Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Stamatios Georgoulis"'
Autor:
Patricia Vitoria, Stamatios Georgoulis, Stepan Tulyakov, Alfredo Bochicchio, Julius Erbach, Yuanyou Li
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031250712
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bd9bb05a07f0257ddc472ab2be5d4823
https://doi.org/10.1007/978-3-031-25072-9_7
https://doi.org/10.1007/978-3-031-25072-9_7
Autor:
Stepan Tulyakov, Alfredo Bochicchio, Daniel Gehrig, Stamatios Georgoulis, Yuanyou Li, Davide Scaramuzza
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::357c326905565e00de6d548c32063fa9
https://doi.org/10.1109/cvpr52688.2022.01723
https://doi.org/10.1109/cvpr52688.2022.01723
The ability to make educated predictions about their surroundings, and associate them with certain confidence, is important for intelligent systems, like autonomous vehicles and robots. It allows them to plan early and decide accordingly. Motivated b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::67c6b7dd4d2008feced3cd31d39c34ed
http://arxiv.org/abs/2204.01267
http://arxiv.org/abs/2204.01267
Autor:
Nico Messikommer, Stamatios Georgoulis, Daniel Gehrig, Stepan Tulyakov, Julius Erbach, Alfredo Bochicchio, Yuanyou Li, Davide Scaramuzza
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Modern high dynamic range (HDR) imaging pipelines align and fuse multiple low dynamic range (LDR) images captured at different exposure times. While these methods work well in static scenes, dynamic scenes remain a challenge since the LDR images stil
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::87731ccbc603e9865a91b355dbc57d92
http://arxiv.org/abs/2203.06622
http://arxiv.org/abs/2203.06622
Autor:
Stamatios Georgoulis, Davide Scaramuzza, Li Yuanyou, Daniel Gehrig, Julius Erbach, Mathias Gehrig, Stepan Tulyakov
Publikováno v:
CVPR
State-of-the-art frame interpolation methods generate intermediate frames by inferring object motions in the image from consecutive key-frames. In the absence of additional information, first-order approximations, i.e. optical flow, must be used, but
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a775170b9e11b1ddea1764a092017232
https://doi.org/10.1109/cvpr46437.2021.01589
https://doi.org/10.1109/cvpr46437.2021.01589
Autor:
Marc Proesmans, Wouter Van Gansbeke, Simon Vandenhende, Stamatios Georgoulis, Dengxin Dai, Luc Van Gool
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 44(7)
With the advent of deep learning, many dense prediction tasks, i.e. tasks that produce pixel-level predictions, have seen significant performance improvements. The typical approach is to learn these tasks in isolation, that is, a separate neural netw
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f92255af108f021d54620e20b15695a4
https://pubmed.ncbi.nlm.nih.gov/33497328
https://pubmed.ncbi.nlm.nih.gov/33497328
Autor:
Anton Obukhov, Suman Saha, Yuhua Chen, Stamatios Georgoulis, Luc Van Gool, Menelaos Kanakis, Danda Pani Paudel
Publikováno v:
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
CVPR
CVPR
We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting. Semantic segmentation and monocular depth estimation are shown to be complementary tasks; in a multi-task l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::53499130c3e32ffe00cd8d79744bb766
Autor:
Wenhao Xu, Stamatios Georgoulis, Suman Saha, Menelaos Kanakis, Danda Pani Paudel, Yuhua Chen, Luc Van Gool
Publikováno v:
CVPR Workshops
Nowadays, the increasingly growing number of mobile and computing devices has led to a demand for safer user authentication systems. Face anti-spoofing is a measure towards this direction for bio-metric user authentication, and in particular face rec
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0944065f13cdbb0258e19ea1b6d3a35a
https://lirias.kuleuven.be/handle/123456789/670405
https://lirias.kuleuven.be/handle/123456789/670405
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585471
ECCV (4)
ECCV (4)
In this paper, we argue about the importance of considering task interactions at multiple scales when distilling task information in a multi-task learning setup. In contrast to common belief, we show that tasks with high affinity at a certain scale a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0a313afd6189ee6a7c1ab1982d88ac4c
https://doi.org/10.1007/978-3-030-58548-8_31
https://doi.org/10.1007/978-3-030-58548-8_31
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030586065
ECCV (10)
ECCV (10)
Can we automatically group images into semantically meaningful clusters when ground-truth annotations are absent? The task of unsupervised image classification remains an important, and open challenge in computer vision. Several recent approaches hav
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f2e6bbd37f0c4ca4a9a57064f6875512