Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Spatio-Temporal Video Autoencoder with Differentiable Memory
Viorica Patraucean, Ankur Handa, Roberto Cipolla
Feb 18, 2016 (modified: Feb 18, 2016)ICLR 2016 workshop submissionreaders: everyone
Abstract:We describe a new spatio-temporal video autoencoder, based on a classic spatial image autoencoder and a novel nested temporal autoencoder. The temporal encoder is represented by a differentiable visual memory composed of convolutional long short-term memory (LSTM) cells that integrate changes over time. Here we target motion changes and use as temporal decoder a robust optical flow prediction module together with an image sampler serving as built-in feedback loop. The architecture is end-to-end differentiable. At each time step, the system receives as input a video frame, predicts the optical flow based on the current observation and the LSTM memory state as a dense transformation map, and applies it to the current frame to generate the next frame. By minimising the reconstruction error between the predicted next frame and the corresponding ground truth next frame, we train the whole system to extract features useful for motion estimation without any supervision effort. We believe these features can in turn facilitate learning high-level tasks such as path planning, semantic segmentation, or action recognition, reducing the overall supervision effort.
Enter your feedback below and we'll get back to you as soon as possible.