Discovering Class-Specific Spatial Layouts for Scene Recognition

Scene image is a spatial composition of objects and background contexts and finding discriminative spatial layouts is critical for scene recognition. In this letter, we propose an ℓ1-regularized max-margin formulation to discover class-specific spatial layouts by jointly learning the image classifie...

全面介紹

Saved in:
書目詳細資料
Main Authors: Weng, Chaoqun, Wang, Hongxing, Yuan, Junsong, Jiang, Xudong
其他作者: School of Electrical and Electronic Engineering
格式: Article
語言:English
出版: 2017
主題:
在線閱讀:https://hdl.handle.net/10356/82238
http://hdl.handle.net/10220/43502
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
機構: Nanyang Technological University
語言: English
實物特徵
總結:Scene image is a spatial composition of objects and background contexts and finding discriminative spatial layouts is critical for scene recognition. In this letter, we propose an ℓ1-regularized max-margin formulation to discover class-specific spatial layouts by jointly learning the image classifier and the class-specific spatial layouts for scene recognition. Unlike previous methods that classify images into different categories either without considering the spatial layouts explicitly or only using class generic spatial layout, our proposed method can discover a sparse combination of class-specific spatial layouts for different scenes and boost the recognition performance. Experiments on scene-15, landuse-21, and MIT indoor-67 datasets validate the advantages of our proposed algorithm.