On Encoding Temporal Evolution for Real-time Action Prediction

Fahimeh Rezazadegan, Sareh Shirazi, Mahsa Baktashmotlagh, Larry S. Davis

Research output: Contribution to journalArticle

Abstract

Anticipating future actions is a key component of intelligence, specifically when it applies to realtime systems, such as robots or autonomous cars. While recent works have addressed prediction of raw RGB pixel values, we focus on anticipating the motion evolution in future video frames. To this end, we construct dynamic images (DIs) by summarising moving pixels through a sequence of future frames. We train a convolutional LSTMs to predict the next DIs based on an unsupervised learning process, and then recognise the activity associated with the predicted DI. We demonstrate the effectiveness of our approach on 3 benchmark action datasets showing that despite running on videos with complex activities, our approach is able to anticipate the next human action with high accuracy and obtain better results than the state-of-the-art
methods.
Original languageEnglish
Number of pages7
JournalInternational Journal of Computer Vision
Publication statusSubmitted - 2018

Fingerprint Dive into the research topics of 'On Encoding Temporal Evolution for Real-time Action Prediction'. Together they form a unique fingerprint.

  • Cite this

    Rezazadegan, F., Shirazi, S., Baktashmotlagh, M., & Davis, L. S. (2018). On Encoding Temporal Evolution for Real-time Action Prediction. Manuscript submitted for publication.