Color-WISE: a system for image similarity retrieval using color

1997 ◽  
Author(s):  
Ishwar K. Sethi ◽  
Ioana L. Coman ◽  
Brian Day ◽  
F. Jiang ◽  
Dongge Li ◽  
...  
Keyword(s):  
Image Similarity ◽  
Similarity Retrieval

A Novel Model for Medical Image Similarity Retrieval

2013 ◽  
pp. 595-606 ◽  
Author(s):  
Pengyuan Li ◽  
Haiwei Pan ◽  
Jianzhong Li ◽  
Qilong Han ◽  
Xiaoqin Xie ◽  
...  
Keyword(s):  
Medical Image ◽  
Image Similarity ◽  
Similarity Retrieval ◽  
Novel Model

Brain CT Image Similarity Retrieval Method Based on Uncertain Location Graph

2014 ◽  
Vol 18 (2) ◽  
pp. 574-584 ◽  
Author(s):  
Haiwei Pan ◽  
Pengyuan Li ◽  
Qing Li ◽  
Qilong Han ◽  
Xiaoning Feng ◽  
...  
Keyword(s):  
Image Similarity ◽  
Ct Image ◽  
Retrieval Method ◽  
Similarity Retrieval ◽  
Brain Ct

scholarly journals POSE-AWARE EMBEDDING NETWORKS AND MULTI-MODAL IMAGE-LANGUAGE RETRIEVAL

2021 ◽  
Author(s):  
Domenico Curro
Keyword(s):  
Recent Work ◽  
Metric Spaces ◽  
Current Model ◽  
Metric Learning ◽  
Image Similarity ◽  
Similarity Retrieval ◽  
Human Pose ◽  
Human Joint

Inspired by recent work in human pose metric learning this thesis explores a family of pose-aware embedding networks designed for the purpose of image similarity retrieval. Circumventing the need for direct human joint localization, a series of CNN embedding networks are trained to respect a variety of Euclidean and language-primitive metric spaces. Querying with imagery alone presents certain limitations and thus this thesis proposes a multi-modal image-language embedding space, extending the current model to allow for language-primitive queries. This additional language mode provides the benefit of improving retrieval quality by 3% to 14% under the hit@k metric. Finally, two approaches are constructed to address the issues of conducting partial language-primitive queries, with the former generating maximally likely descriptors and the latter exploiting the network’s tendency to factorize the embedding space into (mostly) linearly separable sub-spaces. These two approaches improve upon recall by 13% and 17% over the provided baselines.

Sign in / Sign up

Export Citation Format

Share Document