Towards optimal bag-of-features for object categorization and semantic video retrieval

• Main Authors: JIANG, Yu-Gang, NGO, Chong-wah, YANG, Jun
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2007
• Subjects: Bag-of-features; Kernel; Keypoint detector; Object categorization; Semantic video retrieval; Soft-weighting; Data Storage Systems; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/6528; https://ink.library.smu.edu.sg/context/sis_research/article/7531/viewcontent/1282280.1282352.pdf
• Institution: Singapore Management University

Bag-of-features (BoF) deriving from local keypoints has recently appeared promising for object and scene classification. Whether BoF can naturally survive the challenges such as reliability and scalability of visual classification, nevertheless, remains uncertain due to various implementation choice...