Zobrazeno 1 - 10
of 264
pro vyhledávání: '"PSI_VISICS"'
Publikováno v:
Multimedia Tools and Applications. 76:22599-22622
We propose a novel weakly supervised framework that jointly tackles entity analysis tasks in vision and language. Given a video with subtitles, we jointly address the questions: a) What do the textual entity mentions refer to? and b) What/ who are in
Publikováno v:
Computer Vision and Image Understanding. 142:1-12
© 2015 Elsevier Inc. All rights reserved. Recent algorithms for exemplar-based single image super-resolution have shown impressive results, mainly due to well-chosen priors and recently also due to more accurate blur kernels. Some methods exploit cl
Publikováno v:
International Journal of Computer Vision. 118:22-48
© 2015, Springer Science+Business Media New York. We propose a novel approach for semantic segmentation of building facades. Our system consists of three distinct layers, representing different levels of abstraction in facade images: segments, objec
Publikováno v:
WACV
© 2018 IEEE. The promise of self-driving cars promotes several advantages, e.g. they have the ability to outperform human drivers while being safer. Here we take a deeper look into some aspects from algorithms aimed at making this promise a reality.
Autor:
Dries Hulens, Tinne Tuytelaars, Luc Van Gool, Toon Goedemé, Joost Vennekens, Bram Aerts, Luc Van Eycken, Hugo Van hamme, Tom Roussel, Ali Diba, Punarjay Chakravarty, Jeroen Zegers
Publikováno v:
MultiMedia Modeling ISBN: 9783319736020
MMM (1)
MMM (1)
In this paper, we demonstrate a system that automates the process of recording video lectures in classrooms. Through special hard-ware (lecturer and audience facing cameras and microphone arrays), we record multiple points of view of the lecture. Per
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::858d44e1b2ab8243e75b98b4d2c560ad
https://doi.org/10.1007/978-3-319-73603-7_42
https://doi.org/10.1007/978-3-319-73603-7_42
Autor:
Tinne Tuytelaars, Roeland De Geest
Publikováno v:
WACV
© 2018 IEEE. Online action detection is a challenging problem: A system needs to decide what action is happening at the current frame, based on previous frames only. Fortunately in real-life, human actions are not independent from one another: There
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::955f3f3a0bf7853502dafba5b2acd203
https://lirias.kuleuven.be/handle/123456789/612004
https://lirias.kuleuven.be/handle/123456789/612004
Autor:
Basura Fernando, Tinne Tuytelaars, Cees G. M. Snoek, Arnold W. M. Smeulders, Efstratios Gavves
Publikováno v:
International Journal of Computer Vision
International Journal of Computer Vision, 111(2), 191-212. Springer Netherlands
International Journal of Computer Vision, 111(2), 191-212. Springer Netherlands
The aim of this paper is fine-grained categorization without human interaction. Different from prior work, which relies on detectors for specific object parts, we propose to localize distinctive details by roughly aligning the objects using just the
Publikováno v:
Clapés, A, Tuytelaars, T & Escalera, S 2017, Darwintrees for action recognition . in Proceedings-2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017 . IEEE Signal Processing Society, Proceedings-2017 IEEE International Conference on Computer Vision Workshops, ICCVW 2017, vol. 2018-January, pp. 3169-3178, 16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017, Venice, Italy, 22/10/2017 . https://doi.org/10.1109/ICCVW.2017.375
ICCV Workshops
ICCV Workshops
© 2017 IEEE. We propose a novel mid-level representation for action/activity recognition on RGB videos. We model the evolution of improved dense trajectory features not only for the entire video sequence, but also on subparts of the video. Subparts
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bc30f80d228ca8e8b999b75fb093fbd4
https://lirias.kuleuven.be/handle/123456789/612010
https://lirias.kuleuven.be/handle/123456789/612010
Autor:
Georgoulis, Stamatios
In this thesis, we try to reverse the image formation process, enabling computers to factor images into their intrinsic components, i.e. 3D shape, surface reflectance, environmental illumination. On the one hand, traditional approaches have relied on
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1131::ded0233370306c224aa5648a3f8f75f2
https://lirias.kuleuven.be/handle/123456789/587188
https://lirias.kuleuven.be/handle/123456789/587188
Most approaches for instance-aware semantic labeling traditionally focus on accuracy. Other aspects like runtime and memory footprint are arguably as important for real-time applications such as autonomous driving. Motivated by this observation and i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8add534242b0837af66e81dce8ce09d4
http://arxiv.org/abs/1708.02550
http://arxiv.org/abs/1708.02550