Bag of Bags: Adaptive Visual Vocabularies for Genizah Join Image Retrieval

ArXi:2604.08138v1 Announce Type: new A join is a set of manuscript fragments identified as originally emanating from the same manuscript. We study manuscript join retrieval: Given a query image of a fragment, retrieve other fragments originating from the same physical manuscript. We propose Bag of Bags (BoB), an image-level representation that replaces the global-level visual codebook of classical Bag of Words (BoW) with a fragment-specific vocabulary of local visual words.