ACAR (multi-scale, ensemble)

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

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

Computer Vision2 results

Action LocalizationonAVA-Kinetics
test mAP· uses extra data· 2020-06-14
39.62
SOTA
Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization arXiv:2006.07976
Action LocalizationonAVA-Kinetics
val mAP· uses extra data· 2020-06-14
40.49
best: 42.6 (VideoMAE V2-g)
SOTA
Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization arXiv:2006.07976