no code implementations • 15 Sep 2020 • Logan Courtney, Ramavarapu Sreenivas
Many methods for learning from video sequences involve temporally processing 2D CNN features from the individual frames or directly utilizing 3D convolutions within high-performing 2D CNN architectures.
no code implementations • 9 Apr 2019 • Logan Courtney, Ramavarapu Sreenivas
This paper explores the use of convolution LSTMs to simultaneously learn spatial- and temporal-information in videos.