CaltechAUTHORS
  A Caltech Library Service

Context Embedding Networks

Kim, Kun Ho and Mac Aodha, Oisin and Perona, Pietro (2018) Context Embedding Networks. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE , Piscataway, NJ, pp. 8679-8687. ISBN 978-1-5386-6420-9. http://resolver.caltech.edu/CaltechAUTHORS:20180622-113357959

[img] PDF - Accepted Version
See Usage Policy.

5Mb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20180622-113357959

Abstract

Low dimensional embeddings that capture the main variations of interest in collections of data are important for many applications. One way to construct these embeddings is to acquire estimates of similarity from the crowd. Similarity is a multi-dimensional concept that varies from individual to individual. However, existing models for learning crowd embeddings typically make simplifying assumptions such as all individuals estimate similarity using the same criteria, the list of criteria is known in advance, or that the crowd workers are not influenced by the data that they see. To overcome these limitations we introduce Context Embedding Networks (CENs). In addition to learning interpretable embeddings from images, CENs also model worker biases for different attributes along with the visual context i.e. the attributes highlighted by a set of images. Experiments on three noisy crowd annotated datasets show that modeling both worker bias and visual context results in more interpretable embeddings compared to existing approaches.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1109/CVPR.2018.00905DOIArticle
https://arxiv.org/abs/1710.01691arXivDiscussion Paper
ORCID:
AuthorORCID
Kim, Kun Ho0000-0002-9271-9631
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2018 IEEE. We thank Google for supporting the Visipedia project and AWS Research Credits for their donation.
Funders:
Funding AgencyGrant Number
GoogleUNSPECIFIED
Amazon Web ServicesUNSPECIFIED
Record Number:CaltechAUTHORS:20180622-113357959
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20180622-113357959
Official Citation:K. H. Kim, O. M. Aodha and P. Perona, "Context Embedding Networks," 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, 2018, pp. 8679-8687. doi: 10.1109/CVPR.2018.00905
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:87328
Collection:CaltechAUTHORS
Deposited By: Caroline Murphy
Deposited On:22 Jun 2018 21:41
Last Modified:21 Feb 2019 15:31

Repository Staff Only: item control page