSE)
Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification arXiv:1912.01349
Unsupervised Domain AdaptationonDuke to Market
mAP· 2019-12-03
60.6
best: 84.4 (CORE-ReID)
Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification arXiv:1912.01349
Unsupervised Domain AdaptationonDuke to Market
rank-1· 2019-12-03
80.5
best: 93.6 (CORE-ReID)
Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identification arXiv:1912.01349

Robots1 result

Robot ManipulationonThe COLOSSEUM
Average decrease average across all perturbations· 2023-04-23
-61.8
best: -4.3 (SAM2Act)
Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware arXiv:2304.13705