no code implementations • 11 Apr 2024 • Zeng Yu, Yunxiao Shi
Importantly, in the alignment process of SAS and AAL, all the parameters are immediately optimized with optimization principles rather than training the whole network, which yields a better parameter training manner.
no code implementations • 6 Apr 2022 • Peng Xie, Minbo Ma, Tianrui Li, Shenggong Ji, Shengdong Du, Zeng Yu, Junbo Zhang
Second, we employ a dynamic graph relationship learning module to learn dynamic spatial relationships between metro stations without a predefined graph adjacency matrix.
no code implementations • 22 Nov 2017 • Zeng Yu, Tianrui Li, Ning Yu, Xun Gong, Ke Chen, Yi Pan
This paper aims to develop a new architecture that can make full use of the feature maps of convolutional networks.
no code implementations • 8 Oct 2017 • Zeng Yu, Tianrui Li, Ning Yu, Yi Pan, Hongmei Chen, Bing Liu
We believe that minimizing the reconstruction error of the hidden representation is more robust than minimizing the Frobenius norm of the Jacobian matrix of the hidden representation.