Yuan-Zhi Zhao

Proxy-Guided Masked Contrastive Alignment for Cross-Modal Hashing

Semantic Guidance for Boundary Aware Cross-Modal Hashing under Noisy Supervision

When labels are corrupted by noise, cross-modal hashing often fails to maintain reliable semantic neighborhoods and clear decision boundaries in the Hamming space. Existing robust hashing methods mainly improve the reliability of samples or pairwise supervision, while the class-level semantics contained in multi-label...

Advances in Multi-Omics Research on Post-Stroke Depression: From Molecular Mechanisms to Therapeutic Strategies

Overall, multi-omics studies have provided new insights into the molecular basis of PSD and facilitated the identification of potential biomarkers and therapeutic targets, however, their clinical utility requires further evaluation through standardized cohorts and validation studies.

DSSL-Hash: Dynamic Semantic Structure Learning for Unsupervised Cross-Modal Hashing

A central bottleneck in unsupervised cross-modal hashing is that both similarity guidance and objective weighting are typically static, while the semantic structure induced during training is inherently dynamic. We present DSSL-Hash, which turns semantic structure learning into an evolving process rather than a one-sho...