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/Singularity

Singularity

Reported on 22 benchmarks across 3 tasks · 2 papers · 6 SOTA

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

Computer Vision18 results

VideoonDiDeMo
text-to-video R@1· uses extra data· 2022-06-07
53.9
best: 74.2 (InternVideo2-6B)
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
VideoonDiDeMo
text-to-video R@10· uses extra data· 2022-06-07
86.9
best: 94.2 (vid-TLDR (UMT-L))
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
VideoonDiDeMo
text-to-video R@5· uses extra data· 2022-06-07
79.4
best: 91.2 (vid-TLDR (UMT-L))
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
Video RetrievalonDiDeMo
text-to-video R@1· uses extra data· 2022-06-07
53.9
best: 74.2 (InternVideo2-6B)
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
Video RetrievalonDiDeMo
text-to-video R@10· uses extra data· 2022-06-07
86.9
best: 94.2 (vid-TLDR (UMT-L))
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
Video RetrievalonDiDeMo
text-to-video R@5· uses extra data· 2022-06-07
79.4
best: 91.2 (vid-TLDR (UMT-L))
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
VideoonMSR-VTT-1kA
text-to-video R@1· uses extra data· 2022-06-07
41.5
best: 62.9 (HunYuan_tvr (huge))
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
VideoonMSR-VTT-1kA
text-to-video R@10· uses extra data· 2022-06-07
77
best: 90.8 (HunYuan_tvr (huge))
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
VideoonMSR-VTT-1kA
text-to-video R@5· uses extra data· 2022-06-07
68.7
best: 84.5 (HunYuan_tvr (huge))
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
VideoonActivityNet
text-to-video R@1· uses extra data· 2022-06-07
47.1
best: 74.1 (InternVideo2-6B)
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
VideoonActivityNet
text-to-video R@10· uses extra data· 2022-06-07
85.5
best: 96.1 (GRAM)
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
VideoonActivityNet
text-to-video R@5· uses extra data· 2022-06-07
75.5
best: 90.9 (VAST)
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
Video RetrievalonMSR-VTT-1kA
text-to-video R@1· uses extra data· 2022-06-07
41.5
best: 62.9 (HunYuan_tvr (huge))
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
Video RetrievalonMSR-VTT-1kA
text-to-video R@10· uses extra data· 2022-06-07
77
best: 90.8 (HunYuan_tvr (huge))
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
Video RetrievalonMSR-VTT-1kA
text-to-video R@5· uses extra data· 2022-06-07
68.7
best: 84.5 (HunYuan_tvr (huge))
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
Video RetrievalonActivityNet
text-to-video R@1· uses extra data· 2022-06-07
47.1
best: 74.1 (InternVideo2-6B)
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
Video RetrievalonActivityNet
text-to-video R@10· uses extra data· 2022-06-07
85.5
best: 96.1 (GRAM)
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
Video RetrievalonActivityNet
text-to-video R@5· uses extra data· 2022-06-07
75.5
best: 90.9 (VAST)
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428

Reasoning4 results

Video Question AnsweringonRoadTextVQA
ACCURACY· uses extra data· 2023-07-08
24.62
best: 29.58 (GIT)
Reading Between the Lanes: Text VideoQA on the Road arXiv:2307.03948
Video Question AnsweringonActivityNet-QA
Accuracy· uses extra data· 2022-06-07
43.1
best: 61.6 (Tarsier (34B))
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
Video Question AnsweringonMSRVTT-QA
Accuracy· 2022-06-07
43.5
best: 72.4 (Flash-VStream)
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
Video Question AnsweringonMSRVTT-MC
Accuracy· 2022-06-07
92.1
best: 97.6 (VIOLETv2)
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428