DQEN enhances DETR-based HOI detection by initializing object and interaction queries with encoder features and CLIP text-derived semantics, improving HICO-Det mAP but not V-COCO.
Unseen no more: Unlocking the potential of clip for generative zero-shot hoi detection,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DQEN: Dual Query Enhancement Network for DETR-based HOI Detection
DQEN enhances DETR-based HOI detection by initializing object and interaction queries with encoder features and CLIP text-derived semantics, improving HICO-Det mAP but not V-COCO.