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/CMCL

CMCL

Reported on 16 benchmarks across 3 tasks · 1 paper · 16 SOTA

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

Natural Language Processing10 results

Image CaptioningonAIC-ICC
BLEU· 2021-03-11
66.1
SOTA
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training arXiv:2103.06561
Image CaptioningonAIC-ICC
CIDEr· 2021-03-11
220.7
SOTA
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training arXiv:2103.06561
Image CaptioningonAIC-ICC
METEOR· 2021-03-11
41.1
SOTA
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training arXiv:2103.06561
Image CaptioningonAIC-ICC
ROUGE-L· 2021-03-11
71.9
SOTA
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training arXiv:2103.06561
Image-to-Text RetrievalonAIC-ICC
Recall@1· 2021-03-11
20.3
best: 33.7 (ERNIE-ViL2.0)
SOTA
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training arXiv:2103.06561
Image-to-Text RetrievalonAIC-ICC
Recall@10· 2021-03-11
45.6
best: 60 (ERNIE-ViL2.0)
SOTA
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training arXiv:2103.06561
Image-to-Text RetrievalonAIC-ICC
Recall@5· 2021-03-11
37
best: 52.1 (ERNIE-ViL2.0)
SOTA
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training arXiv:2103.06561
Image-to-Text RetrievalonRUC-CAS-WenLan
Recall@1· 2021-03-11
36.1
SOTA
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training arXiv:2103.06561
Image-to-Text RetrievalonRUC-CAS-WenLan
Recall@10· 2021-03-11
62.2
SOTA
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training arXiv:2103.06561
Image-to-Text RetrievalonRUC-CAS-WenLan
Recall@5· 2021-03-11
55.5
SOTA
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training arXiv:2103.06561

Computer Vision6 results

Image RetrievalonAIC-ICC
Recall@1· 2021-03-11
14.4
best: 19 (ERNIE-ViL2.0)
SOTA
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training arXiv:2103.06561
Image RetrievalonAIC-ICC
Recall@10· 2021-03-11
39.1
best: 43.5 (ERNIE-ViL2.0)
SOTA
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training arXiv:2103.06561
Image RetrievalonAIC-ICC
Recall@5· 2021-03-11
39.1
SOTA
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training arXiv:2103.06561
Image RetrievalonRUC-CAS-WenLan
Recall@1· 2021-03-11
36
SOTA
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training arXiv:2103.06561
Image RetrievalonRUC-CAS-WenLan
Recall@10· 2021-03-11
62.1
SOTA
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training arXiv:2103.06561
Image RetrievalonRUC-CAS-WenLan
Recall@5· 2021-03-11
55.4
SOTA
WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training arXiv:2103.06561