STiTch refines LLM captions via embedding transition and uses set-to-set bidirectional transportation alignment to improve training-free zero-shot composed image retrieval.
Hierarchical optimal transport for multimodal distribution alignment.Advances in neural information processing sys- tems, 32, 2019
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
-
STiTch: Semantic Transition and Transportation in Collaboration for Training-Free Zero-Shot Composed Image Retrieval
STiTch refines LLM captions via embedding transition and uses set-to-set bidirectional transportation alignment to improve training-free zero-shot composed image retrieval.