Weakly supervised activity analysis with spatio-temporal localisation
- Submitting institution
-
The University of Leeds
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- UOA11-190
- Type
- D - Journal article
- DOI
-
10.1016/j.neucom.2016.08.032
- Title of journal
- Neurocomputing
- Article number
- -
- First page
- 778
- Volume
- 216
- Issue
- -
- ISSN
- 0925-2312
- Open access status
- Compliant
- Month of publication
- August
- Year of publication
- 2016
- URL
-
https://doi.org/10.1016/j.neucom.2016.08.032
- Supplementary information
-
-
- 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
-
6
- Research group(s)
-
B - AI (Artificial Intelligence)
- Citation count
- 3
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Significance: In computer vision, an increasing number of weakly annotated videos have become available, due to the fact it is often difficult and time consuming to annotate all the details in the videos collected. The results of this paper provide a way of exploiting such weak annotation to significantly improve learned activity models. The research was exploited in the DARPA Mind’s Eye research program in which Leeds was partnered with SRI and Maryland.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
