LPMT combines ensemble bidirectional diffusion, reciprocal-neighborhood distribution embeddings, and a Sinkhorn-Wasserstein distance, claiming state-of-the-art re-ranking on ROxf and RPar.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Locality Preserving Markovian Transition for Instance Retrieval
LPMT combines ensemble bidirectional diffusion, reciprocal-neighborhood distribution embeddings, and a Sinkhorn-Wasserstein distance, claiming state-of-the-art re-ranking on ROxf and RPar.