Deep Head Pose: Gaze-Direction Estimation in Multimodal Video
- Submitting institution
-
Queen's University of Belfast
- Unit of assessment
- 12 - Engineering
- Output identifier
- 74444334
- Type
- D - Journal article
- DOI
-
10.1109/TMM.2015.2482819
- Title of journal
- IEEE Transactions on Multimedia
- Article number
- -
- First page
- 2094
- Volume
- 17
- Issue
- 11
- ISSN
- 1520-9210
- Open access status
- Out of scope for open access requirements
- Month of publication
- September
- Year of publication
- 2015
- 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
-
1
- Research group(s)
-
C - Electrical and Electronic
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The work presented in this paper is the first real-time unification of depth and colour images via deep learning which spans face detection, tracking and recognition over high-resolution and low-resolution (surveillance) sensing domains. New applications are demonstrated: human attention and interaction modelling. As a result Robertson founding CTO of Anyvision ltd. attracted an initial international investment of $5m based on a value of $20m (CEO: eylon@anyvision.co). The algorithms presented in this paper have led to contracts with multinational security organisations (e.g. NCS, zhangyu@ncs.com.sg) and the establishment of a UK-leading research centre in Belfast for visual security (www.anyvision.co).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -