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/UniMD+Sync.

UniMD+Sync.

Reported on 19 benchmarks across 6 tasks · 1 paper · 2 SOTA

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

Computer Vision12 results

Moment RetrievalonCharades-STA
R@5 IoU=0.5· 2024-04-07
91.94
SOTA
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection arXiv:2404.04933
Moment RetrievalonCharades-STA
R@5 IoU=0.7· 2024-04-07
67.72
SOTA
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection arXiv:2404.04933
VideoonActivityNet-1.3
mAP· 2024-04-07
39.83
best: 42.9 (RDFA-S6 (InternVideo2-6B))
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection arXiv:2404.04933
VideoonActivityNet-1.3
mAP IOU@0.5· 2024-04-07
60.29
best: 64.1 (RDFA-S6 (InternVideo2-6B))
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection arXiv:2404.04933
VideoonActivityNet Captions
R@5,IoU=0.5· 2024-04-07
80.54
best: 81.5 (UnLoc-B)
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection arXiv:2404.04933
VideoonActivityNet Captions
R@5,IoU=0.7· 2024-04-07
57.04
best: 63.33 (VLG-Net)
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection arXiv:2404.04933
Temporal Action LocalizationonActivityNet-1.3
mAP· 2024-04-07
39.83
best: 42.9 (RDFA-S6 (InternVideo2-6B))
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection arXiv:2404.04933
Temporal Action LocalizationonActivityNet-1.3
mAP IOU@0.5· 2024-04-07
60.29
best: 64.1 (RDFA-S6 (InternVideo2-6B))
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection arXiv:2404.04933
Action LocalizationonActivityNet-1.3
mAP· 2024-04-07
39.83
best: 42.9 (RDFA-S6 (InternVideo2-6B))
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection arXiv:2404.04933
Action LocalizationonActivityNet-1.3
mAP IOU@0.5· 2024-04-07
60.29
best: 64.1 (RDFA-S6 (InternVideo2-6B))
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection arXiv:2404.04933
Moment RetrievalonCharades-STA
R@1 IoU=0.5· 2024-04-07
63.98
best: 71.1 (SG-DETR (w/ PT))
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection arXiv:2404.04933
Moment RetrievalonCharades-STA
R@1 IoU=0.7· 2024-04-07
44.46
best: 52.8 (SG-DETR (w/ PT))
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection arXiv:2404.04933

Natural Language Processing5 results

Natural Language QueriesonEgo4D
R@1 IoU=0.3· 2024-04-07
14.16
best: 28.05 (EgoVideo)
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection arXiv:2404.04933
Natural Language QueriesonEgo4D
R@1 IoU=0.5· 2024-04-07
10.06
best: 19.31 (EgoVideo)
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection arXiv:2404.04933
Natural Language QueriesonEgo4D
R@1 Mean(0.3 and 0.5)· 2024-04-07
12.11
best: 23.68 (EgoVideo)
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection arXiv:2404.04933
Natural Language QueriesonEgo4D
R@5 IoU=0.3· 2024-04-07
26.95
best: 45.63 (DeCafNet-100%)
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection arXiv:2404.04933
Natural Language QueriesonEgo4D
R@5 IoU=0.5· 2024-04-07
19.16
best: 33.93 (DeCafNet-100%)
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection arXiv:2404.04933

Methodology2 results

Zero-Shot LearningonActivityNet-1.3
mAP· 2024-04-07
39.83
best: 42.9 (RDFA-S6 (InternVideo2-6B))
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection arXiv:2404.04933
Zero-Shot LearningonActivityNet-1.3
mAP IOU@0.5· 2024-04-07
60.29
best: 64.1 (RDFA-S6 (InternVideo2-6B))
UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection arXiv:2404.04933