CASIA OpenIR  > 类脑智能研究中心
Improving context-sensitive similarity via smooth neighborhood for object retrieval
Song Bai; Shaoyan Sun; Xiang Bai; Zhaoxiang Zhang; Qi Tian
Source PublicationPattern Recognition
2018
Issue83Pages:353-364
AbstractDue to the ability of capturing the geometry structure of data manifold, context-sensitive similarity has demonstrated impressive performances in the retrieval task. The key idea of context-sensitive similarity is that the similarity between two data points can be more reliably estimated with the local context of other points in the affinity graph. Therefore, neighborhood selection is a crucial factor for those algorithms, which affects the performance dramatically. In this paper, we propose a new algorithm called Smooth Neighborhood (SN) that mines the neighborhood structure to satisfy the manifold assumption. By doing so, nearby points on the underlying manifold are guaranteed to yield similar neighbors as much as possible. Moreover, SN is adjusted to tackle multiple affinity graphs by imposing a weight learning paradigm, and this is the primary difference compared with related works which are only applicable with one affinity graph. Finally, we integrate SN with Sparse Contextual Activation (SCA), a representative context-sensitive similarity proposed recently. Extensive experimental results and comparisons manifest that with the neighborhood structure generated by SN, the proposed framework can yield state-of-the-art performances on shape retrieval, image retrieval and 3D model retrieval.
KeywordObject Retrieval Context-sensitive Similarity 3d Shape Re-ranking Rank Aggregation
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/21588
Collection类脑智能研究中心
Recommended Citation
GB/T 7714
Song Bai,Shaoyan Sun,Xiang Bai,et al. Improving context-sensitive similarity via smooth neighborhood for object retrieval[J]. Pattern Recognition,2018(83):353-364.
APA Song Bai,Shaoyan Sun,Xiang Bai,Zhaoxiang Zhang,&Qi Tian.(2018).Improving context-sensitive similarity via smooth neighborhood for object retrieval.Pattern Recognition(83),353-364.
MLA Song Bai,et al."Improving context-sensitive similarity via smooth neighborhood for object retrieval".Pattern Recognition .83(2018):353-364.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Song Bai]'s Articles
[Shaoyan Sun]'s Articles
[Xiang Bai]'s Articles
Baidu academic
Similar articles in Baidu academic
[Song Bai]'s Articles
[Shaoyan Sun]'s Articles
[Xiang Bai]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Song Bai]'s Articles
[Shaoyan Sun]'s Articles
[Xiang Bai]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.