Learning Visual Semantic Relationships For Proficient Visual Recovery

S. Vimalananthi
2017 Zenodo  
In this paper, I investigate how to establish the relationship between semantic concepts based on the large-scale real-world click data from image commercial engine, which is a challenging topic because the click data suffers from the noise such as typos, the same concept with different queries, etc. I first define five specific relationships between concepts. I extract some concept relationship features in textual and visual domain to train the concept relationship models. The relationship of
more » ... ach pair of concepts will thus be classified into one of the five special relationships. I study the efficacy of the conceptual relationships by applying them to augment imperfect image tags, i.e., improve representative power. We further employ a sophisticated hashing approach to transform augmented image tags into binary codes, which are subsequently used for content-based image retrieval task.
doi:10.5281/zenodo.546016 fatcat:evmzrh7zffauho4luaojzzxudy