There will be a Center for Artificial Intelligence Innovation Fall Seminar on Monday, October 12 at 11:00 a.m. U.S. Central Time via Zoom. Presenting "Convolutional Tensor-Train LSTM for Spatio-Temporal Learning" will be Wonmin Byeon from NVIDIA.
Abstract: Learning from spatio-temporal data has numerous applications such as human-behavior analysis, object tracking, video compression, and physics simulation. However, existing methods still perform poorly on challenging video tasks such as long-term forecasting. This is because these kinds of challenging tasks require learning long-term spatio-temporal correlations in the video sequence. In this talk, we explain a higher-order convolutional LSTM model that can efficiently learn these correlations, along with a succinct representations of the history. This is accomplished through a novel tensor train module that performs prediction by combining convolutional features across time. The proposed convolutional tensor-train decomposition reduces the model complexity by jointly approximating a sequence of convolutional kernels as a low-rank tensor-train factorization. As a result, our model outperforms existing approaches, but uses only a fraction of parameters in a wide range of applications.
Register to attend this webinar.
Seminar Zoom link.