APKH uses prompt-optimized attribute kernel mapping and kernel-smoothed contrastive alignment to improve generalization from seen to unseen categories in data-constrained unsupervised cross-modal hashing.
On estimation of a probability density function and mode,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Attribute-Prompted Kernel Hashing for Unsupervised Data-Efficient Cross-Modal Retrieval
APKH uses prompt-optimized attribute kernel mapping and kernel-smoothed contrastive alignment to improve generalization from seen to unseen categories in data-constrained unsupervised cross-modal hashing.