作者位次 #3/7SIGIR 2026Oral· Information Retrieval (Full)
Attention Grounded Enhancement for Visual Document Retrieval
Wanqing Cui · Wei Huang · Yazhi Guo · Yibo Hu · Meiguang Jin · Junfeng Ma · Keping Bi
摘要
Visual document retrieval requires understanding heterogeneous and multi-modal content to satisfy implicit information needs. Recent advances use screenshot-based document encoding with fine-grained late interaction to encode holistic information and capture nuanced alignments, significantly impr...