15-Scene Image Dataset

The initial 8 classes were collected by Oliva and Torralba [1], and then 5 categories were added by Fei-Fei and Perona [2]; finally, 2 additional categories were introduced by Lazebnik et al. [3]. <br>[1] A. Oliva and A. Torralba, “Modeling the shape of the scene: A holistic representation of the spatial envelope,” IJCV, 2001. <br>[2] L. Fei-Fei and P. Perona, “A bayesian hierarchical model for learning natural scene categories,” CVPR, 2005. <br>[3] S. Lazebnik, C. Schmid, and J. Ponce, “Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories,” CVPR, 2006. <br><br><br>

本数据集最初的8个类别由Oliva与Torralba[1]采集，随后Fei-Fei与Perona[2]新增了5个类别，最终Lazebnik等学者[3]又引入了2个额外类别。<br>[1] A. Oliva、A. Torralba，《场景形状建模：空间包络的整体表征》，IJCV，2001年。<br>[2] L. Fei-Fei、P. Perona，《用于自然场景类别学习的贝叶斯层次模型》，CVPR，2005年。<br>[3] S. Lazebnik、C. Schmid、J. Ponce，《超越特征袋：用于自然场景类别识别的空间金字塔匹配方法》，CVPR，2006年。<br><br><br>