Details
| Original language | English |
|---|---|
| Title of host publication | ICMR 2015 |
| Subtitle of host publication | Proceedings of the 2015 ACM International Conference on Multimedia Retrieval |
| Pages | 187-194 |
| Number of pages | 8 |
| ISBN (electronic) | 9781450332743 |
| Publication status | Published - 22 Jun 2015 |
| Event | 5th ACM International Conference on Multimedia Retrieval, ICMR 2015 - Shanghai, China Duration: 23 Jun 2015 → 26 Jun 2015 |
Publication series
| Name | ICMR 2015 - Proceedings of the 2015 ACM International Conference on Multimedia Retrieval |
|---|
Abstract
When selecting important photos from a personal photo collection - e.g. for creating an enjoyable sub-collection for revisiting or preservation - photos are not considered in isolation. Therefore, collection-level criteria are also taken into account by automated photo selection methods. However, the typical two-step process of first clustering and subsequently picking from the clusters seems to overstress coverage as a criterion when applied to the task of selecting the photos most important to a user. We, therefore, propose a novel expectation-oriented photo selection method, which combines a variety of collection-level and image-level selection criteria in a exible way. In our evaluation, which is based on large real-world personal photo collections with overall more than 18,000 images, we show that our method outperforms state-of-the-art photo selection methods. In addition, the proposed method does not rely on any manual annotations, making it applicable in realistic settings of personal photo collections.
Keywords
- Clustering, Coverage, Photo selection, User expectations
ASJC Scopus subject areas
- Computer Science(all)
- Computer Graphics and Computer-Aided Design
- Computer Science(all)
- Software
- Computer Science(all)
- Computer Vision and Pattern Recognition
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
ICMR 2015 : Proceedings of the 2015 ACM International Conference on Multimedia Retrieval. 2015. p. 187-194 (ICMR 2015 - Proceedings of the 2015 ACM International Conference on Multimedia Retrieval).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - To keep or not to keep
T2 - 5th ACM International Conference on Multimedia Retrieval, ICMR 2015
AU - Ceroni, Andrea
AU - Solachidis, Vassilios
AU - Niederée, Claudia
AU - Papadopoulou, Olga
AU - Kanhabua, Nattiya
AU - Mezaris, Vasileios
N1 - Funding Information: This work was partially funded by the European Commission in the context of the FP7 ICT project ForgetIT (under grant no: 600826).
PY - 2015/6/22
Y1 - 2015/6/22
N2 - When selecting important photos from a personal photo collection - e.g. for creating an enjoyable sub-collection for revisiting or preservation - photos are not considered in isolation. Therefore, collection-level criteria are also taken into account by automated photo selection methods. However, the typical two-step process of first clustering and subsequently picking from the clusters seems to overstress coverage as a criterion when applied to the task of selecting the photos most important to a user. We, therefore, propose a novel expectation-oriented photo selection method, which combines a variety of collection-level and image-level selection criteria in a exible way. In our evaluation, which is based on large real-world personal photo collections with overall more than 18,000 images, we show that our method outperforms state-of-the-art photo selection methods. In addition, the proposed method does not rely on any manual annotations, making it applicable in realistic settings of personal photo collections.
AB - When selecting important photos from a personal photo collection - e.g. for creating an enjoyable sub-collection for revisiting or preservation - photos are not considered in isolation. Therefore, collection-level criteria are also taken into account by automated photo selection methods. However, the typical two-step process of first clustering and subsequently picking from the clusters seems to overstress coverage as a criterion when applied to the task of selecting the photos most important to a user. We, therefore, propose a novel expectation-oriented photo selection method, which combines a variety of collection-level and image-level selection criteria in a exible way. In our evaluation, which is based on large real-world personal photo collections with overall more than 18,000 images, we show that our method outperforms state-of-the-art photo selection methods. In addition, the proposed method does not rely on any manual annotations, making it applicable in realistic settings of personal photo collections.
KW - Clustering
KW - Coverage
KW - Photo selection
KW - User expectations
UR - http://www.scopus.com/inward/record.url?scp=84962367662&partnerID=8YFLogxK
U2 - 10.1145/2671188.2749372
DO - 10.1145/2671188.2749372
M3 - Conference contribution
AN - SCOPUS:84962367662
T3 - ICMR 2015 - Proceedings of the 2015 ACM International Conference on Multimedia Retrieval
SP - 187
EP - 194
BT - ICMR 2015
Y2 - 23 June 2015 through 26 June 2015
ER -