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/D2-Net

D2-Net

Reported on 45 benchmarks across 5 tasks · 1 paper · 21 SOTA

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

Computer Vision36 results

VideoonTHUMOS 2014
mAP@0.5· 2020-12-11
35.9
best: 52.2 (HR-Pro)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
VideoonTHUMOS’14
mAP@0.5· 2020-12-11
35.9
best: 45.3 (LACP)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
VideoonActivityNet-1.2
Mean mAP· 2020-12-11
26
best: 30.8 (SAL)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
VideoonActivityNet-1.2
mAP@0.5· 2020-12-11
42.3
best: 49.6 (AICL)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Temporal Action LocalizationonTHUMOS 2014
mAP@0.5· 2020-12-11
35.9
best: 52.2 (HR-Pro)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Temporal Action LocalizationonTHUMOS’14
mAP@0.5· 2020-12-11
35.9
best: 45.3 (LACP)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Temporal Action LocalizationonActivityNet-1.2
Mean mAP· 2020-12-11
26
best: 30.8 (SAL)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Temporal Action LocalizationonActivityNet-1.2
mAP@0.5· 2020-12-11
42.3
best: 49.6 (AICL)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Action LocalizationonTHUMOS 2014
mAP@0.5· 2020-12-11
35.9
best: 52.2 (HR-Pro)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Action LocalizationonTHUMOS’14
mAP@0.5· 2020-12-11
35.9
best: 45.3 (LACP)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Action LocalizationonActivityNet-1.2
Mean mAP· 2020-12-11
26
best: 30.8 (SAL)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Action LocalizationonActivityNet-1.2
mAP@0.5· 2020-12-11
42.3
best: 49.6 (AICL)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Weakly Supervised Action LocalizationonTHUMOS 2014
mAP@0.5· 2020-12-11
35.9
best: 52.2 (HR-Pro)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Weakly Supervised Action LocalizationonFineAction
mAP IOU@0.5· 2020-12-11
6.75
best: 7.05 (HAAN)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Weakly Supervised Action LocalizationonTHUMOS’14
mAP@0.5· 2020-12-11
35.9
best: 45.3 (LACP)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Weakly Supervised Action LocalizationonActivityNet-1.2
Mean mAP· 2020-12-11
26
best: 30.8 (SAL)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Weakly Supervised Action LocalizationonActivityNet-1.2
mAP@0.5· 2020-12-11
42.3
best: 49.6 (AICL)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
VideoonTHUMOS 2014
mAP@0.1:0.5· 2020-12-11
51.4
best: 71.6 (HR-Pro)
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
VideoonFineAction
mAP· 2020-12-11
3.35
best: 29.6 (RDFA-S6 (InternVideo2-6B))
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
VideoonFineAction
mAP IOU@0.5· 2020-12-11
6.75
best: 46.4 (RDFA-S6 (InternVideo2-6B))
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
VideoonFineAction
mAP IOU@0.75· 2020-12-11
3.02
best: 29.5 (RDFA-S6 (InternVideo2-6B))
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
VideoonFineAction
mAP IOU@0.95· 2020-12-11
0.82
best: 7.6 (RDFA-S6 (InternVideo2-6B))
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Temporal Action LocalizationonTHUMOS 2014
mAP@0.1:0.5· 2020-12-11
51.4
best: 71.6 (HR-Pro)
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Temporal Action LocalizationonFineAction
mAP· 2020-12-11
3.35
best: 29.6 (RDFA-S6 (InternVideo2-6B))
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Temporal Action LocalizationonFineAction
mAP IOU@0.5· 2020-12-11
6.75
best: 46.4 (RDFA-S6 (InternVideo2-6B))
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Temporal Action LocalizationonFineAction
mAP IOU@0.75· 2020-12-11
3.02
best: 29.5 (RDFA-S6 (InternVideo2-6B))
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Temporal Action LocalizationonFineAction
mAP IOU@0.95· 2020-12-11
0.82
best: 7.6 (RDFA-S6 (InternVideo2-6B))
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Action LocalizationonTHUMOS 2014
mAP@0.1:0.5· 2020-12-11
51.4
best: 71.6 (HR-Pro)
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Action LocalizationonFineAction
mAP· 2020-12-11
3.35
best: 29.6 (RDFA-S6 (InternVideo2-6B))
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Action LocalizationonFineAction
mAP IOU@0.5· 2020-12-11
6.75
best: 46.4 (RDFA-S6 (InternVideo2-6B))
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Action LocalizationonFineAction
mAP IOU@0.75· 2020-12-11
3.02
best: 29.5 (RDFA-S6 (InternVideo2-6B))
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Action LocalizationonFineAction
mAP IOU@0.95· 2020-12-11
0.82
best: 7.6 (RDFA-S6 (InternVideo2-6B))
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Weakly Supervised Action LocalizationonTHUMOS 2014
mAP@0.1:0.5· 2020-12-11
51.4
best: 71.6 (HR-Pro)
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Weakly Supervised Action LocalizationonFineAction
mAP· 2020-12-11
3.35
best: 4.1 (HAAN)
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Weakly Supervised Action LocalizationonFineAction
mAP IOU@0.75· 2020-12-11
3.02
best: 3.95 (HAAN)
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Weakly Supervised Action LocalizationonFineAction
mAP IOU@0.95· 2020-12-11
0.82
best: 3.3 (ASL)
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440

Methodology9 results

Zero-Shot LearningonTHUMOS 2014
mAP@0.5· 2020-12-11
35.9
best: 52.2 (HR-Pro)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Zero-Shot LearningonTHUMOS’14
mAP@0.5· 2020-12-11
35.9
best: 45.3 (LACP)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Zero-Shot LearningonActivityNet-1.2
Mean mAP· 2020-12-11
26
best: 30.8 (SAL)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Zero-Shot LearningonActivityNet-1.2
mAP@0.5· 2020-12-11
42.3
best: 49.6 (AICL)
SOTA
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Zero-Shot LearningonTHUMOS 2014
mAP@0.1:0.5· 2020-12-11
51.4
best: 71.6 (HR-Pro)
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Zero-Shot LearningonFineAction
mAP· 2020-12-11
3.35
best: 29.6 (RDFA-S6 (InternVideo2-6B))
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Zero-Shot LearningonFineAction
mAP IOU@0.5· 2020-12-11
6.75
best: 46.4 (RDFA-S6 (InternVideo2-6B))
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Zero-Shot LearningonFineAction
mAP IOU@0.75· 2020-12-11
3.02
best: 29.5 (RDFA-S6 (InternVideo2-6B))
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440
Zero-Shot LearningonFineAction
mAP IOU@0.95· 2020-12-11
0.82
best: 7.6 (RDFA-S6 (InternVideo2-6B))
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations arXiv:2012.06440