Cross-domain-Human-Parsing-via-Adversarial-Feature-and-Label-Adaptation icon indicating copy to clipboard operation
Cross-domain-Human-Parsing-via-Adversarial-Feature-and-Label-Adaptation copied to clipboard

we propose a novel and efficient cross-domain human parsing model to bridge the cross-domain differences in terms of visual appearance and environment conditions and fully exploit commonalities across...

Cross-domain-Human-Parsing-via-Adversarial-Feature-and-Label-Adaptation

The project is not completed yet, this is not the final version.