TenniSet: A dataset for dense fine-grained event recognition, localisation and description
| dc.contributor.author | Faulkner, H. | |
| dc.contributor.author | Dick, A. | |
| dc.contributor.conference | International Conference on Digital Image Computing: Techniques and Applications (DICTA 2017) (29 Nov 2017 - 1 Dec 2017 : Sydney, AUSTRALIA) | |
| dc.contributor.editor | Guo, Y. | |
| dc.contributor.editor | Li, H. | |
| dc.contributor.editor | Cai, W. | |
| dc.contributor.editor | Murshed, M. | |
| dc.contributor.editor | Wang, Z. | |
| dc.contributor.editor | Gao, J. | |
| dc.contributor.editor | Feng, D. | |
| dc.date.issued | 2017 | |
| dc.description.abstract | This paper introduces a new video understanding dataset which can be utilised for the related problems of event recognition, localisation and description in video. Our dataset consists of dense, well structured event annotations in untrimmed video of tennis matches. We also include highly detailed commentary style descriptions, which are heavily dependent on both the occurrence as well as the sequence of particular events. We use general deep learning techniques to acquire some initial baseline results on our dataset, without the need for explicit domain-specific assumptions. | |
| dc.description.statementofresponsibility | Hayden Faulkner, Anthony Dick | |
| dc.identifier.citation | Proceedings of the International Conference on Digital Image Computing: Techniques and Applications (DICTA 2017), 2017 / Guo, Y., Li, H., Cai, W., Murshed, M., Wang, Z., Gao, J., Feng, D. (ed./s), vol.2017-December, pp.1-8 | |
| dc.identifier.doi | 10.1109/DICTA.2017.8227494 | |
| dc.identifier.isbn | 1538628406 | |
| dc.identifier.isbn | 9781538628409 | |
| dc.identifier.orcid | Dick, A. [0000-0001-9049-7345] | |
| dc.identifier.uri | http://hdl.handle.net/2440/113022 | |
| dc.language.iso | en | |
| dc.publisher | IEEE | |
| dc.publisher.place | Piscataway, NJ | |
| dc.rights | ©2017 IEEE | |
| dc.source.uri | https://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=8226656 | |
| dc.title | TenniSet: A dataset for dense fine-grained event recognition, localisation and description | |
| dc.type | Conference paper | |
| pubs.publication-status | Published |