Dynamic temporal filtering in video models

• المؤلفون الرئيسيون: LONG, Fuchen, QIU, Zhaofan, PAN, Yingwei, YAO, Ting, NGO, Chong-wah, MEI, Tao
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2022
• الموضوعات: Artificial Intelligence and Robotics; Graphics and Human Computer Interfaces
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/7509; https://ink.library.smu.edu.sg/context/sis_research/article/8512/viewcontent/136950470.pdf
• المؤسسة: Singapore Management University

Video temporal dynamics is conventionally modeled with 3D spatial-temporal kernel or its factorized version comprised of 2D spatial kernel and 1D temporal kernel. The modeling power, nevertheless, is limited by the fixed window size and static weights of a kernel along the temporal dimension. The pr...