Zobrazeno 1 - 10
of 49
pro vyhledávání: '"Enver Sangineto"'
Environments in Reinforcement Learning are usually only partially observable. To address this problem, a possible solution is to provide the agent with information about the past. However, providing complete observations of numerous steps can be exce
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6c358aca7c0b03ff6df20a8b4b540279
http://arxiv.org/abs/2204.03525
http://arxiv.org/abs/2204.03525
Autor:
Jichao Zhang, Enver Sangineto, Hao Tang, Aliaksandr Siarohin, Zhun Zhong, Nicu Sebe, Wei Wang
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031197833
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::de94887d6d544b9837ca7b3a01c27491
https://link.springer.com/chapter/10.1007/978-3-031-19784-0_20#citeas
https://link.springer.com/chapter/10.1007/978-3-031-19784-0_20#citeas
Autor:
Marco De Nadai, Yajing Chen, Bruno Lepri, Wei Wang, Linchao Bao, Nicu Sebe, Enver Sangineto, Haoxian Zhang, Yahui Liu
Publikováno v:
CVPR
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Image-to-Image (I2I) multi-domain translation models are usually evaluated also using the quality of their semantic interpolation results. However, state-of-the-art models frequently show abrupt changes in the image appearance during interpolation, a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9df013810369b2b963f426180e794823
http://arxiv.org/abs/2106.09016
http://arxiv.org/abs/2106.09016
Most domain adaptation methods consider the problem of transferring knowledge to the target domain from a single-source dataset. However, in practical applications, we typically have access to multiple sources. In this paper we propose the first appr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b2558550775348aacce14c28d73df79c
https://hdl.handle.net/11380/1264574
https://hdl.handle.net/11380/1264574
Publikováno v:
WACV
Gaze redirection aims at manipulating the gaze of a given face image with respect to a desired direction (i.e., a reference angle) and it can be applied to many real life scenarios, such as video-conferencing or taking group photos. However, previous
Publikováno v:
European Conference on Computer Vision
European Conference on Computer Vision, Aug 2020, edinburgh, United Kingdom
Computer Vision – ECCV 2020 ISBN: 9783030586034
ECCV (28)
European Conference on Computer Vision, Aug 2020, edinburgh, United Kingdom
Computer Vision – ECCV 2020 ISBN: 9783030586034
ECCV (28)
Continual Learning (CL) aims to develop agents emulating the human ability to sequentially learn new tasks while being able to retain knowledge obtained from past experiences. In this paper, we introduce the novel problem of Memory-Constrained Online
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f010fde3f88fe5f8c08f20d36c707ca6
https://hal.telecom-paris.fr/hal-02941923
https://hal.telecom-paris.fr/hal-02941923
Publikováno v:
ACM Multimedia
In this paper we address the problem of unsupervised gaze correction in the wild, presenting a solution that works without the need for precise annotations of the gaze angle and the head pose. We have created a new dataset called CelebAGaze, which co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dcb771f7e4ff00a3fb3a4b06b375427d
http://arxiv.org/abs/2008.03834
http://arxiv.org/abs/2008.03834
Autor:
Aliaksandr Siarohin, Nicu Sebe, Subhankar Roy, Enver Sangineto, Samuel Rota Bulò, Elisa Ricci
Publikováno v:
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
CVPR
CVPR
A classifier trained on a dataset seldom works on other datasets obtained under different conditions due to domain shift. This problem is commonly addressed by domain adaptation methods. In this work we introduce a novel deep learning framework which
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a9c1470bf31d736005565068892eb86d
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2019
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2019
In this paper, we address the problem of generating person images conditioned on both pose and appearance information. Specifically, given an image xa of a person and a target pose P(xb), extracted from a different image xb, we synthesize a new image
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1fca07c91db4abe434e7cb269ef191c3
Publikováno v:
IEEE Geoscience and Remote Sensing Letters
Hashing methods have been recently found very effective in retrieval of remote sensing (RS) images due to their computational efficiency and fast search speed. The traditional hashing methods in RS usually exploit hand-crafted features to learn hash
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::598550ef05060df23cec67bd2a222381