Deep canonical time warping for simultaneous alignment and representation learning of sequences
- Submitting institution
-
Imperial College of Science, Technology and Medicine
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2196
- Type
- D - Journal article
- DOI
-
10.1109/TPAMI.2017.2710047
- Title of journal
- IEEE transactions on Pattern Analysis and Machine Intelligence
- Article number
- 5
- First page
- 1128
- Volume
- 40
- Issue
- 5
- ISSN
- 2160-9292
- Open access status
- Compliant
- Month of publication
- June
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
10.1109/TPAMI.2017.2710047
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 18
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This novel machine learning algorithm for the alignment of heterogeneous time series, such as those from multimodal or multisensorial data, outperforms the concurrent popular approaches on several datasets. It is an extension of the CVPR’16 paper (https://doi.org/10.1109/CVPR.2016.552). The audio intelligence company audEERING (https://www.audeering.com), co-founded by Schuller, exploits the algorithm for emotion recognition and personal analysis.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
