Paper Info
Title
Video Primal Sketch: A Unified Middle-Level Representation for Video.
Abstract
This paper presents a middle-level video representation named video primal sketch (VPS), which integrates two regimes of models: (i) sparse coding model using static or moving primitives to explicitly represent moving corners, lines, feature points, etc., (ii) FRAME /MRF model reproducing feature statistics extracted from input video to implicitly represent textured motion, such as water and fire. The feature statistics include histograms of spatio-temporal filters and velocity distributions. This paper makes three contributions to the literature: (i) Learning a dictionary of video primitives using parametric generative models; (ii) Proposing the spatio-temporal FRAME and motion-appearance FRAME models for modeling and synthesizing textured motion; and (iii) Developing a parsimonious hybrid model for generic video representation. Given an input video, VPS selects the proper models automatically for different motion patterns and is compatible with high-level action representations. In the experiments, we synthesize a number of textured motion; reconstruct real videos using the VPS; report a series of human perception experiments to verify the quality of reconstructed videos; demonstrate how the VPS changes over the scale transition in videos; and present the close connection between VPS and high-level action models.
Year
DOI
Venue
2015
10.1007/s10851-015-0563-2
Journal of Mathematical Imaging and Vision
Keywords
Field
DocType
Middle-level vision,Video representation,Textured motion,Dynamic texture synthesis,Primal sketch
Computer vision,Histogram,Block-matching algorithm,Neural coding,Computer science,Motion compensation,Parametric statistics,Artificial intelligence,Generative grammar,Sketch
Journal
Volume
Issue
ISSN
abs/1502.02965
2
0924-9907
Citations 
PageRank 
References 
4
0.39
29
Authors
3
Name
Order
Citations
PageRank
Zhi Han122518.58
Zongben Xu23203198.88
Song-Chun Zhu36580741.75