Abstract | ||
---|---|---|
This paper presents a hierarchical and compositional scene layout (i.e., spatial configuration) representation and a method of learning reconfigurable model for scene categorization. Three types of shape primitives (i.e., triangle, parallelogram and trapezoid), called "tans", are used to tile scene image lattice in a hierarchical and compositional way, and a directed acyclic And-Or graph (AOG) is proposed to organize the overcomplete dictionary of tan instances placed in image lattice, exploring a very large number of scene layouts. With certain "off-the-shelf" appearance features used for grounding terminal-nodes (i.e., tan instances) in the AOG, a scene layout is represented by the globally optimal parse tree learned via a dynamic programming algorithm from the AOG, which we call tangram model. Then, a scene category is represented by a mixture of tangram models discovered with an exemplar-based clustering method. On basis of the tangram model, we address scene categorization in two aspects: (i) Building a "tangram bank" representation for linear classifiers, which utilizes a collection of tangram models learned from all categories, and (ii) Building a tangram matching kernel for kernel-based classification, which accounts for all hidden spatial configurations in the AOG. In experiments, our methods are evaluated on three scene datasets for both the configurationlevel and semantic-level scene categorization, and outperform the spatial pyramid model consistently. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/TIP.2015.2498407 | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society |
Keywords | Field | DocType |
And-Or Graph,Dynamic Programming,Scene Categorization,Scene Layout,Tangram Model,Tangram model,and-or graph,dynamic programming,scene categorization,scene layout | Kernel (linear algebra),Dynamic programming,Computer vision,Categorization,Data set,Parallelogram,Parse tree,Pattern recognition,Computer science,Artificial intelligence,Pyramid,Cluster analysis | Journal |
Volume | Issue | ISSN |
25 | 1 | 1057-7149 |
Citations | PageRank | References |
4 | 0.38 | 39 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jun Zhu | 1 | 1926 | 154.82 |
Tianfu Wu | 2 | 331 | 26.72 |
Song-Chun Zhu | 3 | 6580 | 741.75 |
Xiaokang Yang | 4 | 3581 | 238.09 |