Learning to Rank Words: Optimizing Ranking Metrics for Word Spotting
This work addresses word spotting for retrieval applications, but it is incremental as it builds on existing ranking methods without introducing a major breakthrough.
The paper tackled the problem of learning word string and image encoders for word spotting by using ranking-based objective functions, achieving competitive performance on query-by-string tasks for handwritten and real scene word images.
In this paper, we explore and evaluate the use of ranking-based objective functions for learning simultaneously a word string and a word image encoder. We consider retrieval frameworks in which the user expects a retrieval list ranked according to a defined relevance score. In the context of a word spotting problem, the relevance score has been set according to the string edit distance from the query string. We experimentally demonstrate the competitive performance of the proposed model on query-by-string word spotting for both, handwritten and real scene word images. We also provide the results for query-by-example word spotting, although it is not the main focus of this work.