All issues
Predecessor
41.28 Media Engineering(ME)
Displaying 1-4 of 4 articles from this issue
- |<
- <
- 1
- >
- >|
-
Pages Cover1-
Published: 2017
Released on J-STAGE: August 25, 2021
CONFERENCE PROCEEDINGS FREE ACCESSDownload PDF (111K) -
Pages Cover2-
Published: 2017
Released on J-STAGE: August 25, 2021
CONFERENCE PROCEEDINGS FREE ACCESSDownload PDF (140K) -
Shuhei TARASHIMA, Takayuki KUROZUMI, Tetsuya KINEBUCHISession ID: ME2017-89
Published: 2017
Released on J-STAGE: August 25, 2021
CONFERENCE PROCEEDINGS FREE ACCESSIn this paper we propose to build large-scale datasets for learning local descriptors via mining recurring visual patterns. Such recurring patterns are discovered via partitioning correspondence graphs where each node represents a correspondence (i.e., similar keypoint pair) and each edge represents a geometric affinity between a correspondence pair. We evaluate our approach on a publicly available dataset and demonstrate that our approach is more efficient than an existing recurring pattern mining method. We also show that a descriptor learned from the datasets with our approach achieves superior performance on an image retrieval task than existing descriptors.View full abstractDownload PDF (681K) -
Pages 96-
Published: 2017
Released on J-STAGE: August 25, 2021
CONFERENCE PROCEEDINGS FREE ACCESSDownload PDF (131K)
- |<
- <
- 1
- >
- >|