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/EMCL-Net

EMCL-Net

Reported on 50 benchmarks across 5 tasks · 1 paper

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

Computer Vision48 results

VideoonMSR-VTT-1kA
text-to-video Mean Rank· 2022-11-21
2
best: 28.2 (Collaborative Experts)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonMSR-VTT-1kA
text-to-video R@1· 2022-11-21
46.8
best: 62.9 (HunYuan_tvr (huge))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonMSR-VTT-1kA
text-to-video R@10· 2022-11-21
83.1
best: 90.8 (HunYuan_tvr (huge))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonMSR-VTT-1kA
text-to-video R@5· 2022-11-21
73.1
best: 84.5 (HunYuan_tvr (huge))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonMSR-VTT-1kA
video-to-text Mean Rank· 2022-11-21
2
best: 10.2 (CenterCLIP (ViT-B/16))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonMSR-VTT-1kA
video-to-text R@1· 2022-11-21
46.5
best: 64.8 (HunYuan_tvr (huge))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonMSR-VTT-1kA
video-to-text R@10· 2022-11-21
83.5
best: 91.1 (HunYuan_tvr (huge))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonMSR-VTT-1kA
video-to-text R@5· 2022-11-21
73.5
best: 783 (PIDRo)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonActivityNet
text-to-video Mean Rank· 2022-11-21
2
best: 23.1 (Collaborative Experts)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonActivityNet
text-to-video R@1· 2022-11-21
41.2
best: 74.1 (InternVideo2-6B)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonActivityNet
text-to-video R@5· 2022-11-21
72.7
best: 90.9 (VAST)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonActivityNet
video-to-text Mean Rank· 2022-11-21
2
best: 6.7 (DiffusionRet+QB-Norm)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonActivityNet
video-to-text R@1· 2022-11-21
42.7
best: 69.7 (InternVideo2-6B)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonActivityNet
video-to-text R@5· 2022-11-21
74
best: 89.1 (UMT-L (ViT-L/16))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonActivityNet
video-to-text R@50· 2022-11-21
98.3
best: 98.4 (EMCL-Net++)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonLSMDC
text-to-video R@1· 2022-11-21
23.9
best: 46.4 (InternVideo2-6B)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonLSMDC
text-to-video R@10· 2022-11-21
50.9
best: 92.8 (HunYuan_tvr (huge))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonLSMDC
text-to-video R@5· 2022-11-21
42.4
best: 80.1 (HunYuan_tvr (huge))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonLSMDC
video-to-text Mean Rank· 2022-11-21
12
best: 48.9 (HunYuan_tvr)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonLSMDC
video-to-text R@1· 2022-11-21
22.2
best: 46.7 (InternVideo2-6B)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonLSMDC
video-to-text R@10· 2022-11-21
49.2
best: 91.8 (HunYuan_tvr (huge))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
VideoonLSMDC
video-to-text R@5· 2022-11-21
40.6
best: 71.8 (HunYuan_tvr (huge))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video CaptioningonMSR-VTT
BLEU-4· 2022-11-21
45.3
best: 57.8 (mPLUG-2)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video CaptioningonMSR-VTT
CIDEr· 2022-11-21
54.6
best: 80 (mPLUG-2)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video CaptioningonMSR-VTT
METEOR· 2022-11-21
30.2
best: 38.7 (MV-GPT)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video CaptioningonMSR-VTT
ROUGE-L· 2022-11-21
63.2
best: 70.1 (mPLUG-2)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonMSR-VTT-1kA
text-to-video Mean Rank· 2022-11-21
2
best: 28.2 (Collaborative Experts)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonMSR-VTT-1kA
text-to-video R@1· 2022-11-21
46.8
best: 62.9 (HunYuan_tvr (huge))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonMSR-VTT-1kA
text-to-video R@10· 2022-11-21
83.1
best: 90.8 (HunYuan_tvr (huge))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonMSR-VTT-1kA
text-to-video R@5· 2022-11-21
73.1
best: 84.5 (HunYuan_tvr (huge))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonMSR-VTT-1kA
video-to-text Mean Rank· 2022-11-21
2
best: 10.2 (CenterCLIP (ViT-B/16))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonMSR-VTT-1kA
video-to-text R@1· 2022-11-21
46.5
best: 64.8 (HunYuan_tvr (huge))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonMSR-VTT-1kA
video-to-text R@10· 2022-11-21
83.5
best: 91.1 (HunYuan_tvr (huge))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonMSR-VTT-1kA
video-to-text R@5· 2022-11-21
73.5
best: 783 (PIDRo)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonActivityNet
text-to-video Mean Rank· 2022-11-21
2
best: 23.1 (Collaborative Experts)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonActivityNet
text-to-video R@1· 2022-11-21
41.2
best: 74.1 (InternVideo2-6B)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonActivityNet
text-to-video R@5· 2022-11-21
72.7
best: 90.9 (VAST)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonActivityNet
video-to-text Mean Rank· 2022-11-21
2
best: 6.7 (DiffusionRet+QB-Norm)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonActivityNet
video-to-text R@1· 2022-11-21
42.7
best: 69.7 (InternVideo2-6B)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonActivityNet
video-to-text R@5· 2022-11-21
74
best: 89.1 (UMT-L (ViT-L/16))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonActivityNet
video-to-text R@50· 2022-11-21
98.3
best: 98.4 (EMCL-Net++)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonLSMDC
text-to-video R@1· 2022-11-21
23.9
best: 46.4 (InternVideo2-6B)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonLSMDC
text-to-video R@10· 2022-11-21
50.9
best: 92.8 (HunYuan_tvr (huge))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonLSMDC
text-to-video R@5· 2022-11-21
42.4
best: 80.1 (HunYuan_tvr (huge))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonLSMDC
video-to-text Mean Rank· 2022-11-21
12
best: 48.9 (HunYuan_tvr)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonLSMDC
video-to-text R@1· 2022-11-21
22.2
best: 46.7 (InternVideo2-6B)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonLSMDC
video-to-text R@10· 2022-11-21
49.2
best: 91.8 (HunYuan_tvr (huge))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427
Video RetrievalonLSMDC
video-to-text R@5· 2022-11-21
40.6
best: 71.8 (HunYuan_tvr (huge))
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427

Natural Language Processing1 result

Visual Question Answering (VQA)onMSRVTT-QA
Accuracy· 2022-11-21
0.458
best: 0.496 (VLAB)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427

Reasoning1 result

Video Question AnsweringonMSRVTT-QA
Accuracy· 2022-11-21
45.8
best: 72.4 (Flash-VStream)
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations arXiv:2211.11427