Conceptphrase grounding
Phrase Grounding
A cross-modal alignment framework that splits a textual description into tokens, aligns object queries with the tokens through cross-modal attention, and then aggregates the token scores to obtain class confidence. It is commonly used for open-vocabulary object detection.
Timeline (last 90 days)
Oct 20
Mainstream OVOD methods adopt a phrase grounding framework: the text description is broken into tokens, object queries are aligned with the tokens, and category scores are then recovered through token-to-category aggregation.
Unverified50%