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/MGN

MGN

Reported on 12 benchmarks across 3 tasks · 3 papers · 2 SOTA

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

Computer Vision11 results

Person Re-IdentificationonMarket-1501
Rank-1· 2018-04-04
95.7
best: 98 (st-ReID(RE, RK))
SOTA
Learning Discriminative Features with Multiple Granularities for Person Re-Identification arXiv:1804.01438
Person Re-IdentificationonDukeMTMC-reID
Rank-1· 2018-04-04
88.7
best: 95.6 (CTL Model (ResNet50, 256x128))
SOTA
Learning Discriminative Features with Multiple Granularities for Person Re-Identification arXiv:1804.01438
3D Shape ReconstructiononPix3D
CD· 2020-02-27
0.0836
best: 0.125 (AtlasNet)
Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image arXiv:2002.12212
Person Re-IdentificationonCUHK03-C
Rank-1· 2020-01-21
5.44
best: 17.04 (CaceNet)
Learning Diverse Features with Part-Level Resolution for Person Re-Identification arXiv:2001.07442
Person Re-IdentificationonCUHK03-C
mAP· 2020-01-21
4.2
best: 10.62 (CaceNet)
Learning Diverse Features with Part-Level Resolution for Person Re-Identification arXiv:2001.07442
Person Re-IdentificationonCUHK03-C
mINP· 2020-01-21
0.46
best: 2.09 (CaceNet)
Learning Diverse Features with Part-Level Resolution for Person Re-Identification arXiv:2001.07442
Person Re-IdentificationonMarket-1501-C
Rank-1· 2018-04-04
29.56
best: 53.19 (TransReID)
Learning Discriminative Features with Multiple Granularities for Person Re-Identification arXiv:1804.01438
Person Re-IdentificationonMarket-1501-C
mAP· 2018-04-04
9.72
best: 27.38 (TransReID)
Learning Discriminative Features with Multiple Granularities for Person Re-Identification arXiv:1804.01438
Person Re-IdentificationonMarket-1501-C
mINP· 2018-04-04
0.29
best: 1.98 (TransReID)
Learning Discriminative Features with Multiple Granularities for Person Re-Identification arXiv:1804.01438
Person Re-IdentificationonMarket-1501
mAP· 2018-04-04
86.9
best: 96.21 (Unsupervised Pre-training (ResNet101+RK))
Learning Discriminative Features with Multiple Granularities for Person Re-Identification arXiv:1804.01438
Person Re-IdentificationonDukeMTMC-reID
mAP· 2018-04-04
78.4
best: 97.1 (DenseIL)
Learning Discriminative Features with Multiple Granularities for Person Re-Identification arXiv:1804.01438

Methodology1 result

3DonPix3D
CD· 2020-02-27
0.0836
best: 0.125 (AtlasNet)
Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image arXiv:2002.12212