Loading...
Please wait, while we are loading the content...
Similar Documents
Learning reconfigurable scene representation by tangram model (2012)
| Content Provider | CiteSeerX |
|---|---|
| Author | Zhu, Jun Wu, Tianfu Zhu, Song-Chun Yang, Xiaokang Zhang, Wenjun |
| Description | This paper proposes a method to learn reconfigurable and sparse scene representation in the joint space of spa-tial configuration and appearance in a principled way. We call it the tangram model, which has three properties: (1) Unlike fixed structure of the spatial pyramid widely used in the literature, we propose a compositional shape dictionary organized in an And-Or directed acyclic graph (AOG) to quantize the space of spatial configurations. (2) The shape primitives (called tans) in the dictionary can be described by using any ”off-the-shelf ” appearance features according to different tasks. (3) A dynamic programming (DP) algo-rithm is utilized to learn the globally optimal parse tree in the joint space of spatial configuration and appearance. We demonstrate the tangram model in both a generative learn-ing formulation and a discriminative matching kernel. In experiments, we show that the tangram model is capable of capturing meaningful spatial configurations as well as ap-pearance for various scene categories, and achieves state-of-the-art classification performance on the LSP 15-class scene dataset and the MIT 67-class indoor scene dataset. In WACV |
| File Format | |
| Language | English |
| Publisher Date | 2012-01-01 |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
