Compact Deep Aggregation for Set Retrieval
Abstract
The objective of this work is to learn a compact embedding of a set of descriptors that is suitable for efficient retrieval and ranking, whilst maintaining discriminability of the individual descriptors. We focus on a specific example of this general problem – that of retrieving images containing multiple faces from a large scale dataset of images. Here the set consists of the face descriptors in each image, and given a query for multiple identities, the goal is then to retrieve, in order, images which contain all the identities, all but one, etc.
Cite
Text
Zhong et al. "Compact Deep Aggregation for Set Retrieval." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11018-5_36Markdown
[Zhong et al. "Compact Deep Aggregation for Set Retrieval." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/zhong2018eccvw-compact/) doi:10.1007/978-3-030-11018-5_36BibTeX
@inproceedings{zhong2018eccvw-compact,
title = {{Compact Deep Aggregation for Set Retrieval}},
author = {Zhong, Yujie and Arandjelovic, Relja and Zisserman, Andrew},
booktitle = {European Conference on Computer Vision Workshops},
year = {2018},
pages = {413-430},
doi = {10.1007/978-3-030-11018-5_36},
url = {https://mlanthology.org/eccvw/2018/zhong2018eccvw-compact/}
}