Молимо вас користите овај идентификатор за цитирање или овај линк до ове ставке:
https://open.uns.ac.rs/handle/123456789/5383
Назив: | Unsupervised tube extraction using transductive learning and dense trajectories | Аутори: | Puscas M. Sangineto E. Ćulibrk, Dubravko Sebe N. |
Датум издавања: | 17-феб-2015 | Часопис: | Proceedings of the IEEE International Conference on Computer Vision | Сажетак: | © 2015 IEEE. We address the problem of automatic extraction of foreground objects from videos. The goal is to provide a method for unsupervised collection of samples which can be further used for object detection training without any human intervention. We use the well known Selective Search approach to produce an initial still-image based segmentation of the video frames. This initial set of proposals is pruned and temporally extended using optical flow and transductive learning. Specifically, we propose to use Dense Trajectories in order to robustly match and track candidate boxes over different frames. The obtained box tracks are used to collect samples for unsupervised training of track-specific detectors. Finally, the detectors are run on the videos to extract the final tubes. The combination of appearance-based static "objectness" (Selective Search), motion information (Dense Trajectories) and transductive learning (detectors are forced to "overfit" on the unsupervised data used for training) makes the proposed approach extremely robust. We outperform state-of-the-art systems by a large margin on common benchmarks used for tube proposal evaluation. | URI: | https://open.uns.ac.rs/handle/123456789/5383 | ISBN: | 9781467383912 | ISSN: | 15505499 | DOI: | 10.1109/ICCV.2015.193 |
Налази се у колекцијама: | FTN Publikacije/Publications |
Приказати целокупан запис ставки
SCOPUSTM
Навођења
20
проверено 03.05.2024.
Преглед/и станица
29
Протекла недеља
8
8
Протекли месец
0
0
проверено 10.05.2024.
Google ScholarTM
Проверите
Алт метрика
Ставке на DSpace-у су заштићене ауторским правима, са свим правима задржаним, осим ако није другачије назначено.