TY - CONF T1 - Moving vistas: Exploiting motion for describing scenes T2 - 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Y1 - 2010 A1 - Shroff, N. A1 - Turaga,P. A1 - Chellapa, Rama KW - Application software KW - Automation KW - Chaos KW - chaotic system KW - Computational modeling KW - Computer vision KW - dynamic scene categorization KW - Educational institutions KW - HUMANS KW - image recognition KW - in the wild dynamic scene KW - Layout KW - motion attribute KW - natural scenes KW - Physics KW - probability KW - scene recognition KW - Snow KW - video data AB - Scene recognition in an unconstrained setting is an open and challenging problem with wide applications. In this paper, we study the role of scene dynamics for improved representation of scenes. We subsequently propose dynamic attributes which can be augmented with spatial attributes of a scene for semantically meaningful categorization of dynamic scenes. We further explore accurate and generalizable computational models for characterizing the dynamics of unconstrained scenes. The large intra-class variation due to unconstrained settings and the complex underlying physics present challenging problems in modeling scene dynamics. Motivated by these factors, we propose using the theory of chaotic systems to capture dynamics. Due to the lack of a suitable dataset, we compiled a dataset of `in-the-wild' dynamic scenes. Experimental results show that the proposed framework leads to the best classification rate among other well-known dynamic modeling techniques. We also show how these dynamic features provide a means to describe dynamic scenes with motion-attributes, which then leads to meaningful organization of the video data. JA - 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) PB - IEEE SN - 978-1-4244-6984-0 M3 - 10.1109/CVPR.2010.5539864 ER -