Cascaded Retrieval with Cross-Modal Query Refinement for Efficient Visual Document Search
This work proposes SCOUT, a cascaded two-track retrieval framework that separates retrieval performance from exhaustive search, and evaluates it on 4 major benchmarks against 6 baselines and observes a significant query-time latency improvement up to 80.7x.
Diana Turmakhan, Aseem Srivastava, Vivek Gupta et al.
· 0 citations