Online Real-Time Multiple Spatiotemporal Action Localisation and Prediction
- Submitting institution
-
Oxford Brookes University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- FC2
- Type
- E - Conference contribution
- DOI
-
10.1109/iccv.2017.393
- Title of conference / published proceedings
- 2017 IEEE International Conference on Computer Vision (ICCV)
- First page
- 3657
- Volume
- -
- Issue
- -
- ISSN
- 2380-7504
- Open access status
- Not compliant
- Month of publication
- December
- Year of publication
- 2017
- URL
-
-
- 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
-
4
- Research group(s)
-
-
- Citation count
- 50
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This is a seminal paper which proposed a methodology for detecting multiple human actions in streaming videos. This paper has much influenced subsequent work on action detection by other researchers, and led to 6/7 follow-up papers at ICCV/ECCV. We built on this contribution to win grants from InnovateUK (2 KTPs), the €4,3M EU project SARAS on surgical robotics, a Huawei research agreement on activity detection and a UKIERI exchange with IIT Bombay (£1.5M in total), plus an upcoming spin-off company (Olympia.ai), taking the lab from few students to a project 35 people in 2021.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -