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/E2E-TAD (SlowFast R50+TadTR)

E2E-TAD (SlowFast R50+TadTR)

Reported on 40 benchmarks across 4 tasks · 1 paper · 4 SOTA

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

Computer Vision30 results

VideoonActivityNet-1.3
mAP IOU@0.95· 2022-04-06
10.83
best: 10.85 (AdaTAD (VideoMAEv2-giant))
SOTA
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Temporal Action LocalizationonActivityNet-1.3
mAP IOU@0.95· 2022-04-06
10.83
best: 10.85 (AdaTAD (VideoMAEv2-giant))
SOTA
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Action LocalizationonActivityNet-1.3
mAP IOU@0.95· 2022-04-06
10.83
best: 10.85 (AdaTAD (VideoMAEv2-giant))
SOTA
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
VideoonActivityNet-1.3
mAP· 2022-04-06
35.1
best: 42.9 (RDFA-S6 (InternVideo2-6B))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
VideoonActivityNet-1.3
mAP IOU@0.5· 2022-04-06
50.47
best: 64.1 (RDFA-S6 (InternVideo2-6B))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
VideoonActivityNet-1.3
mAP IOU@0.75· 2022-04-06
35.99
best: 44 (RDFA-S6 (InternVideo2-6B))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
VideoonTHUMOS’14
Avg mAP (0.3:0.7)· 2022-04-06
54.2
best: 76.9 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
VideoonTHUMOS’14
mAP IOU@0.3· 2022-04-06
69.4
best: 89.7 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
VideoonTHUMOS’14
mAP IOU@0.4· 2022-04-06
64.3
best: 86.7 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
VideoonTHUMOS’14
mAP IOU@0.5· 2022-04-06
56
best: 80.9 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
VideoonTHUMOS’14
mAP IOU@0.6· 2022-04-06
46.4
best: 71 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
VideoonTHUMOS’14
mAP IOU@0.7· 2022-04-06
34.9
best: 56.1 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Temporal Action LocalizationonActivityNet-1.3
mAP· 2022-04-06
35.1
best: 42.9 (RDFA-S6 (InternVideo2-6B))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Temporal Action LocalizationonActivityNet-1.3
mAP IOU@0.5· 2022-04-06
50.47
best: 64.1 (RDFA-S6 (InternVideo2-6B))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Temporal Action LocalizationonActivityNet-1.3
mAP IOU@0.75· 2022-04-06
35.99
best: 44 (RDFA-S6 (InternVideo2-6B))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Temporal Action LocalizationonTHUMOS’14
Avg mAP (0.3:0.7)· 2022-04-06
54.2
best: 76.9 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.3· 2022-04-06
69.4
best: 89.7 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.4· 2022-04-06
64.3
best: 86.7 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.5· 2022-04-06
56
best: 80.9 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.6· 2022-04-06
46.4
best: 71 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.7· 2022-04-06
34.9
best: 56.1 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Action LocalizationonActivityNet-1.3
mAP· 2022-04-06
35.1
best: 42.9 (RDFA-S6 (InternVideo2-6B))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Action LocalizationonActivityNet-1.3
mAP IOU@0.5· 2022-04-06
50.47
best: 64.1 (RDFA-S6 (InternVideo2-6B))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Action LocalizationonActivityNet-1.3
mAP IOU@0.75· 2022-04-06
35.99
best: 44 (RDFA-S6 (InternVideo2-6B))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Action LocalizationonTHUMOS’14
Avg mAP (0.3:0.7)· 2022-04-06
54.2
best: 76.9 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Action LocalizationonTHUMOS’14
mAP IOU@0.3· 2022-04-06
69.4
best: 89.7 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Action LocalizationonTHUMOS’14
mAP IOU@0.4· 2022-04-06
64.3
best: 86.7 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Action LocalizationonTHUMOS’14
mAP IOU@0.5· 2022-04-06
56
best: 80.9 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Action LocalizationonTHUMOS’14
mAP IOU@0.6· 2022-04-06
46.4
best: 71 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Action LocalizationonTHUMOS’14
mAP IOU@0.7· 2022-04-06
34.9
best: 56.1 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932

Methodology10 results

Zero-Shot LearningonActivityNet-1.3
mAP IOU@0.95· 2022-04-06
10.83
best: 10.85 (AdaTAD (VideoMAEv2-giant))
SOTA
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Zero-Shot LearningonActivityNet-1.3
mAP· 2022-04-06
35.1
best: 42.9 (RDFA-S6 (InternVideo2-6B))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Zero-Shot LearningonActivityNet-1.3
mAP IOU@0.5· 2022-04-06
50.47
best: 64.1 (RDFA-S6 (InternVideo2-6B))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Zero-Shot LearningonActivityNet-1.3
mAP IOU@0.75· 2022-04-06
35.99
best: 44 (RDFA-S6 (InternVideo2-6B))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Zero-Shot LearningonTHUMOS’14
Avg mAP (0.3:0.7)· 2022-04-06
54.2
best: 76.9 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.3· 2022-04-06
69.4
best: 89.7 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.4· 2022-04-06
64.3
best: 86.7 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.5· 2022-04-06
56
best: 80.9 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.6· 2022-04-06
46.4
best: 71 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.7· 2022-04-06
34.9
best: 56.1 (AdaTAD (VideoMAEv2-giant))
An Empirical Study of End-to-End Temporal Action Detection arXiv:2204.02932