Action Recognition with Dynamic Image Networks
We introduce the concept of dynamic image, a novel compact representation of videos useful for video analysis, particularly in combination with convolutional neural networks (CNNs). A dynamic image encodes temporal data such as RGB or optical flow videos by using the concept of 'rank pooling'. The idea is to learn a ranking machine that captures the temporal evolution of the data and to use the parameters of the latter as a representation. We call the resulting representation dynamic image...[Show more]
|Collections||ANU Research Publications|
|Source:||IEEE Transactions on Pattern Analysis and Machine Intelligence|
|01_Bilen_Action_Recognition_with_2017.pdf||7.42 MB||Adobe PDF||Request a copy|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.