Cross-Modality Hashing with Partial Correspondence
This addresses the challenge of cross-media search for applications like image-text retrieval, but it is incremental as it builds on existing hashing methods by handling partial correspondence.
The paper tackles the problem of learning cross-modal hashing functions when data lacks full correspondence between modalities, using partially corresponded data to enhance performance, and demonstrates that the proposed method outperforms state-of-the-art hashing approaches on Wiki and NUS-WIDE datasets with fewer correspondence information.
Learning a hashing function for cross-media search is very desirable due to its low storage cost and fast query speed. However, the data crawled from Internet cannot always guarantee good correspondence among different modalities which affects the learning for hashing function. In this paper, we focus on cross-modal hashing with partially corresponded data. The data without full correspondence are made in use to enhance the hashing performance. The experiments on Wiki and NUS-WIDE datasets demonstrates that the proposed method outperforms some state-of-the-art hashing approaches with fewer correspondence information.