A bilateral collaboration between an HOI detector and BLIP-2, combining attention bias guidance and token-level LLM supervision, achieves state-of-the-art open-vocabulary and closed-set HOI detection.
Title resolution pending
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
-
Bilateral Collaboration with Large Vision-Language Models for Open Vocabulary Human-Object Interaction Detection
A bilateral collaboration between an HOI detector and BLIP-2, combining attention bias guidance and token-level LLM supervision, achieves state-of-the-art open-vocabulary and closed-set HOI detection.