HoPA captures high-order cross-modal alignments via a shared proxy to enable scalable omnimodal dataset distillation with better performance-compression trade-offs.
Languagebind: Extending video-language pretraining to n-modality by language-based se- mantic alignment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Omnimodal Dataset Distillation via High-order Proxy Alignment
HoPA captures high-order cross-modal alignments via a shared proxy to enable scalable omnimodal dataset distillation with better performance-compression trade-offs.