MatrixLSTM Overview
A Differentiable Recurrent Surface for Asynchronous Event-Based Data
ECCV, 2020
project page / code / 1min video / 10min video /

We reconstruct a dense feature representation from sparse events using a grid of LSTM cells so that we could apply standard frame-based CNNs architectures for tasks such as image recognition and optical flow.

Led by Marco Cannici, joint with myself, Andrea Romanoni and Matteo Matteucci