Bo-Wen Fu

StaG-CoTMR: Paraphrase-Consistent Zero-Shot Composed Image Retrieval via Finite Edit Graphs and Consensus-Guided Ranking

Zero-shot composed image retrieval (ZS-CIR) methods often use large vision-language models (LVLMs) to represent an image-text query comprising a reference image and a modification instruction. However, semantically equivalent instructions can alter the generated representations and final rankings. An individual retriev...