Paper Info
Title
Feedback Loop Between High Level Semantics And Low Level Vision
Abstract
High level semantic analysis typically involves constructing a Markov network over detections from low level detectors to encode context and model relationships between them. In complex higher order networks (e.g. Markov Logic Networks), each detection can be part of many factors and the network size grows rapidly as a function of the number of detections. Hence to keep the network size small, a threshold is applied on the confidence measures of the detections to discard the less likely detections. A practical challenge is to decide what thresholds to use to discard noisy detections. A high threshold will lead to a high false dismissal rate. A low threshold can result in many detections including mostly noisy ones which leads to a large network size and increased computational requirements. We propose a feedback based incremental technique to keep the network size small. We initialize the network with detections above a high confidence threshold and then based on the high level semantics in the initial network, we incrementally select the relevant detections from the remaining ones that are below the threshold. We show three different ways of selecting detections which are based on three scoring functions that bound the increase in the optimal value of the objective function of network, with varying degrees of accuracy and computational cost. We perform experiments with an event recognition task in one-on-one basketball videos that uses Markov Logic Networks.
Year
DOI
Venue
2014
10.1007/978-3-319-16181-5_38
COMPUTER VISION - ECCV 2014 WORKSHOPS, PT II
Field
DocType
Volume
Network size,Computer vision,ENCODE,Confidence measures,Computer science,Markov chain,Feedback loop,Artificial intelligence,Detector,Event recognition,Semantics
Conference
8926
ISSN
Citations 
PageRank 
0302-9743
0
0.34
References 
Authors
13
3
Name
Order
Citations
PageRank
Varun K. Nagaraja1524.05
Vlad I. Morariu244128.13
Larry S. Davis3142012690.83