Seeing the Arrow of Time

Author

Pickup, Lyndsey C. ; Zheng Pan ; Donglai Wei ; YiChang Shih ; Changshui Zhang ; Zisserman, Andrew ; Scholkopf, Bernhard ; Freeman, William T.

Author_Institution

Dept. of Eng. Sci., Univ. of Oxford, Oxford, UK

fYear

2014

fDate

23-28 June 2014

Firstpage

2043

Lastpage

2050

Abstract

We explore whether we can observe Time´s Arrow in a temporal sequence - is it possible to tell whether a video is running forwards or backwards? We investigate this somewhat philosophical question using computer vision and machine learning techniques. We explore three methods by which we might detect Time´s Arrow in video sequences, based on distinct ways in which motion in video sequences might be asymmetric in time. We demonstrate good video forwards/backwards classification results on a selection of YouTube video clips, and on natively-captured sequences (with no temporally-dependent video compression), and examine what motions the models have learned that help discriminate forwards from backwards time.

Keywords

computer vision; image classification; image motion analysis; image sequences; learning (artificial intelligence); object detection; social networking (online); video signal processing; Time Arrow detection; YouTube video clips; computer vision; machine learning techniques; motion; video forward-backward classification results; video sequences; Histograms; Physics; Support vector machines; Testing; Training; Visualization; YouTube; Time; forwards/backwards; video;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on

Conference_Location

Columbus, OH

Type

conf

DOI

10.1109/CVPR.2014.262

Filename

6909659