MLP-3D: A MLP-like 3D architecture with grouped time mixing

• المؤلفون الرئيسيون: QIU, Zhaofan, 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/7505; https://ink.library.smu.edu.sg/context/sis_research/article/8508/viewcontent/Qiu_MLP_3D_A_MLP_Like_3D_Architecture_With_Grouped_Time_Mixing_CVPR_2022_paper.pdf

Convolutional Neural Networks (CNNs) have been re-garded as the go-to models for visual recognition. More re-cently, convolution-free networks, based on multi-head self-attention (MSA) or multi-layer perceptrons (MLPs), become more and more popular. Nevertheless, it is not trivial when utilizing the...