SSPR & SPR '08 Proceedings of the 2008 Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition
Comparing compact codebooks for visual categorization
Computer Vision and Image Understanding
Region Contextual Visual Words for scene categorization
Expert Systems with Applications: An International Journal
Semantics extraction from images
Knowledge-driven multimedia information extraction and ontology evolution
Novelty detection using graphical models for semantic room classification
EPIA'11 Proceedings of the 15th Portugese conference on Progress in artificial intelligence
A novel object categorization model with implicit local spatial relationship
ISNN'10 Proceedings of the 7th international conference on Advances in Neural Networks - Volume Part II
| Hi-index | 0.00 |
Semantic scene classification is still a challenging problem in computer vision. In contrast to the common approach of using low-level features computed from the scene, our approach uses explicit semantic object detectors and scene configuration models. To overcome faulty semantic detectors, it is critical to develop a region-based, generative model of outdoor scenes based on characteristic objects in the scene and spatial relationships between them. Since a fully connected scene configuration model is intractable, we chose to model pairwise relationships between regions and estimate scene probabilities using loopy belief propagation on a factor graph. We demonstrate the promise of this approach on a set of over 2000 outdoor photographs, comparing it with existing discriminative approaches and those using low-level features.