Paper Info
Title
Max-Product Dynamical Systems And Applications To Audio-Visual Salient Event Detection In Videos
Abstract
This paper introduces a theory for max-product systems by analyzing them as discrete-time nonlinear dynamical systems that obey a superposition of a weighted maximum type and evolve on nonlinear spaces which we call complete weighted lattices. Special cases of such systems have found applications in speech recognition as weighted finite-state transducers and in belief propagation on graphical models. Our theoretical approach establishes their representation in state and input-output spaces using monotone lattice operators, finds analytically their state and output responses using nonlinear convolutions, studies their stability, and provides optimal solutions to solving max-product matrix equations. Further, we apply these systems to extend the Viterbi algorithm in HMMs by adding control inputs and model cognitive processes such as detecting audio and visual salient events in multimodal video streams, which shows good performance as compared to human attention.
Year
DOI
Venue
2015
10.1109/ICASSP.2015.7178378
2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP)
Keywords
Field
DocType
nonlinear systems, multimedia signal processing, lattices, minimax algebra, event detection, cognitive modeling
Superposition principle,Nonlinear system,Computer science,Theoretical computer science,Dynamical systems theory,Graphical model,Hidden Markov model,Viterbi algorithm,Belief propagation,Salient
Conference
ISSN
Citations 
PageRank 
1520-6149
2
0.38
References 
Authors
12
2
Name
Order
Citations
PageRank
Petros Maragos13733591.97
Petros Koutras2166.35