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/STAR/L

STAR/L

Reported on 8 benchmarks across 4 tasks · 1 paper · 3 SOTA

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

Time Series5 results

Action DetectiononUCF101-24
Frame-mAP 0.5· uses extra data· 2023-04-24
90.3
SOTA
End-to-End Spatio-Temporal Action Localisation with Video Transformers arXiv:2304.12160
Action RecognitiononAVA v2.1
mAP (Val)· uses extra data· 2023-04-24
41.7
SOTA
End-to-End Spatio-Temporal Action Localisation with Video Transformers arXiv:2304.12160
Action DetectiononUCF101-24
Video-mAP 0.2· uses extra data· 2023-04-24
88
best: 88.8 (HIT)
End-to-End Spatio-Temporal Action Localisation with Video Transformers arXiv:2304.12160
Action DetectiononUCF101-24
Video-mAP 0.5· uses extra data· 2023-04-24
71.8
best: 76.3 (Stable Mean Teacher (I3D))
End-to-End Spatio-Temporal Action Localisation with Video Transformers arXiv:2304.12160
Action RecognitiononAVA v2.2
mAP· uses extra data· 2023-04-24
41.7
best: 45.1 (LART (Hiera-H, K700 PT+FT))
End-to-End Spatio-Temporal Action Localisation with Video Transformers arXiv:2304.12160

Robots2 results

Activity RecognitiononAVA v2.1
mAP (Val)· uses extra data· 2023-04-24
41.7
SOTA
End-to-End Spatio-Temporal Action Localisation with Video Transformers arXiv:2304.12160
Activity RecognitiononAVA v2.2
mAP· uses extra data· 2023-04-24
41.7
best: 45.1 (LART (Hiera-H, K700 PT+FT))
End-to-End Spatio-Temporal Action Localisation with Video Transformers arXiv:2304.12160

Computer Vision1 result

Action LocalizationonAVA-Kinetics
val mAP· uses extra data· 2023-04-24
41.7
best: 42.6 (VideoMAE V2-g)
End-to-End Spatio-Temporal Action Localisation with Video Transformers arXiv:2304.12160