QPIC + CPC

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

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

Computer Vision2 results

Human-Object Interaction DetectiononV-COCO
MAP· 2022-04-11
63.1
SOTA
Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection arXiv:2204.04836
Human-Object Interaction DetectiononHICO-DET
mAP· 2022-04-11
29.63
best: 46.49 (Ours (PViC+))
Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection arXiv:2204.04836