Context-aware and scale-insensitive temporal repetition counting

• Main Authors: ZHANG, Huaidong, XU, Xuemiao, HAN, Guoqiang, HE, Shengfeng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2020
• Subjects: Coarse to fine; Context-Aware; Contextual understanding; Cycle length; Learning methods; Number of cycles; Refinement methods; State-of-the-art methods; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/8523; https://ink.library.smu.edu.sg/context/sis_research/article/9526/viewcontent/Context_Aware_and_Scale_Insensitive_Temporal_Repetition_Counting.pdf
• Institution: Singapore Management University

Temporal repetition counting aims to estimate the number of cycles of a given repetitive action. Existing deep learning methods assume repetitive actions are performed in a fixed time-scale, which is invalid for the complex repetitive actions in real life. In this paper, we tailor a context-aware an...