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-temporal

Singularity-temporal

Reported on 15 benchmarks across 3 tasks · 1 paper · 15 SOTA

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

Computer Vision12 results

VideoonSSv2-template retrieval
text-to-video R@1· uses extra data· 2022-06-07
77.6
best: 90.8 (UMT-L (ViT-L/16))
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
VideoonSSv2-template retrieval
text-to-video R@10· uses extra data· 2022-06-07
98.9
best: 100 (UMT-L (ViT-L/16))
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
VideoonSSv2-template retrieval
text-to-video R@5· uses extra data· 2022-06-07
96
best: 100 (UMT-L (ViT-L/16))
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
VideoonSSv2-label retrieval
text-to-video R@1· uses extra data· 2022-06-07
47.4
best: 73.3 (UMT-L (ViT-L/16))
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
VideoonSSv2-label retrieval
text-to-video R@10· uses extra data· 2022-06-07
84
best: 96.6 (UMT-L (ViT-L/16))
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
VideoonSSv2-label retrieval
text-to-video R@5· uses extra data· 2022-06-07
75.9
best: 93.3 (vid-TLDR (UMT-L))
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
Video RetrievalonSSv2-template retrieval
text-to-video R@1· uses extra data· 2022-06-07
77.6
best: 90.8 (UMT-L (ViT-L/16))
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
Video RetrievalonSSv2-template retrieval
text-to-video R@10· uses extra data· 2022-06-07
98.9
best: 100 (UMT-L (ViT-L/16))
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
Video RetrievalonSSv2-template retrieval
text-to-video R@5· uses extra data· 2022-06-07
96
best: 100 (UMT-L (ViT-L/16))
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
Video RetrievalonSSv2-label retrieval
text-to-video R@1· uses extra data· 2022-06-07
47.4
best: 73.3 (UMT-L (ViT-L/16))
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
Video RetrievalonSSv2-label retrieval
text-to-video R@10· uses extra data· 2022-06-07
84
best: 96.6 (UMT-L (ViT-L/16))
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
Video RetrievalonSSv2-label retrieval
text-to-video R@5· uses extra data· 2022-06-07
75.9
best: 93.3 (vid-TLDR (UMT-L))
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428

Reasoning3 results

Video Question AnsweringonActivityNet-QA
Accuracy· uses extra data· 2022-06-07
44.1
best: 61.6 (Tarsier (34B))
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
Video Question AnsweringonMSRVTT-QA
Accuracy· 2022-06-07
43.9
best: 72.4 (Flash-VStream)
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428
Video Question AnsweringonMSRVTT-MC
Accuracy· 2022-06-07
93.7
best: 97.6 (VIOLETv2)
SOTA
Revealing Single Frame Bias for Video-and-Language Learning arXiv:2206.03428