Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Vujasinovic, Stephane"'
Autor:
Vujasinović, Stéphane, Becker, Stefan, Bullinger, Sebastian, Scherer-Negenborn, Norbert, Arens, Michael
In this paper, we introduce a variant of video object segmentation (VOS) that bridges interactive and semi-automatic approaches, termed Lazy Video Object Segmentation (ziVOS). In contrast, to both tasks, which handle video object segmentation in an o
Externí odkaz:
http://arxiv.org/abs/2408.00169
Autor:
Vujasinović, Stéphane, Bullinger, Sebastian, Becker, Stefan, Scherer-Negenborn, Norbert, Arens, Michael, Stiefelhagen, Rainer
Publikováno v:
34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023
We present READMem (Robust Embedding Association for a Diverse Memory), a modular framework for semi-automatic video object segmentation (sVOS) methods designed to handle unconstrained videos. Contemporary sVOS works typically aggregate video frames
Externí odkaz:
http://arxiv.org/abs/2305.12823
Autor:
Vujasinovic, Stephane, Bullinger, Sebastian, Becker, Stefan, Scherer-Negenborn, Norbert, Arens, Michael, Stiefelhagen, Rainer
Publikováno v:
IEEE International Conference on Image Processing (ICIP), 2022, pp. 2756-2760
While current methods for interactive Video Object Segmentation (iVOS) rely on scribble-based interactions to generate precise object masks, we propose a Click-based interactive Video Object Segmentation (CiVOS) framework to simplify the required use
Externí odkaz:
http://arxiv.org/abs/2203.01784
Autor:
Vujasinović, Stéphane, Becker, Stefan, Breuer, Timo, Bullinger, Sebastian, Scherer-Negenborn, Norbert, Arens, Michael
Publikováno v:
Vujasinovi\'c, S.; Becker, S.; Breuer, T.; Bullinger, S.; Scherer-Negenborn, N.; Arens, M. Integration of the 3D Environment for UAV Onboard Visual Object Tracking. Appl. Sci. 2020, 10, 7622
Single visual object tracking from an unmanned aerial vehicle (UAV) poses fundamental challenges such as object occlusion, small-scale objects, background clutter, and abrupt camera motion. To tackle these difficulties, we propose to integrate the 3D
Externí odkaz:
http://arxiv.org/abs/2008.02834
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.