Paper Info
Title
Recognizing Car Fluents From Video
Abstract
Physical fluents, a term originally used by Newton [40], refers to time-varying object states in dynamic scenes. In this paper, we are interested in inferring the fluents of vehicles from video. For example, a door (hood, trunk) is open or closed through various actions, light is blinking to turn. Recognizing these fluents has broad applications, yet have received scant attention in the computer vision literature. Car fluent recognition entails a unified framework for car detection, car part localization and part status recognition, which is made difficult by large structural and appearance variations, low resolutions and occlusions. This paper learns a spatial-temporal And-Or hierarchical model to represent car fluents. The learning of this model is formulated under the latent structural SVM framework. Since there are no publicly related dataset, we collect and annotate a car fluent dataset consisting of car videos with diverse fluents. In experiments, the proposed method outperforms several highly related baseline methods in terms of car fluent recognition and car part localization.
Year
DOI
Venue
2016
10.1109/CVPR.2016.413
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
DocType
Volume
ISSN
Conference
abs/1603.08067
1063-6919
Citations 
PageRank 
References 
0
0.34
46
Authors
4
Name
Order
Citations
PageRank
Bo Li1634.01
Tianfu Wu233126.72
Caiming Xiong396969.56
Song-Chun Zhu46580741.75