no code implementations • 5 Sep 2020 • Alvin Chan, Martin D. Levine, Mehrsan Javan
We propose an end-to-end trainable ResNet+LSTM network, with a residual network (ResNet) base and a long short-term memory (LSTM) layer, to discover spatio-temporal features of jersey numbers over time and learn long-term dependencies.
no code implementations • 29 May 2018 • Yaxiang Fan, Gongjian Wen, Deren Li, Shaohua Qiu, Martin D. Levine
The method is based on Gaussian Mixture Variational Autoencoder, which can learn feature representations of the normal samples as a Gaussian Mixture Model trained using deep learning.
no code implementations • 27 Mar 2017 • Yuguang Liu, Martin D. Levine
The second stage is a Boosted Forests classifier, which utilizes deep facial features pooled from inside the candidate face regions as well as deep contextual features pooled from a larger region surrounding the candidate face regions.
no code implementations • CVPR 2013 • Mehrsan Javan Roshtkhari, Martin D. Levine
We do not employ any models of the entities in the scene in order to detect these two kinds of behaviors.