Discovering Class-Specific Spatial Layouts for Scene Recognition

• Main Authors: Weng, Chaoqun, Wang, Hongxing, Yuan, Junsong, Jiang, Xudong
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2017
• Subjects: Discovering class-specific spatial layouts; Scene recognition
• Online Access: https://hdl.handle.net/10356/82238; http://hdl.handle.net/10220/43502
• Institution: Nanyang Technological University

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...