Optimization Planning for 3D ConvNets
Zhaofan Qiu 1 Ting Yao 1 Chong-Wah Ngo 2 Tao Mei 1
Abstract stance, an ensemble of LGD-3D networks (Qiu et al., 2019)
achieves 17.88% in terms of average error in trimmed video
It is not trivial to optimally learn a 3D Convo- classification task of ActivityNet Challenge 2019, which is
lutional Neural Networks (3D ConvNets) due to dramatically lower than the ...


雷达卡




京公网安备 11010802022788号







