Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Carl Doersch"'
Autor:
Klaus Greff, Francois Belletti, Lucas Beyer, Carl Doersch, Yilun Du, Daniel Duckworth, David J Fleet, Dan Gnanapragasam, Florian Golemo, Charles Herrmann, Thomas Kipf, Abhijit Kundu, Dmitry Lagun, Issam Laradji, Hsueh-Ti Liu, Henning Meyer, Yishu Miao, Derek Nowrouzezahrai, Cengiz Oztireli, Etienne Pot, Noha Radwan, Daniel Rebain, Sara Sabour, Mehdi S. M. Sajjadi, Matan Sela, Vincent Sitzmann, Austin Stone, Deqing Sun, Suhani Vora, Ziyu Wang, Tianhao Wu, Kwang Moo Yi, Fangcheng Zhong, Andrea Tagliasacchi
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
Publikováno v:
CVPR
We introduce the Action Transformer model for recognizing and localizing human actions in video clips. We repurpose a Transformer-style architecture to aggregate features from the spatiotemporal context around the person whose actions we are trying t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c295fc25f1d86bf915586bf0eb06c4fc
https://doi.org/10.1109/cvpr.2019.00033
https://doi.org/10.1109/cvpr.2019.00033
Publikováno v:
CVPR
We present a bundle-adjustment-based algorithm for recovering accurate 3D human pose and meshes from monocular videos. Unlike previous algorithms which operate on single frames, we show that reconstructing a person over an entire sequence gives extra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dfde20ecdd0662f97cd2ed0ff5b9bbb8
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012304
ECCV (6)
ECCV (6)
Attention mechanisms in biological perception are thought to select subsets of perceptual information for more sophisticated processing which would be prohibitive to perform on all sensory inputs. In computer vision, however, there has been relativel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b81eddb7a4835010d07b71aaa217ce36
https://doi.org/10.1007/978-3-030-01231-1_1
https://doi.org/10.1007/978-3-030-01231-1_1
Autor:
Andrew Zisserman, Carl Doersch
Publikováno v:
ICCV
We investigate methods for combining multiple self-supervised tasks--i.e., supervised tasks where data can be collected without manual labeling--in order to train a single visual representation. First, we provide an apples-to-apples comparison of fou
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::64b11ac7dbdde1509c04bd690c81e26a
http://arxiv.org/abs/1708.07860
http://arxiv.org/abs/1708.07860
Publikováno v:
Computer Vision – ECCV 2016 ISBN: 9783319464770
ECCV (7)
ECCV (7)
In a given scene, humans can easily predict a set of immediate future events that might happen. However, pixel-level anticipation in computer vision is difficult because machine learning struggles with the ambiguity in predicting the future. In this
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5b0ce9ad5292b83caa9b3c78ac37d814
https://doi.org/10.1007/978-3-319-46478-7_51
https://doi.org/10.1007/978-3-319-46478-7_51
Publikováno v:
Communications of the ACM
Communications of the ACM, 2015, 58 (12), pp.103-110. ⟨10.1145/2830541⟩
Communications of the ACM, Association for Computing Machinery, 2015, 58 (12), pp.103-110. ⟨10.1145/2830541⟩
ACM Transactions on Graphics
ACM Transactions on Graphics, 2012, 31 (4)
ACM Transactions on Graphics, Association for Computing Machinery, 2012, 31 (4)
Communications of the ACM, 2015, 58 (12), pp.103-110. ⟨10.1145/2830541⟩
Communications of the ACM, Association for Computing Machinery, 2015, 58 (12), pp.103-110. ⟨10.1145/2830541⟩
ACM Transactions on Graphics
ACM Transactions on Graphics, 2012, 31 (4)
ACM Transactions on Graphics, Association for Computing Machinery, 2012, 31 (4)
Given a large repository of geo-tagged imagery, we seek to automatically find visual elements, for example windows, balconies, and street signs, that are most distinctive for a certain geo-spatial area, for example the city of Paris. This is a tremen
Publikováno v:
ICCV
This work explores the use of spatial context as a source of free and plentiful supervisory signal for training a rich visual representation. Given only a large, unlabeled image collection, we extract random pairs of patches from each image and train
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1d3b548b088d2db2e5f95f386a421307
http://arxiv.org/abs/1505.05192
http://arxiv.org/abs/1505.05192
Publikováno v:
Computer Vision – ECCV 2014 ISBN: 9783319105772
ECCV (3)
ECCV (3)
This paper addresses the well-established problem of unsupervised object discovery with a novel method inspired by weakly-supervised approaches. In particular, the ability of an object patch to predict the rest of the object (its context) is used as
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f07fe11598b70dc25f3a52e173c8e7cb
https://doi.org/10.1007/978-3-319-10578-9_24
https://doi.org/10.1007/978-3-319-10578-9_24
Publikováno v:
CVPR
Optical character recognition (OCR) remains a difficult problem for noisy documents or documents not scanned at high resolution. Many current approaches rely on stored font models that are vulnerable to cases in which the document is noisy or is writ