GNAH transfers semantic structure from vision-language models into compact binary codes using prototype-anchored global alignment and contrastive stochastic neighborhood alignment for data-efficient unsupervised cross-modal hashing.
Implementation Details Our method is evaluated using three widely used datasets: MIR Flickr [22], Pascal Sentence [23], and NUS-WIDE [24]
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
-
Unsupervised Data-Efficient Cross-Modal Retrieval with Global-Neighborhood Alignment Hashing
GNAH transfers semantic structure from vision-language models into compact binary codes using prototype-anchored global alignment and contrastive stochastic neighborhood alignment for data-efficient unsupervised cross-modal hashing.