作者位次 #5/5SIGIR 2026Poster· Information Retrieval (Short)
PeaCap: Patch-Level Retrieval for Lightweight Retrieval-Augmented Image Captioning
Robin Viltoriano · Wei Emma Zhang · Hu Wang · Mong Yuan Sim · Yanjun Shu
摘要
Retrieval-augmented image captioning aims to improve caption quality by grounding generation in external evidence, but most prior systems retrieve evidence using coarse whole-image similarity, which can miss small or rare objects in cluttered scenes. We propose PeaCap, a patch-based retrieval-aug...