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/DAS

DAS

Reported on 20 benchmarks across 13 tasks · 4 papers · 8 SOTA

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

Computer Vision12 results

Object DetectiononMSCOCO
Average mAP· 2023-11-20
39.7
SOTA
DAS: A Deformable Attention to Capture Salient Information in CNNs arXiv:2311.12091
3D Multi-Person Pose Estimation (root-relative)onMuPoTS-3D
3DPCK· 2022-03-15
82.7
best: 89.6 (TDBU_Net)
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation arXiv:2203.07697
3D Human Pose EstimationonPanoptic
Average MPJPE (mm)· uses extra data· 2022-03-15
53.8
best: 135.4 (BMP)
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation arXiv:2203.07697
3D Human Pose EstimationonMuPoTS-3D
3DPCK· 2022-03-15
39.2
best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation arXiv:2203.07697
3D Human Pose EstimationonMuPoTS-3D
3DPCK· 2022-03-15
82.7
best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation arXiv:2203.07697
3D Multi-Person Pose Estimation (absolute)onMuPoTS-3D
3DPCK· 2022-03-15
39.2
best: 50.9 (POTR-3D)
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation arXiv:2203.07697
Pose EstimationonPanoptic
Average MPJPE (mm)· uses extra data· 2022-03-15
53.8
best: 135.4 (BMP)
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation arXiv:2203.07697
Pose EstimationonMuPoTS-3D
3DPCK· 2022-03-15
39.2
best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation arXiv:2203.07697
Pose EstimationonMuPoTS-3D
3DPCK· 2022-03-15
82.7
best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation arXiv:2203.07697
3D Multi-Person Pose EstimationonPanoptic
Average MPJPE (mm)· uses extra data· 2022-03-15
53.8
best: 135.4 (BMP)
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation arXiv:2203.07697
3D Multi-Person Pose EstimationonMuPoTS-3D
3DPCK· 2022-03-15
39.2
best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation arXiv:2203.07697
3D Multi-Person Pose EstimationonMuPoTS-3D
3DPCK· 2022-03-15
82.7
best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation arXiv:2203.07697

Methodology9 results

3DonMSCOCO
Average mAP· 2023-11-20
39.7
SOTA
DAS: A Deformable Attention to Capture Salient Information in CNNs arXiv:2311.12091
2D ClassificationonMSCOCO
Average mAP· 2023-11-20
39.7
SOTA
DAS: A Deformable Attention to Capture Salient Information in CNNs arXiv:2311.12091
2D Object DetectiononMSCOCO
Average mAP· 2023-11-20
39.7
SOTA
DAS: A Deformable Attention to Capture Salient Information in CNNs arXiv:2311.12091
16konMSCOCO
Average mAP· 2023-11-20
39.7
SOTA
DAS: A Deformable Attention to Capture Salient Information in CNNs arXiv:2311.12091
Continual PretrainingonACL-ARC
F1 (macro)· 2023-02-07
0.6936
SOTA
Continual Pre-training of Language Models arXiv:2302.03241
Continual PretrainingonSciERC
F1 (macro)· 2023-02-07
0.7093
SOTA
Continual Pre-training of Language Models arXiv:2302.03241
3DonPanoptic
Average MPJPE (mm)· uses extra data· 2022-03-15
53.8
best: 135.4 (BMP)
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation arXiv:2203.07697
3DonMuPoTS-3D
3DPCK· 2022-03-15
39.2
best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation arXiv:2203.07697
3DonMuPoTS-3D
3DPCK· 2022-03-15
82.7
best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation arXiv:2203.07697

Audio3 results

1 Image, 2*2 StitchionPanoptic
Average MPJPE (mm)· uses extra data· 2022-03-15
53.8
best: 135.4 (BMP)
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation arXiv:2203.07697
1 Image, 2*2 StitchionMuPoTS-3D
3DPCK· 2022-03-15
39.2
best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation arXiv:2203.07697
1 Image, 2*2 StitchionMuPoTS-3D
3DPCK· 2022-03-15
82.7
best: 89.9 (Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement)
Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation arXiv:2203.07697

Miscellaneous1 result

Interpretability Techniques for Deep LearningonCausalGym
Log odds-ratio (pythia-6.9b)· 2024-02-19
9.95
SOTA
CausalGym: Benchmarking causal interpretability methods on linguistic tasks arXiv:2402.12560