Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Puneet K. Dokania"'
Autor:
Thomas Tanay, Aivar Sootla, Matteo Maggioni, Puneet K. Dokania, Philip Torr, Ales Leonardis, Gregory Slabaugh
Recurrent models are a popular choice for video enhancement tasks such as video denoising or super-resolution. In this work, we focus on their stability as dynamical systems and show that they tend to fail catastrophically at inference time on long v
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::791e6dfde3945c5d5c6581b19caf66da
http://arxiv.org/abs/2010.05099
http://arxiv.org/abs/2010.05099
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585358
ECCV (2)
ECCV (2)
We discuss a general formulation for the Continual Learning (CL) problem for classification—a learning task where a stream provides samples to a learner and the goal of the learner, depending on the samples it receives, is to continually upgrade it
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cdd5499db7d7753059bb7afd8456b44f
https://ora.ox.ac.uk/objects/uuid:64d21a33-3792-40ae-ae82-becd87f32757
https://ora.ox.ac.uk/objects/uuid:64d21a33-3792-40ae-ae82-becd87f32757
Autor:
Arnab Ghosh, Richard Zhang, Eli Shechtman, Oliver Wang, Puneet K. Dokania, Alexei A. Efros, Philip H. S. Torr
Publikováno v:
ICCV
We propose an interactive GAN-based sketch-to-image translation method that helps novice users create images of simple objects. As the user starts to draw a sketch of a desired object type, the network interactively recommends plausible completions,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::73ed519dcb4e63553f0c5348c82a0407
Publikováno v:
IEEE journal of biomedical and health informatics. 23(4)
Deformable registration has been one of the pillars of biomedical image computing. Conventional approaches refer to the definition of a similarity criterion that, once endowed with a deformation model and a smoothness constraint, determines the optim
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1660ac78941f26f342a9f3a8677ab6fd
https://pubmed.ncbi.nlm.nih.gov/30207969
https://pubmed.ncbi.nlm.nih.gov/30207969
Publikováno v:
CVPR
We present FlipDial, a generative model for visual dialogue that simultaneously plays the role of both participants in a visually-grounded dialogue. Given context in the form of an image and an associated caption summarising the contents of the image
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d48116790054289389825ef0056df165
http://arxiv.org/abs/1802.03803
http://arxiv.org/abs/1802.03803
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012519
ECCV (11)
ECCV (11)
Incremental learning (IL) has received a lot of attention recently, however, the literature lacks a precise problem definition, proper evaluation settings, and metrics tailored specifically for the IL problem. One of the main objectives of this work
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c92469f7bbd24fe2ac143038381b69be
http://arxiv.org/abs/1801.10112
http://arxiv.org/abs/1801.10112
Publikováno v:
ICCV
Compressing large Neural Networks (NN) by quantizing the parameters, while maintaining the performance is highly desirable due to reduced memory and time complexity. In this work, we cast NN quantization as a discrete labelling problem, and by examin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::54dd00df39dd60fd1f7e9a42cc941d22
Autor:
Yunchao Wei, Philip H. S. Torr, Puneet K. Dokania, Qibin Hou, Daniela Massiceti, Ming-Ming Cheng
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319781983
EMMCVPR
EMMCVPR
We consider the task of learning a classifier for semantic segmentation using weak supervision in the form of image labels which specify the object classes present in the image. Our method uses deep convolutional neural networks (CNNs) and adopts an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e4f1c29d26e391e8103e02781f5f06e6
Publikováno v:
Computer Vision – ECCV 2016 ISBN: 9783319464534
ECCV (5)
ECCV (5)
We propose a novel partial linearization based approach for optimizing the multi-class svm learning problem. Our method is an intuitive generalization of the Frank-Wolfe and the exponentiated gradient algorithms. In particular, it allows us to combin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::83da91d9daebe57dc13c76e39b9a5ac1
https://doi.org/10.1007/978-3-319-46454-1_51
https://doi.org/10.1007/978-3-319-46454-1_51
Autor:
Puneet K. Dokania, M. Pawan Kumar
Publikováno v:
ICCV 2015-International Conference on Computer Vision 2015
ICCV 2015-International Conference on Computer Vision 2015, Dec 2015, Santiago, Chile. ⟨10.1109/ICCV.2015.205⟩
ICCV 2015-International Conference on Computer Vision 2015, Dec 2015, Santiago, Chile. ⟨10.1109/ICCV.2015.205⟩
International audience; We propose a new family of discrete energy minimization problems, which we call parsimonious labeling. Our energy function consists of unary potentials and high-order clique potentials. While the unary potentials are arbitrary
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2002bb7e654f18fc840913dc3bc05147
https://doi.org/10.1109/iccv.2015.205
https://doi.org/10.1109/iccv.2015.205