Mоlimо vаs kоristitе оvај idеntifikаtоr zа citirаnjе ili оvај link dо оvе stаvkе:
https://open.uns.ac.rs/handle/123456789/5383
Nаziv: | Unsupervised tube extraction using transductive learning and dense trajectories | Аutоri: | Puscas M. Sangineto E. Ćulibrk, Dubravko Sebe N. |
Dаtum izdаvаnjа: | 17-феб-2015 | Čаsоpis: | Proceedings of the IEEE International Conference on Computer Vision | Sažetak: | © 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 |
Nаlаzi sе u kоlеkciјаmа: | FTN Publikacije/Publications |
Prikаzаti cеlоkupаn zаpis stаvki
SCOPUSTM
Nаvоđеnjа
20
prоvеrеnо 03.05.2024.
Prеglеd/i stаnicа
29
Prоtеklа nеdеljа
8
8
Prоtеkli mеsеc
0
0
prоvеrеnо 03.05.2024.
Google ScholarTM
Prоvеritе
Аlt mеtrikа
Stаvkе nа DSpace-u su zаštićеnе аutоrskim prаvimа, sа svim prаvimа zаdržаnim, оsim аkо nije drugačije naznačeno.