Learning Aligned Cross-Modal Representations from Weakly Aligned Data
Name
Torralba_Learning aligned.pdf
Size
6.24 MB
Format
Adobe PDF
Checksum (MD5)
ce141a27e12f8b4a7280feb6d6c33025
Author(s)
Castrejon, Lluis
Pirsiavash, Hamed
Aytar, Yusuf
Vondrick, Carl Martin
Torralba, Antonio
Date Issued
December 2016
Journal
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Castrejon, Lluis, et al. "Learning Aligned Cross-Modal Representations from Weakly Aligned Data." 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 27-30 June 2016, Las Vegas, NV, IEEE, 2016, pp. 2940–49.
Version
Original manuscript
Abstract
People can recognize scenes across many different modalities beyond natural images. In this paper, we investigate how to learn cross-modal scene representations that transfer across modalities. To study this problem, we introduce a new cross-modal scene dataset. While convolutional neural networks can categorize cross-modal scenes well, they also learn an intermediate representation not aligned across modalities, which is undesirable for crossmodal transfer applications. We present methods to regularize cross-modal convolutional neural networks so that they have a shared representation that is agnostic of the modality. Our experiments suggest that our scene representation can help transfer representations across modalities for retrieval. Moreover, our visualizations suggest that units emerge in the shared representation that tend to activate on consistent concepts independently of the modality.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
http://dx.doi.org/10.1109/CVPR.2016.321
