Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
International Journal of Computer Vision
A Bayesian Hierarchical Model for Learning Natural Scene Categories
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
A fast learning algorithm for deep belief nets
Neural Computation
A stochastic grammar of images
Foundations and Trends® in Computer Graphics and Vision
LabelMe: A Database and Web-Based Tool for Image Annotation
International Journal of Computer Vision
Computational Geometry: Algorithms and Applications
Computational Geometry: Algorithms and Applications
Learning reconfigurable scene representation by tangram model
WACV '12 Proceedings of the 2012 IEEE Workshop on the Applications of Computer Vision
Error bounds for convolutional codes and an asymptotically optimum decoding algorithm
IEEE Transactions on Information Theory
Reconfigurable models for scene recognition
CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Hi-index | 0.00 |
A typical scene category, e.g., street and beach, contains an enormous number (e.g., in the order of 104 to 105) of distinct scene configurations that are composed of objects and regions of varying shapes in different layouts. A well-known representation that can effectively address such complexity is the family of compositional models; however, learning the structures of the hierarchical compositional models remains a challenging task in vision. The objective of this paper is to present an efficient method for learning such models from a set of scene configurations. We start with an over-complete representation called Hierarchical Space Tiling (HST), which quantizes the huge and continuous scene configuration space in an And-Or tree (AOT). This hierarchical AOT can generate a combinatorial number of configurations (in the order of 1031) through a small dictionary of elements. Then we estimate the HST/AOT model through a learning-by-parsing strategy, which iteratively updates the HST/AOT parameters while constructing the optimal parse trees for each training configuration. Finally we prune out the branches with zero or low probability to obtain a much smaller HST/AOT. The HST quantization allows us to transfer the challenging structure-learning problem to a tractable parameter-learning problem. We evaluate the representation in three aspects. (i) Coding efficiency. We show the learned representation can approximate valid configurations with less errors using smaller number of primitives than other popular representations. (ii) Semantic power of learning. The learned representation is less ambiguous in parsing configuration and has semantically meaningful inner concepts. It captures both the diversity and the frequency (prior) of the scene configurations. (iii) Scene classification. The model is not only fully generative but also yields discriminative scene classification performance which outperforms the state-of-the-art methods.