Select Language

公开数据集

室内场景识别数据库

室内场景识别数据库

Scene:

Urban,Environment,Environment

Data Type:

2D Box,Classification
所需积分:10 去赚积分?
  • 419浏览
  • 4下载
  • 0点赞
  • 收藏
  • 分享

贡献者查看主页

Massachusetts Institute of Technology

The MIT community is driven by a shared purpose: to make a better world through education, research, and innovation. We are fun and quirky, elite but not elitist, inventive and artistic, obsessed with numbers, and welcoming to talented people regardless o

Data Preview ? 2.33G

    Data Structure ?

    *数据结构实际以真实数据为准

    Indoor scene recognition is a challenging open problem in high level vision. Most scene recognition models that work well for outdoor scenes perform poorly in the indoor domain. The main difficulty is that while some indoor scenes (e.g. corridors) can be well characterized by global spatial properties, others (e.g., bookstores) are better characterized by the objects they contain. More generally, to address the indoor scenes recognition problem we need a model that can exploit local and global discriminative information.

    evaluation

    For the results in the paper we use a subset of the dataset that has the same number of training and testing samples per class. The partition that we use is:

    1. TrainImages.txt: contains the file names of each training image. Total 67*80 images

    2. TestImages.txt: contains the file names of each test image. Total 67*20 images

    Paper
    A. Quattoni, and A.Torralba. Recognizing Indoor Scenes. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009.

    0相关评论
    ×

    帕依提提提温馨提示

    该数据集正在整理中,为您准备了其他渠道,请您使用

    注:部分数据正在处理中,未能直接提供下载,还请大家理解和支持。