@inproceedings{26061bd453e044c6bf8ff070fbcff0a6,
title = "Spot On: Action Localization from Pointly-Supervised Proposals",
abstract = "We strive for spatio-temporal localization of actions in videos. The state-of-the-art relies on action proposals at test time and selects the best one with a classifier trained on carefully annotated box annotations. Annotating action boxes in video is cumbersome, tedious, and error prone. Rather than annotating boxes, we propose to annotate actions in video with points on a sparse subset of frames only. We introduce an overlap measure between action proposals and points and incorporate them all into the objective of a non-convex Multiple Instance Learning optimization. Experimental evaluation on the UCF Sports and UCF 101 datasets shows that (i) spatio-temporal proposals can be used to train classifiers while retaining the localization performance, (ii) point annotations yield results comparable to box annotations while being significantly faster to annotate, (iii) with a minimum amount of supervision our approach is competitive to the state-of-the-art. Finally, we introduce spatio-temporal action annotations on the train and test videos of Hollywood2, resulting in Hollywood2Tubes, available at http://tinyurl.com/hollywood2tubes.",
keywords = "Action localization, Action proposals",
author = "Pascal Mettes and {van Gemert}, Jan and CGM Snoek",
year = "2016",
doi = "10.1007/978-3-319-46454-1_27",
language = "English",
isbn = "978-3-319-46453-4",
volume = "5",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "437--453",
editor = "B. Leibe and J. Matas and N. Sebe and M. Welling",
booktitle = "Computer Vision ECCV 2016",
note = "ECCV 2016 : 29th European Conference on Computer Vision ; Conference date: 08-10-2016 Through 16-10-2016",
}