Comprehensible Video Thumbnails
- Submitting institution
-
The University of Surrey
- Unit of assessment
- 12 - Engineering
- Output identifier
- 9012483_2
- Type
- D - Journal article
- DOI
-
10.1111/cgf.12550
- Title of journal
- Computer Graphics Forum
- Article number
- -
- First page
- 167-177
- Volume
- 34
- Issue
- 2
- ISSN
- 0167-7055
- Open access status
- Out of scope for open access requirements
- Month of publication
- -
- 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
-
-
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Most prior work selects best keyframes from video to make the thumbnails. Uniquely, this work analyses the video at the object level - finding the important objects and arranging them to tell a visual story of the video content using object composition augmented with motion cues. It is being considered for productization within Adobe.
Randomised user trials show proposed automatic technique beats state of the art, even competing techniques that use human input in the loop.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -