In the paper’s cross-domain experiments, person detectors trained on natural images were evaluated on the Picasso and People-Art artwork datasets. Which conclusion is supported by those experiments?

Question

Answer

R-CNN achieved the highest average precision on both artwork datasets.

Answer

YOLO achieved higher average precision than DPM and R-CNN on both artwork datasets, supporting stronger cross-domain generalization in this experiment.

Answer

All compared methods lost the same proportion of their performance.

Answer

YOLO achieved good results only after being fine-tuned on each artwork dataset.

Crowdly

In the paper’s cross-domain experiments, person detectors trained on natural ima...

Want instant access to all verified answers on sifo.comillas.edu?