Attention in Convolutional LSTM for Gesture Recognition
Liang Zhang, Guangming Zhu, Lin Mei, Peiyi Shen, Syed Afaq Ali Shah, Mohammed Bennamoun
–Neural Information Processing Systems
In the preliminary "Res3D+ConvLSTM+MobileNet" architecture, the blocks 1-4 of Res3D [16] are used first to learn the local short-term spatiotemporal feature maps which have a relativelylargespatialsize.
Neural Information Processing Systems
Feb-12-2026, 11:27:00 GMT