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/UnLoc-L

UnLoc-L

Reported on 16 benchmarks across 6 tasks · 1 paper · 6 SOTA

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

Computer Vision15 results

Action LocalizationonCOIN
Frame accuracy· 2023-08-21
72.8
SOTA
UnLoc: A Unified Framework for Video Localization Tasks arXiv:2308.11062
Action SegmentationonCOIN
Frame accuracy· 2023-08-21
72.8
SOTA
UnLoc: A Unified Framework for Video Localization Tasks arXiv:2308.11062
Moment RetrievalonCharades-STA
R@1 IoU=0.5· 2023-08-21
60.8
best: 71.1 (SG-DETR (w/ PT))
SOTA
UnLoc: A Unified Framework for Video Localization Tasks arXiv:2308.11062
Moment RetrievalonCharades-STA
R@1 IoU=0.7· 2023-08-21
38.4
best: 52.8 (SG-DETR (w/ PT))
SOTA
UnLoc: A Unified Framework for Video Localization Tasks arXiv:2308.11062
Moment RetrievalonCharades-STA
R@5 IoU=0.7· 2023-08-21
61.1
best: 67.72 (UniMD+Sync.)
SOTA
UnLoc: A Unified Framework for Video Localization Tasks arXiv:2308.11062
Moment RetrievalonQVHighlights
R@1 IoU=0.5· 2023-08-21
66.1
best: 76.59 (LLaVA-MR)
SOTA
UnLoc: A Unified Framework for Video Localization Tasks arXiv:2308.11062
VideoonActivityNet-1.3
mAP IOU@0.5· 2023-08-21
59.3
best: 64.1 (RDFA-S6 (InternVideo2-6B))
UnLoc: A Unified Framework for Video Localization Tasks arXiv:2308.11062
VideoonActivityNet Captions
R@1,IoU=0.5· 2023-08-21
48.3
best: 60.67 (GVL (paragraph-level))
UnLoc: A Unified Framework for Video Localization Tasks arXiv:2308.11062
VideoonActivityNet Captions
R@1,IoU=0.7· 2023-08-21
30.2
best: 38.55 (GVL (paragraph-level))
UnLoc: A Unified Framework for Video Localization Tasks arXiv:2308.11062
VideoonActivityNet Captions
R@5,IoU=0.5· 2023-08-21
79.2
best: 81.5 (UnLoc-B)
UnLoc: A Unified Framework for Video Localization Tasks arXiv:2308.11062
VideoonActivityNet Captions
R@5,IoU=0.7· 2023-08-21
61.3
best: 63.33 (VLG-Net)
UnLoc: A Unified Framework for Video Localization Tasks arXiv:2308.11062
Temporal Action LocalizationonActivityNet-1.3
mAP IOU@0.5· 2023-08-21
59.3
best: 64.1 (RDFA-S6 (InternVideo2-6B))
UnLoc: A Unified Framework for Video Localization Tasks arXiv:2308.11062
Action LocalizationonActivityNet-1.3
mAP IOU@0.5· 2023-08-21
59.3
best: 64.1 (RDFA-S6 (InternVideo2-6B))
UnLoc: A Unified Framework for Video Localization Tasks arXiv:2308.11062
Moment RetrievalonCharades-STA
R@5 IoU=0.5· 2023-08-21
88.2
best: 91.94 (UniMD+Sync.)
UnLoc: A Unified Framework for Video Localization Tasks arXiv:2308.11062
Moment RetrievalonQVHighlights
R@1 IoU=0.7· 2023-08-21
46.7
best: 61.48 (LLaVA-MR)
UnLoc: A Unified Framework for Video Localization Tasks arXiv:2308.11062

Methodology1 result

Zero-Shot LearningonActivityNet-1.3
mAP IOU@0.5· 2023-08-21
59.3
best: 64.1 (RDFA-S6 (InternVideo2-6B))
UnLoc: A Unified Framework for Video Localization Tasks arXiv:2308.11062