Hierarchical matching and reasoning for multi-query image retrieval

Zhong Ji, Zhihao Li, Yan Zhang, Haoran Wang, Yanwei Pang, Xuelong Li

Abstract: Highlights•Cope with the difficulties arising from the heterogeneous gap between images and multiple detailed text queries.•Design a hierarchical structure to explore and aggregate diverse semantical characteristics.•Perform multi-level matching to facilitate the fine-grained alignments.•Conduct high-level reasoning to mine the inherent intra-correlations and inter-correlations.•Significantly outperform the state-of-the-art methods by more than 20% on the R@1 metric.