Back to Search
Start Over
Online Action Detection
- Source :
- Computer Vision – ECCV 2016 ISBN: 9783319464534, ECCV (5), Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016 : proceedings, 5, 269-284
- Publication Year :
- 2016
- Publisher :
- Springer International Publishing, 2016.
-
Abstract
- In online action detection, the goal is to detect the start of an action in a video stream as soon as it happens. For instance, if a child is chasing a ball, an autonomous car should recognize what is going on and respond immediately. This is a very challenging problem for four reasons. First, only partial actions are observed. Second, there is a large variability in negative data. Third, the start of the action is unknown, so it is unclear over what time window the information should be integrated. Finally, in real world data, large within-class variability exists. This problem has been addressed before, but only to some extent. Our contributions to online action detection are threefold. First, we introduce a realistic dataset composed of 27 episodes from 6 popular TV series. The dataset spans over 16 h of footage annotated with 30 action classes, totaling 6,231 action instances. Second, we analyze and compare various baseline methods, showing this is a challenging problem for which none of the methods provides a good solution. Third, we analyze the change in performance when there is a variation in viewpoint, occlusion, truncation, etc. We introduce an evaluation protocol for fair comparison. The dataset, the baselines and the models will all be made publicly available to encourage (much needed) further research on online action detection on realistic data.
- Subjects :
- business.industry
Computer science
020207 software engineering
02 engineering and technology
Variation (game tree)
Machine learning
computer.software_genre
Action (philosophy)
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Artificial intelligence
Truncation (statistics)
business
Protocol (object-oriented programming)
computer
Subjects
Details
- ISBN :
- 978-3-319-46453-4
- ISBNs :
- 9783319464534
- Database :
- OpenAIRE
- Journal :
- Computer Vision – ECCV 2016 ISBN: 9783319464534, ECCV (5), Computer Vision – ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016 : proceedings, 5, 269-284
- Accession number :
- edsair.doi.dedup.....234a713cfd2f64600b4f885aae0c1e03