Scene Recognition via Bi-enhanced Knowledge Space Learning

Scene Recognition via Bi-enhanced Knowledge Space Learning
复制标题

通过双增强知识空间学习进行场景识别

DOI:
10.1007/978-981-13-9190-3_23
复制
发表时间:
2018-12
期刊:
International Computer Symposium, 2018. 
影响因子:
--
通讯作者:
Changsheng Xu
Changsheng Xu
中科院分区:
其他
文献类型:
--
作者:
Jin Zhang;Bing-Kun Bao;Changsheng Xu

文献摘要

参考文献

被引文献

相似文献

场景识别是计算机视觉的标志性任务之一,因为它提供了物体识别和动作识别之外的丰富信息。很容易接受的是,同一类别的场景图像总是包含相同的基本对象和关系,例如“婚礼”的场景图像通常有新郎和新娘在他身边。根据这一观察,我们引入了一种新颖的想法,通过挖掘基本场景子图和学习双向增强知识空间来提高场景识别的准确性。基本场景子图描述了每个场景类的基本对象及其关系。通过整个图像上的全局表示和相应的基本场景子图上的局部表示来双重增强学习的知识空间。在名为 Scene 30 的构建数据集上的实验结果证明了我们提出的方法的有效性。
Scene recognition is one of the hallmark tasks in computer vision, as it provides rich information beyond object recognition and action recognition. It is easy to accept that scene images from the same class always include the same essential objects and relations, for example, scene images of “wedding” usually have bridegroom and bride next to him. Following this observation, we introduce a novel idea to boost the accuracy of scene recognition by mining essential scene sub-graph and learning a bi-enhanced knowledge space. The essential scene sub-graph describes the essential objects and their relations for each scene class. The learned knowledge space is bi-enhanced by global representation on the entire image and local representation on the corresponding essential scene sub-graph. Experimental results on the constructed dataset called Scene 30 demonstrate the effectiveness of our proposed method.
用于场景识别和领域适应的混合 CNN 和基于字典的模型
DOI: 10.1109/tcsvt.2015.2511543
发表时间: 2016-01
影响因子: 8.4
作者:
Guo-Sen Xie;Xu-Yao Zhang;Shuicheng Yan;Cheng-Lin Liu
通讯作者: Cheng-Lin Liu
DOI: 10.1109/iccv.2005.137
发表时间: 2005-10
期刊: Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1
影响因子: --
作者:
Erik B. Sudderth;A. Torralba;W. Freeman;A. Willsky
通讯作者: Erik B. Sudderth;A. Torralba;W. Freeman;A. Willsky
DOI: 10.1201/9781315213262-2
发表时间: 2017-09
期刊: --
影响因子: --
作者:
M. Stamp
通讯作者: M. Stamp
DOI: 10.1023/a:1011139631724
发表时间: 2001-01-01
影响因子: 19.5
作者:
Oliva, A;Torralba, A
通讯作者: Torralba, A
DOI: 10.1007/s11263-015-0816-y
发表时间: 2015-12-01
影响因子: 19.5
作者:
Russakovsky, Olga;Deng, Jia;Fei-Fei, Li
通讯作者: Fei-Fei, Li