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/TACo

TACo

Reported on 45 benchmarks across 7 tasks · 1 paper · 9 SOTA

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

Computer Vision44 results

VideoonYouCook2
text-to-video R@1· uses extra data· 2021-08-23
29.6
best: 50.4 (VAST)
SOTA
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
VideoonYouCook2
text-to-video R@10· uses extra data· 2021-08-23
72.7
best: 80.8 (VAST)
SOTA
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
VideoonYouCook2
text-to-video R@5· uses extra data· 2021-08-23
59.7
best: 74.3 (VAST)
SOTA
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Video RetrievalonYouCook2
text-to-video R@1· uses extra data· 2021-08-23
29.6
best: 50.4 (VAST)
SOTA
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Video RetrievalonYouCook2
text-to-video R@10· uses extra data· 2021-08-23
72.7
best: 80.8 (VAST)
SOTA
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Video RetrievalonYouCook2
text-to-video R@5· uses extra data· 2021-08-23
59.7
best: 74.3 (VAST)
SOTA
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Zero-Shot Video RetrievalonYouCook2
text-to-video R@1· 2021-08-23
19.9
best: 26.1 (OmniVec2)
SOTA
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Zero-Shot Video RetrievalonYouCook2
text-to-video R@10· 2021-08-23
55.7
best: 70.8 (OmniVec2)
SOTA
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Zero-Shot Video RetrievalonYouCook2
text-to-video R@5· 2021-08-23
43.2
best: 54.1 (OmniVec2)
SOTA
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
VideoonCrossTask
Recall· uses extra data· 2021-08-23
42.5
best: 47.3 (VideoCLIP)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
VideoonMSR-VTT-1kA
text-to-video Median Rank· 2021-08-23
4
best: 13 (JSFusion)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
VideoonMSR-VTT-1kA
text-to-video R@1· 2021-08-23
28.4
best: 62.9 (HunYuan_tvr (huge))
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
VideoonMSR-VTT-1kA
text-to-video R@10· 2021-08-23
71.2
best: 90.8 (HunYuan_tvr (huge))
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
VideoonMSR-VTT-1kA
text-to-video R@5· 2021-08-23
57.8
best: 84.5 (HunYuan_tvr (huge))
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
VideoonActivityNet
text-to-video Median Rank· uses extra data· 2021-08-23
3
best: 6 (Collaborative Experts)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
VideoonActivityNet
text-to-video R@1· uses extra data· 2021-08-23
30.4
best: 74.1 (InternVideo2-6B)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
VideoonActivityNet
text-to-video R@5· uses extra data· 2021-08-23
61.2
best: 90.9 (VAST)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
VideoonActivityNet
text-to-video R@50· uses extra data· 2021-08-23
93.4
best: 98.2 (CLIP4Clip)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
VideoonYouCook2
text-to-video Median Rank· uses extra data· 2021-08-23
4
best: 77 (Satar et al.)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
VideoonMSR-VTT
text-to-video Median Rank· uses extra data· 2021-08-23
5
best: 55 (C+LSTM+SA+FC7)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
VideoonMSR-VTT
text-to-video R@1· uses extra data· 2021-08-23
24.8
best: 64 (GRAM)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
VideoonMSR-VTT
text-to-video R@10· uses extra data· 2021-08-23
64
best: 89.6 (VAST)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
VideoonMSR-VTT
text-to-video R@5· uses extra data· 2021-08-23
52.1
best: 84.3 (VAST)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Temporal Action LocalizationonCrossTask
Recall· uses extra data· 2021-08-23
42.5
best: 47.3 (VideoCLIP)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Action LocalizationonCrossTask
Recall· uses extra data· 2021-08-23
42.5
best: 47.3 (VideoCLIP)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Action LocalizationonCOIN
Frame accuracy· 2021-08-23
68.4
best: 72.8 (UnLoc-L)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Video RetrievalonMSR-VTT-1kA
text-to-video Median Rank· 2021-08-23
4
best: 13 (JSFusion)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Video RetrievalonMSR-VTT-1kA
text-to-video R@1· 2021-08-23
28.4
best: 62.9 (HunYuan_tvr (huge))
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Video RetrievalonMSR-VTT-1kA
text-to-video R@10· 2021-08-23
71.2
best: 90.8 (HunYuan_tvr (huge))
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Video RetrievalonMSR-VTT-1kA
text-to-video R@5· 2021-08-23
57.8
best: 84.5 (HunYuan_tvr (huge))
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Video RetrievalonActivityNet
text-to-video Median Rank· uses extra data· 2021-08-23
3
best: 6 (Collaborative Experts)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Video RetrievalonActivityNet
text-to-video R@1· uses extra data· 2021-08-23
30.4
best: 74.1 (InternVideo2-6B)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Video RetrievalonActivityNet
text-to-video R@5· uses extra data· 2021-08-23
61.2
best: 90.9 (VAST)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Video RetrievalonActivityNet
text-to-video R@50· uses extra data· 2021-08-23
93.4
best: 98.2 (CLIP4Clip)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Video RetrievalonYouCook2
text-to-video Median Rank· uses extra data· 2021-08-23
4
best: 77 (Satar et al.)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Video RetrievalonMSR-VTT
text-to-video Median Rank· uses extra data· 2021-08-23
5
best: 55 (C+LSTM+SA+FC7)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Video RetrievalonMSR-VTT
text-to-video R@1· uses extra data· 2021-08-23
24.8
best: 64 (GRAM)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Video RetrievalonMSR-VTT
text-to-video R@10· uses extra data· 2021-08-23
64
best: 89.6 (VAST)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Video RetrievalonMSR-VTT
text-to-video R@5· uses extra data· 2021-08-23
52.1
best: 84.3 (VAST)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Action SegmentationonCOIN
Frame accuracy· 2021-08-23
68.4
best: 72.8 (UnLoc-L)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Zero-Shot Video RetrievalonMSR-VTT
text-to-video R@1· 2021-08-23
9.8
best: 55.9 (InternVideo2-6B)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Zero-Shot Video RetrievalonMSR-VTT
text-to-video R@10· 2021-08-23
33.4
best: 85.1 (InternVideo2-6B)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Zero-Shot Video RetrievalonMSR-VTT
text-to-video R@5· 2021-08-23
25
best: 78.3 (InternVideo2-6B)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980
Zero-Shot Video RetrievalonYouCook2
text-to-video Mean Rank· 2021-08-23
8
best: 13 (VATT-MBS)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980

Methodology1 result

Zero-Shot LearningonCrossTask
Recall· uses extra data· 2021-08-23
42.5
best: 47.3 (VideoCLIP)
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment arXiv:2108.09980