Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Thalaiyasingam Ajanthan"'
Autor:
Kartik Gupta, Thalaiyasingam Ajanthan
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:6810-6818
Neural network quantization has become increasingly popular due to efficient memory consumption and faster computation resulting from bitwise operations on the quantized networks. Even though they exhibit excellent generalization capabilities, their
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::aea59e8d4fecf3c3301b1da18764b9d3
https://doi.org/10.1609/aaai.v36i6.20637
https://doi.org/10.1609/aaai.v36i6.20637
Publikováno v:
2021 Digital Image Computing: Techniques and Applications (DICTA).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3a0363008cef5a627ef66584a9eb4705
https://doi.org/10.1109/dicta52665.2021.9647143
https://doi.org/10.1109/dicta52665.2021.9647143
Publikováno v:
CVPR
Multi-label submodular Markov Random Fields (MRFs) have been shown to be solvable using max-flow based on an encoding of the labels proposed by Ishikawa, in which each variable $X_i$ is represented by $\ell$ nodes (where $\ell$ is the number of label
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7430cc1facea05cfc708599ade44194b
https://doi.org/10.1109/tpami.2018.2819675
https://doi.org/10.1109/tpami.2018.2819675
Publikováno v:
Computer Vision – ACCV 2020 ISBN: 9783030695347
ACCV (3)
ACCV (3)
Despite the availability of many Markov Random Field (MRF) optimization algorithms, their widespread usage is currently limited due to imperfect MRF modelling arising from hand-crafted model parameters and the selection of inferior inference algorith
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7ba2346eb93df4ff08fb277cfcf69f94
https://doi.org/10.1007/978-3-030-69535-4_32
https://doi.org/10.1007/978-3-030-69535-4_32
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030585853
ECCV (24)
ECCV (24)
Weakly Supervised Object Localization (WSOL) methods only require image level labels as opposed to expensive bounding box annotations required by fully supervised algorithms. We study the problem of learning localization model on target classes with
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5be63ae71ba45a0b5a7b47e489ddc121
https://doi.org/10.1007/978-3-030-58586-0_24
https://doi.org/10.1007/978-3-030-58586-0_24
Autor:
Thalaiyasingam Ajanthan, Alessio Tonioni, Oscar Rahnama, Luigi Di Stefano, Philip H. S. Torr, Thomas Joy
Publikováno v:
CVPR
Real world applications of stereo depth estimation require models that are robust to dynamic variations in the environment. Even though deep learning based stereo methods are successful, they often fail to generalize to unseen variations in the envir
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::beda064e9767bc17bb05b2099ab89251
https://doi.org/10.1109/cvpr.2019.00989
https://doi.org/10.1109/cvpr.2019.00989
Autor:
Adnane Boukhayma, Philip H. S. Torr, Arnab Ghosh, N. Siddharth, Thalaiyasingam Ajanthan, Rodrigo de Bem
Publikováno v:
WACV
We propose a deep generative model of humans in natural images which keeps 2D pose separated from other latent factors of variation, such as background scene and clothing. In contrast to methods that learn generative models of low-dimensional represe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7c016b186af666f6b3f26f3fd6d0ecee
https://doi.org/10.1109/wacv.2019.00159
https://doi.org/10.1109/wacv.2019.00159
Autor:
M. Pawan Kumar, Alban Desmaison, Thomas Joy, Thalaiyasingam Ajanthan, Pushmeet Kohli, Mathieu Salzmann, Rudy Bunel, Philip H. S. Torr
Dense conditional random fields (CRFs) have become a popular framework for modelling several problems in computer vision such as stereo correspondence and multi-class semantic segmentation. By modelling long- range interactions, dense CRFs provide a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d6f687885dbf65f0a3454e153b2c3e51
https://ora.ox.ac.uk/objects/uuid:ccdd914f-013e-4596-9bb7-062eed7dfc7c
https://ora.ox.ac.uk/objects/uuid:ccdd914f-013e-4596-9bb7-062eed7dfc7c
Autor:
Philip H. S. Torr, Arnab Ghosh, Rodrigo de Bem, Thalaiyasingam Ajanthan, N. Siddharth, Ondrej Miksik
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030110116
ECCV Workshops (2)
ECCV Workshops (2)
Deep generative modelling for human body analysis is an emerging problem with many interesting applications. However, the latent space learned by such models is typically not interpretable, resulting in less flexible models. In this work, we adopt a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a59131b5e4455e067d406811d82c58e1
https://doi.org/10.1007/978-3-030-11012-3_38
https://doi.org/10.1007/978-3-030-11012-3_38
Autor:
Adnane Boukhayma, N. Siddharth, Philip H. S. Torr, Ondrej Miksik, Arnab Ghosh, Thalaiyasingam Ajanthan, Rodrigo de Bem
Publikováno v:
de Bem, R, Ghosh, A, Ajanthan, T, Miksik, O, Boukhayma, A, Siddharth, N & Torr, P 2020, ' DGPose: Deep Generative Models for Human Body Analysis ', International Journal of Computer Vision, vol. 128, no. 5, pp. 1537-1563 . https://doi.org/10.1007/s11263-020-01306-1
Deep generative modelling for human body analysis is an emerging problem with many interesting applications. However, the latent space learned by such approaches is typically not interpretable, resulting in less flexibility. In this work, we present
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a58cbc18963bb2ec8536a4d6944f92a1
http://arxiv.org/abs/1804.06364
http://arxiv.org/abs/1804.06364