Learning directional co-occurrence for human action classification

• Main Authors: LIU, Hong, LIU, Mengyuan, SUN, Qianru
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2014
• Subjects: Human action recognition; bag-of-word; co-occurrence; Computer Engineering; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/4464; https://ink.library.smu.edu.sg/context/sis_research/article/5467/viewcontent/LEARNINGDIRECTIONALCO_OCCURRENCEFORHUMANACTIONCLASSIFICATION.pdf
• Institution: Singapore Management University

Spatio-temporal interest point (STIP) based methods have shown promising results for human action classification. However, state-of-art works typically utilize bag-of-visual words (BoVW), which focuses on the statistical distribution of features but ignores their inherent structural relationships. T...