Higher-order pooling of cnn features via kernel linearization for action recognition
ost successful deep learning algorithms for action recognition extend models designed for image-based tasks such as object recognition to video. Such extensions are typically trained for actions on single video frames or very short clips, and then their predictions from sliding-windows over the video sequence are pooled for recognizing the action at the sequence level. Usually this pooling step uses the first-order statistics of frame-level action predictions. In this paper, we explore the...[Show more]
|Collections||ANU Research Publications|
|Source:||Proceedings - 2017 IEEE Winter Conference on Applications of Computer Vision, WACV 2017|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.