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/DCAN (TSN features)

DCAN (TSN features)

Reported on 40 benchmarks across 4 tasks · 1 paper

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· 2021-12-07
35.39
best: 42.9 (RDFA-S6 (InternVideo2-6B))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
VideoonActivityNet-1.3
mAP IOU@0.5· 2021-12-07
51.78
best: 64.1 (RDFA-S6 (InternVideo2-6B))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
VideoonActivityNet-1.3
mAP IOU@0.75· 2021-12-07
35.98
best: 44 (RDFA-S6 (InternVideo2-6B))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
VideoonActivityNet-1.3
mAP IOU@0.95· 2021-12-07
9.45
best: 10.85 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
VideoonTHUMOS’14
Avg mAP (0.3:0.7)· 2021-12-07
52.3
best: 76.9 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
VideoonTHUMOS’14
mAP IOU@0.3· 2021-12-07
68.2
best: 89.7 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
VideoonTHUMOS’14
mAP IOU@0.4· 2021-12-07
62.7
best: 86.7 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
VideoonTHUMOS’14
mAP IOU@0.5· 2021-12-07
54.1
best: 80.9 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
VideoonTHUMOS’14
mAP IOU@0.6· 2021-12-07
43.9
best: 71 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
VideoonTHUMOS’14
mAP IOU@0.7· 2021-12-07
32.6
best: 56.1 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Temporal Action LocalizationonActivityNet-1.3
mAP· 2021-12-07
35.39
best: 42.9 (RDFA-S6 (InternVideo2-6B))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Temporal Action LocalizationonActivityNet-1.3
mAP IOU@0.5· 2021-12-07
51.78
best: 64.1 (RDFA-S6 (InternVideo2-6B))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Temporal Action LocalizationonActivityNet-1.3
mAP IOU@0.75· 2021-12-07
35.98
best: 44 (RDFA-S6 (InternVideo2-6B))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Temporal Action LocalizationonActivityNet-1.3
mAP IOU@0.95· 2021-12-07
9.45
best: 10.85 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Temporal Action LocalizationonTHUMOS’14
Avg mAP (0.3:0.7)· 2021-12-07
52.3
best: 76.9 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.3· 2021-12-07
68.2
best: 89.7 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.4· 2021-12-07
62.7
best: 86.7 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.5· 2021-12-07
54.1
best: 80.9 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.6· 2021-12-07
43.9
best: 71 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.7· 2021-12-07
32.6
best: 56.1 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Action LocalizationonActivityNet-1.3
mAP· 2021-12-07
35.39
best: 42.9 (RDFA-S6 (InternVideo2-6B))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Action LocalizationonActivityNet-1.3
mAP IOU@0.5· 2021-12-07
51.78
best: 64.1 (RDFA-S6 (InternVideo2-6B))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Action LocalizationonActivityNet-1.3
mAP IOU@0.75· 2021-12-07
35.98
best: 44 (RDFA-S6 (InternVideo2-6B))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Action LocalizationonActivityNet-1.3
mAP IOU@0.95· 2021-12-07
9.45
best: 10.85 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Action LocalizationonTHUMOS’14
Avg mAP (0.3:0.7)· 2021-12-07
52.3
best: 76.9 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Action LocalizationonTHUMOS’14
mAP IOU@0.3· 2021-12-07
68.2
best: 89.7 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Action LocalizationonTHUMOS’14
mAP IOU@0.4· 2021-12-07
62.7
best: 86.7 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Action LocalizationonTHUMOS’14
mAP IOU@0.5· 2021-12-07
54.1
best: 80.9 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Action LocalizationonTHUMOS’14
mAP IOU@0.6· 2021-12-07
43.9
best: 71 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Action LocalizationonTHUMOS’14
mAP IOU@0.7· 2021-12-07
32.6
best: 56.1 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612

Methodology10 results

Zero-Shot LearningonActivityNet-1.3
mAP· 2021-12-07
35.39
best: 42.9 (RDFA-S6 (InternVideo2-6B))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Zero-Shot LearningonActivityNet-1.3
mAP IOU@0.5· 2021-12-07
51.78
best: 64.1 (RDFA-S6 (InternVideo2-6B))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Zero-Shot LearningonActivityNet-1.3
mAP IOU@0.75· 2021-12-07
35.98
best: 44 (RDFA-S6 (InternVideo2-6B))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Zero-Shot LearningonActivityNet-1.3
mAP IOU@0.95· 2021-12-07
9.45
best: 10.85 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Zero-Shot LearningonTHUMOS’14
Avg mAP (0.3:0.7)· 2021-12-07
52.3
best: 76.9 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.3· 2021-12-07
68.2
best: 89.7 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.4· 2021-12-07
62.7
best: 86.7 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.5· 2021-12-07
54.1
best: 80.9 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.6· 2021-12-07
43.9
best: 71 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.7· 2021-12-07
32.6
best: 56.1 (AdaTAD (VideoMAEv2-giant))
DCAN: Improving Temporal Action Detection via Dual Context Aggregation arXiv:2112.03612