Improved Scoring Models for Semantic Image Retrieval Using Scene Graphs
Image retrieval via a structured query is explored in Johnson, et al. [7]. The query is structured as a scene graph and a graphical model is generated from the scene graph's object, attribute, and relationship structure. Inference is performed on the graphical model with candidate images and th...
| Main Author: | |
|---|---|
| Format: | Others |
| Published: |
PDXScholar
2017
|
| Subjects: | |
| Online Access: | https://pdxscholar.library.pdx.edu/open_access_etds/3879 https://pdxscholar.library.pdx.edu/cgi/viewcontent.cgi?article=4892&context=open_access_etds |
| id |
ndltd-pdx.edu-oai-pdxscholar.library.pdx.edu-open_access_etds-4892 |
|---|---|
| record_format |
oai_dc |
| spelling |
ndltd-pdx.edu-oai-pdxscholar.library.pdx.edu-open_access_etds-48922019-10-20T04:58:30Z Improved Scoring Models for Semantic Image Retrieval Using Scene Graphs Conser, Erik Timothy Image retrieval via a structured query is explored in Johnson, et al. [7]. The query is structured as a scene graph and a graphical model is generated from the scene graph's object, attribute, and relationship structure. Inference is performed on the graphical model with candidate images and the energy results are used to rank the best matches. In [7], scene graph objects that are not in the set of recognized objects are not represented in the graphical model. This work proposes and tests two approaches for modeling the unrecognized objects in order to leverage the attribute and relationship models to improve image retrieval performance. 2017-09-28T07:00:00Z text application/pdf https://pdxscholar.library.pdx.edu/open_access_etds/3879 https://pdxscholar.library.pdx.edu/cgi/viewcontent.cgi?article=4892&context=open_access_etds Dissertations and Theses PDXScholar Content-based image retrieval Semantic computing Image processing -- Digital techniques Computer vision Computer Sciences |
| collection |
NDLTD |
| format |
Others
|
| sources |
NDLTD |
| topic |
Content-based image retrieval Semantic computing Image processing -- Digital techniques Computer vision Computer Sciences |
| spellingShingle |
Content-based image retrieval Semantic computing Image processing -- Digital techniques Computer vision Computer Sciences Conser, Erik Timothy Improved Scoring Models for Semantic Image Retrieval Using Scene Graphs |
| description |
Image retrieval via a structured query is explored in Johnson, et al. [7]. The query is structured as a scene graph and a graphical model is generated from the scene graph's object, attribute, and relationship structure. Inference is performed on the graphical model with candidate images and the energy results are used to rank the best matches. In [7], scene graph objects that are not in the set of recognized objects are not represented in the graphical model. This work proposes and tests two approaches for modeling the unrecognized objects in order to leverage the attribute and relationship models to improve image retrieval performance. |
| author |
Conser, Erik Timothy |
| author_facet |
Conser, Erik Timothy |
| author_sort |
Conser, Erik Timothy |
| title |
Improved Scoring Models for Semantic Image Retrieval Using Scene Graphs |
| title_short |
Improved Scoring Models for Semantic Image Retrieval Using Scene Graphs |
| title_full |
Improved Scoring Models for Semantic Image Retrieval Using Scene Graphs |
| title_fullStr |
Improved Scoring Models for Semantic Image Retrieval Using Scene Graphs |
| title_full_unstemmed |
Improved Scoring Models for Semantic Image Retrieval Using Scene Graphs |
| title_sort |
improved scoring models for semantic image retrieval using scene graphs |
| publisher |
PDXScholar |
| publishDate |
2017 |
| url |
https://pdxscholar.library.pdx.edu/open_access_etds/3879 https://pdxscholar.library.pdx.edu/cgi/viewcontent.cgi?article=4892&context=open_access_etds |
| work_keys_str_mv |
AT consereriktimothy improvedscoringmodelsforsemanticimageretrievalusingscenegraphs |
| _version_ |
1719272040493481984 |