ActionFormer

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.

Other2 results

audio-visual event localizationonUnAV-100
mAP· 2022-02-16
42.2
best: 47.8 (UnAV)
SOTA
ActionFormer: Localizing Moments of Actions with Transformers arXiv:2202.07925
audio-visual event localizationonUnAV-100
AP@IOU0.5· 2022-02-16
43.5
best: 50.6 (UnAV)
SOTA
ActionFormer: Localizing Moments of Actions with Transformers arXiv:2202.07925