Name
Abstract | ||
|---|---|---|
Contextual modeling is a critical issue in scene understanding. Object detection accuracy can be improved by exploiting tendencies that are common among object configurations. However, conventional contextual models only exploit the tendencies of normal objects; abnormal objects that do not follow the same tendencies are hard to detect through contextual model. This paper proposes a novel generative model that detects abnormal objects by meeting four proposed criteria of success. This model generates normal as well as abnormal objects, each following their respective tendencies. Moreover, this generation is controlled by a latent scene variable. All latent variables of the proposed model are predicted through optimization via population-based Markov Chain Monte Carlo, which has a relatively short convergence time. We present a new abnormal dataset classified into three categories to thoroughly measure the accuracy of the proposed model for each category; the results demonstrate the superiority of our proposed approach over existing methods. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1007/978-3-642-33712-3_47 | ECCV (3) |
Keywords | Field | DocType |
contextual model,abnormal object detection,detection accuracy,new abnormal dataset,novel generative model,canonical scene-based contextual model,contextual modeling,proposed criterion,conventional contextual model,abnormal object,sampling,generative model | Convergence (routing),Population,Markov chain Monte Carlo,Computer science,Latent variable,Artificial intelligence,Object detection,Computer vision,Pattern recognition,Contextual design,Sampling (statistics),Machine learning,Generative model | Conference |
Volume | ISSN | Citations |
7574 | 0302-9743 | 7 |
PageRank | References | Authors |
0.45 | 20 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sangdon Park | 1 | 7 | 0.79 |
| Wonsik Kim | 2 | 81 | 7.44 |
| Kyoung Mu Lee | 3 | 3228 | 153.84 |