一作SIGIR 2026Poster· Information Retrieval (Short)
ADaFuSE: Adaptive Diffusion-generated Image and Text Fusion for Interactive Text-to-Image Retrieval
Zhuocheng Zhang · Xingwu Zhang · Kangheng Liang · Guanxuan Li · Richard McCreadie · ZIJUN LONG
摘要
Recent advances in interactive text-to-image retrieval (I-TIR) use diffusion models to bridge the modality gap between the textual information need and the images to be searched. However, existing frameworks fuse multi-modal user feedback by simple embedding addition. In this work, we show that t...