A shared-token encoder-decoder plus a commonality-based margin ranking loss achieves state-of-the-art text-to-image person retrieval on three benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving Text-based Person Search via Part-level Cross-modal Correspondence
A shared-token encoder-decoder plus a commonality-based margin ranking loss achieves state-of-the-art text-to-image person retrieval on three benchmarks.