Enhancing Bag-of-Words Models by Efficient Semantics-Preserving Metric Learning

• Main Authors: WU, Lei, HOI, Steven C. H.
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2011
• Subjects: Bag-of-words models; distance metric learning; image annotation; multimedia and graphics; object codebook; object recognition; semantic gap; Databases and Information Systems; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/2308; https://ink.library.smu.edu.sg/context/sis_research/article/3308/viewcontent/05720676.pdf
• Institution: Singapore Management University

The authors present an online semantics preserving, metric learning technique for improving the bag-of-words model and addressing the semantic-gap issue. This article investigates the challenge of reducing the semantic gap for building BoW models for image representation; propose a novel OSPML algorithm for enhancing BoW by minimizing the semantic loss, which is efficient and scalable for enhancing BoW models for large-scale applications; apply the proposed technique for large-scale image annotation and object recognition; and compare it to the state of the art.