G-MIXER achieves state-of-the-art zero-shot composed image retrieval by using geodesic mixup to build diverse implicit candidates and MLLM-derived explicit semantics for re-ranking.
isearle: Improving textual inversion for zero-shot composed image retrieval.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025
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
-
G-MIXER: Geodesic Mixup-based Implicit Semantic Expansion and Explicit Semantic Re-ranking for Zero-Shot Composed Image Retrieval
G-MIXER achieves state-of-the-art zero-shot composed image retrieval by using geodesic mixup to build diverse implicit candidates and MLLM-derived explicit semantics for re-ranking.