Cross Modal Deep Model and Gaussian Process Based Model for MSR-Bing Challenge

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 先进时空数据分析与学习

	Cross Modal Deep Model and Gaussian Process Based Model for MSR-Bing Challenge
	Jian Wang; Cuicui Kang; Yonghao He; Shiming Xiang; Chunhong Pan; He,Yonghao
	2014
会议名称	ACM Multimedia 2014
会议录名称	ACM International Conference on Multimedia
页码	225-228
会议日期	2014
会议地点	American
摘要	In the MSR-Bing Image Retrieval Challenge, the contestants are required to design a system that can score the query-image pairs based on the relevance between queries and images. To address this problem, we propose a regression based cross modal deep learning model and a Gaussian Process scoring model. The regression based cross modal deep learning model takes the image features and query features as inputs respectively and outputs the relevance scores directly. The Gaussian Process scoring model regards the challenge as a ranking problem and utilizes the click (or pseudo click) information from both the training set and the development set to predict the relevance scores. The proposed models are used in different situations: matched and miss-matched queries. Experiments on the development set show the effectiveness of the proposed models.
关键词	Image Retrieval Deep Network Gaussian Process Convolutional Neural Network Clickthrougth Data
收录类别	EI
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/4739
专题	多模态人工智能系统全国重点实验室_先进时空数据分析与学习
通讯作者	He,Yonghao
推荐引用方式 GB/T 7714	Jian Wang,Cuicui Kang,Yonghao He,et al. Cross Modal Deep Model and Gaussian Process Based Model for MSR-Bing Challenge[C],2014:225-228.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Cross Modal Deep Mod（1668KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载