Title :
Predicting Object Dynamics in Scenes
Author :
Fouhey, David F. ; Zitnick, C. Lawrence
Abstract :
Given a static scene, a human can trivially enumerate the myriad of things that can happen next and characterize the relative likelihood of each. In the process, we make use of enormous amounts of commonsense knowledge about how the world works. In this paper, we investigate learning this commonsense knowledge from data. To overcome a lack of densely annotated spatiotemporal data, we learn from sequences of abstract images gathered using crowd-sourcing. The abstract scenes provide both object location and attribute information. We demonstrate qualitatively and quantitatively that our models produce plausible scene predictions on both the abstract images, as well as natural images taken from the Internet.
Keywords :
image sequences; learning (artificial intelligence); natural scenes; outsourcing; spatiotemporal phenomena; abstract image sequences; abstract images; abstract scenes; attribute information; commonsense knowledge learning; crowdsourcing; densely annotated spatiotemporal data; natural images; object dynamics prediction; object location; qualitative analysis; quantitative analysis; static scene; Abstracts; Cognition; Computational modeling; Dynamics; Predictive models; Spatiotemporal phenomena; Training; commonsense knowledge; prediction; scene dynamics; scene understanding;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2014 IEEE Conference on
Conference_Location :
Columbus, OH
DOI :
10.1109/CVPR.2014.260