Anticipating Visual Representations from Unlabeled Video
| dc.contributor.author | Vondrick, Carl | |
| dc.contributor.author | Pirsiavash, Hamed | |
| dc.contributor.author | Torralba, Antonio | |
| dc.date.accessioned | 2019-06-28T16:22:58Z | |
| dc.date.available | 2019-06-28T16:22:58Z | |
| dc.date.issued | 2016-11-30 | |
| dc.description.abstract | Anticipating actions and objects before they start or appear is a difficult problem in computer vision with several real-world applications. This task is challenging partly because it requires leveraging extensive knowledge of the world that is difficult to write down. We believe that a promising resource for efficiently learning this knowledge is through readily available unlabeled video. We present a framework that capitalizes on temporal structure in unlabeled video to learn to anticipate human actions and objects. The key idea behind our approach is that we can train deep networks to predict the visual representation of images in the future. Visual representations are a promising prediction target because they encode images at a higher semantic level than pixels yet are automatic to compute. We then apply recognition algorithms on our predicted representation to anticipate objects and actions. We experimentally validate this idea on two datasets, anticipating actions one second in the future and objects five seconds in the future. | en_US |
| dc.description.sponsorship | This work was supported by NSF grant IIS-1524817, and by a Google faculty research award to AT, and a Google PhD fellowship to CV. | en_US |
| dc.description.uri | https://ieeexplore.ieee.org/document/7780387 | en_US |
| dc.format.extent | 9 pages | en_US |
| dc.genre | conference papers and proceedings preprints | en_US |
| dc.identifier | doi:10.13016/m26ion-fjjh | |
| dc.identifier.citation | Carl Vondrick, et.al , Anticipating Visual Representations from Unlabeled Video, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), DOI: 10.1109/CVPR.2016.18 | en_US |
| dc.identifier.uri | https://doi.org/10.1109/CVPR.2016.18 | |
| dc.identifier.uri | http://hdl.handle.net/11603/14316 | |
| dc.language.iso | en_US | en_US |
| dc.publisher | IEEE | en_US |
| dc.relation.isAvailableAt | The University of Maryland, Baltimore County (UMBC) | |
| dc.relation.ispartof | UMBC Computer Science and Electrical Engineering Department Collection | |
| dc.relation.ispartof | UMBC Faculty Collection | |
| dc.rights | This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author. | |
| dc.rights | © 2016 IEEE | |
| dc.subject | Visualization | en_US |
| dc.subject | Prediction algorithms | en_US |
| dc.subject | Computer vision | en_US |
| dc.subject | Predictive models | en_US |
| dc.subject | Semantics | en_US |
| dc.subject | Biological system modeling | en_US |
| dc.subject | Network architecture | en_US |
| dc.subject | video signal processing | en_US |
| dc.subject | deep networks | en_US |
| dc.subject | semantic level | en_US |
| dc.title | Anticipating Visual Representations from Unlabeled Video | en_US |
| dc.type | Text | en_US |