Semantics-Preserving Bag-of-Words Models and Applications

• Main Authors: WU, Lei, HOI, Steven C. H., YU, Nenghai
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2010
• Subjects: Image retrieval; Research and development; Image storage; Image segmentation; Image representation; Loss measurement; Particle measurements; Object detection; Testing; Image databases; Computer Sciences; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/2309; https://ink.library.smu.edu.sg/context/sis_research/article/3309/viewcontent/TIP_05056_2009_SPBOW_1_.pdf
• Institution: Singapore Management University

The Bag-of-Words (BoW) model is a promising image representation technique for image categorization and annotation tasks. One critical limitation of existing BoW models is that much semantic information is lost during the codebook generation process, an important step of BoW. This is because the cod...